Proceedings of the 23rd International Conference on Pattern Recognition
ICPR, 2016.

@proceedings{ICPR-2016,
	ee            = "https://ieeexplore.ieee.org/xpl/conhome/7893644/proceeding",
	isbn          = "978-1-5090-4847-2",
	publisher     = "{IEEE}",
	title         = "{Proceedings of the 23rd International Conference on Pattern Recognition}",
	year          = 2016,
}

Contents (708 items)

ICPR-2016-GrantSZG #network #predict #visualisation

Predicting and visualizing psychological attributions with a deep neural network (EG, SS, MZ, MvG), pp. 1–6.

ICPR-2016-WangLLGTO #gesture #network #recognition #scalability #using

Large-scale Isolated Gesture Recognition using Convolutional Neural Networks (PW, WL, SL, ZG, CT, PO), pp. 7–12.

ICPR-2016-WangLLZGO #gesture #network #recognition #scalability #using

Large-scale Continuous Gesture Recognition Using Convolutional Neural Networks (PW, WL, SL, YZ, ZG, PO), pp. 13–18.

ICPR-2016-ZhuZMSSS #3d #gesture #network #recognition #scalability #using

Large-scale Isolated Gesture Recognition using pyramidal 3D convolutional networks (GZ, LZ0, LM, JS, JS, PS), pp. 19–24.

ICPR-2016-LiMTFXLS #3d #data-driven #database #gesture #recognition #scalability

Large-scale gesture recognition with a fusion of RGB-D data based on the C3D model (YL, QM, KT, YF, XX, RL, JS), pp. 25–30.

ICPR-2016-ChaiLYLC #gesture #network #recognition #scalability

Two streams Recurrent Neural Networks for Large-Scale Continuous Gesture Recognition (XC, ZL, FY, ZL, XC), pp. 31–36.

ICPR-2016-AydinKAA #automation #predict #random #using

Automatic personality prediction from audiovisual data using random forest regression (BA, AAK, OA, LA), pp. 37–42.

ICPR-2016-GurpinarKS #estimation #multimodal

Multimodal fusion of audio, scene, and face features for first impression estimation (FG, HK, AAS), pp. 43–48.

ICPR-2016-CamgozHKB #3d #gesture #independence #network #recognition #using

Using Convolutional 3D Neural Networks for User-independent continuous gesture recognition (NCC, SH, OK, RB), pp. 49–54.

ICPR-2016-Rai #recognition

Bi-modal regression for Apparent Personality trait Recognition (NR), pp. 55–60.

ICPR-2016-NorooziMNEA #classification #predict #recognition

Fusion of classifier predictions for audio-visual emotion recognition (FN, MM, AN, SE, GA), pp. 61–66.

ICPR-2016-EscalanteP0RCCE #analysis #challenge #contest #multi #overview #perspective #visual notation

ChaLearn Joint Contest on Multimedia Challenges Beyond Visual Analysis: An overview (HJE, VPL, JW0, MAR, BC, AC, SE, IG, XB, PH, HM, MAL), pp. 67–73.

ICPR-2016-LovellPSVW #analysis #contest #image #pattern matching #pattern recognition #recognition

International Contest on Pattern Recognition techniques for indirect immunofluorescence images analysis (BCL, GP, AS, MV, AW), pp. 74–76.

ICPR-2016-JiaSZY #classification #network

Deep convolutional neural network based HEp-2 cell classification (XJ, LS, XZ, SY), pp. 77–80.

ICPR-2016-Al-DulaimiBTC #automation #geometry #image #segmentation #set #using

Automatic segmentation of HEp-2 cell Fluorescence microscope images using level set method via geometric active contours (KAD, JB, ITR, VC), pp. 81–83.

ICPR-2016-BSSH #approach #classification #network #using

HEp-2 cell classification using artificial neural network approach (DB, KS, NH), pp. 84–89.

ICPR-2016-PrasathKOGHSP #classification #random #segmentation #using

HEp-2 cell classification and segmentation using motif texture patterns and spatial features with random forests (VBSP, YMK, ZAO, JBG, AH, GS, KP), pp. 90–95.

ICPR-2016-LiSZY #classification #network

HEp-2 specimen classification with fully convolutional network (YL, LS, XZ, SY), pp. 96–100.

ICPR-2016-HalfaouiBU #estimation

CNN-based initial background estimation (IH, FB, OU), pp. 101–106.

ICPR-2016-LaugraudPD #generative #named

LaBGen-P: A pixel-level stationary background generation method based on LaBGen (BL, SP, MVD), pp. 107–113.

ICPR-2016-OrtegoSM #dataset #estimation #multi #re-engineering

Rejection based multipath reconstruction for background estimation in SBMnet 2016 dataset (DO, JCS, JMM0), pp. 114–119.

ICPR-2016-JavedJMB #graph #modelling

Motion-Aware Graph Regularized RPCA for background modeling of complex scenes (SJ, SKJ, AM, TB), pp. 120–125.

ICPR-2016-MinematsuST #analysis #bidirectional

Background initialization based on bidirectional analysis and consensus voting (TM, AS, RiT), pp. 126–131.

ICPR-2016-LiuCZLG #estimation

Scene background estimation based on temporal median filter with Gaussian filtering (WL0, YC, MZ, HL, HG), pp. 132–136.

ICPR-2016-MurguiaRA #adaptation #architecture #dataset #evaluation #modelling #network #parallel

Evaluation of the background modeling method Auto-Adaptive Parallel Neural Network Architecture in the SBMnet dataset (MICM, JARQ, GRA), pp. 137–142.

ICPR-2016-MaddalenaP #image #multi

Extracting a background image by a multi-modal scene background model (LM0, AP), pp. 143–148.

ICPR-2016-SantanaMNNP #challenge #contest #evaluation #mobile

Mobile Iris CHallenge Evaluation II: Results from the ICPR competition (MCS, MDM, MN, FN, HP), pp. 149–154.

ICPR-2016-AbateBGN #mobile #named #recognition

SKIPSOM: Skewness & kurtosis of iris pixels in Self Organizing Maps for iris recognition on mobile devices (AFA, SB, LG, FN), pp. 155–159.

ICPR-2016-GaldiD #mobile #performance #recognition

Fusing iris colour and texture information for fast iris recognition on mobile devices (CG, JLD), pp. 160–164.

ICPR-2016-AginakoMSSL #mobile #verification

Local descriptors fusion for mobile iris verification (NA, JMMO, BS, MCS, JLN), pp. 165–169.

ICPR-2016-AginakoMRLS #approach #difference #machine learning

Machine Learning approach to dissimilarity computation: Iris matching (NA, JMMO, IRR, EL, BS), pp. 170–175.

ICPR-2016-AhmedCSNN #image #smarttech #using

Using fusion of iris code and periocular biometric for matching visible spectrum iris images captured by smart phone cameras (NUA, SC, EHS, AN, IN), pp. 176–180.

ICPR-2016-AhujaIBD #case study #verification

A preliminary study of CNNs for iris and periocular verification in the visible spectrum (KA, RI, FAB, KD), pp. 181–186.

ICPR-2016-ZayeneHTMHIA #contest #detection #recognition #video

ICPR2016 contest on Arabic Text detection and Recognition in video frames - AcTiVComp (OZ, NH, SMT, SBM, JH, RI, NEBA), pp. 187–191.

ICPR-2016-MeijerT #set #validation

Regularizing AdaBoost with validation sets of increasing size (DWJM, DMJT), pp. 192–197.

ICPR-2016-ZorYMWKA #matrix #named #optimisation

BeamECOC: A local search for the optimization of the ECOC matrix (CZ, BAY, EM, TW, JK, EA), pp. 198–203.

ICPR-2016-SoleymaniGF #learning

Loss factors for learning Boosting ensembles from imbalanced data (RS, EG, GF), pp. 204–209.

ICPR-2016-LoogY #consistency #empirical #learning #nondeterminism

An empirical investigation into the inconsistency of sequential active learning (ML, YY), pp. 210–215.

ICPR-2016-RoyCSC #classification #predict

Meta-regression based pool size prediction scheme for dynamic selection of classifiers (AR, RMOC, RS, GDCC), pp. 216–221.

ICPR-2016-HajduTKH #approach #constraints #execution #probability

Composing ensembles by a stochastic approach under execution time constraint (AH, HT, LK, LH), pp. 222–227.

ICPR-2016-XieL #re-engineering

Flip-avoiding interpolating surface registration for skull reconstruction (SX, WKL), pp. 228–233.

ICPR-2016-SagawaSHOKF #automation #feature model #robust #using

Automatic feature extraction using CNN for robust active one-shot scanning (RS, YS, TH, SO, HK, RF), pp. 234–239.

ICPR-2016-BullingerBWA #bound #generative #re-engineering #using #video

Moving object reconstruction in monocular video data using boundary generation (SB, CB, SW, MA), pp. 240–246.

ICPR-2016-DanelljanMKF #probability #set

Aligning the dissimilar: A probabilistic method for feature-based point set registration (MD, GM, FSK, MF), pp. 247–252.

ICPR-2016-Roman-RangelM

Indexing Mayan hieroglyphs with neural codes (ERR, SMM), pp. 253–258.

ICPR-2016-LiaoQL #image #learning #multi

Semisupervised manifold learning for color transfer between multiview images (DL, YQ, ZNL), pp. 259–264.

ICPR-2016-TangLLHCF #self

Camera self-calibration from tracking of moving persons (ZT, YSL, KHL, JNH, JHC, ZF), pp. 265–270.

ICPR-2016-SorelB #multi #performance

Efficient JPEG decompression by the alternating direction method of multipliers (MS, MB), pp. 271–276.

ICPR-2016-NakamuraOB #detection #process

Detection of groups in crowd considering their activity state (KN, TO, NB), pp. 277–282.

ICPR-2016-WangLHX #clustering #image #multi #representation

Manifold Regularized Multi-view Subspace Clustering for image representation (LW0, DL, TH, ZX), pp. 283–288.

ICPR-2016-Lezoray #image #using

High dynamic range image processing using manifold-based ordering (OL), pp. 289–294.

ICPR-2016-ChenWWGSJ #hybrid #multi #video

Implicit hybrid video emotion tagging by integrating video content and users' multiple physiological responses (SC, SW, CW, ZG, XS, QJ), pp. 295–300.

ICPR-2016-WuWZGYJ #recognition

Employing subjects' information as privileged information for emotion recognition from EEG signals (SW, SW, YZ, ZG, LY, QJ), pp. 301–306.

ICPR-2016-CirakmanG #online

Online speaker emotion tracking with a dynamic state transition model (OC, BG), pp. 307–312.

ICPR-2016-ChenQYJ #bidirectional #network

Face alignment with Cascaded Bidirectional LSTM Neural Networks (YC, JQ, JY0, ZJ), pp. 313–318.

ICPR-2016-GrimmMBS #classification #using

Sleep position classification from a depth camera using Bed Aligned Maps (TG, MM, AB, RS), pp. 319–324.

ICPR-2016-FengLL #effectiveness #learning #using

Learning effective Gait features using LSTM (YF0, YL, JL), pp. 325–330.

ICPR-2016-KondratevS #automation #constraints #detection #geometry #image #using

Automatic detection of laser-induced structures in live cell fluorescent microscopy images using snakes with geometric constraints (AYK, DVS), pp. 331–336.

ICPR-2016-JafariKNSSWN #image #learning #segmentation #using

Skin lesion segmentation in clinical images using deep learning (MHJ, NK, ENE, SS, SMRS, KRW, KN), pp. 337–342.

ICPR-2016-KrompAWBDBGTAH #framework #image #machine learning

Machine learning framework incorporating expert knowledge in tissue image annotation (FK, IA, TW, DB, HD, MB, TG, STM, PA, AH), pp. 343–348.

ICPR-2016-NgoSMXC #analysis

Quantitative analysis of facial paralysis based on limited-orientation modified circular Gabor filters (THN, MS, NM, WX0, YWC), pp. 349–354.

ICPR-2016-LiaoLL #classification #multi #network #robust #using

Skin disease classification versus skin lesion characterization: Achieving robust diagnosis using multi-label deep neural networks (HL, YL, JL), pp. 355–360.

ICPR-2016-BobbiaBD #segmentation

Remote photoplethysmography based on implicit living skin tissue segmentation (SB, YB, JD), pp. 361–365.

ICPR-2016-WeiLSKM #learning #taxonomy

Joint learning dictionary and discriminative features for high dimensional data (XW, YL, HS, MK, YLM), pp. 366–371.

ICPR-2016-LittwinW #complexity #multi #network

Complexity of multiverse networks and their multilayer generalization (EL, LW), pp. 372–377.

ICPR-2016-MelekhovKR #image #network

Siamese network features for image matching (IM, JK, ER), pp. 378–383.

ICPR-2016-CaoN #fine-grained #learning #process #recognition

Exploring deep learning based solutions in fine grained activity recognition in the wild (SC, RN), pp. 384–389.

ICPR-2016-QuachDLB #modelling #robust

Robust Deep Appearance Models (KGQ, CND, KL, TDB), pp. 390–395.

ICPR-2016-Bai0CH #kernel #transitive

A transitive aligned Weisfeiler-Lehman subtree kernel (LB0, LR0, LC, ERH), pp. 396–401.

ICPR-2016-AwateDK #kernel #robust

Robust kernel principal nested spheres (SPA, MD, NK), pp. 402–407.

ICPR-2016-CavazzaZSM #kernel #recognition

Kernelized covariance for action recognition (JC, AZ, MSB, VM), pp. 408–413.

ICPR-2016-LiTY #fault

Refining pre-image via error compensation for KPCA-based pattern de-noising (JL, QT, ZY), pp. 414–419.

ICPR-2016-FragosoSHT

One-class slab support vector machine (VF, WJS, JPH, MT), pp. 420–425.

ICPR-2016-KouwL #estimation #on the #parametricity

On regularization parameter estimation under covariate shift (WMK, ML), pp. 426–431.

ICPR-2016-CapuaNP #detection #network #social

Unsupervised cyber bullying detection in social networks (MDC, EDN, AP), pp. 432–437.

ICPR-2016-KimuraKSK #classification #multi #performance #random #scalability

Fast random k-labELsets for large-scale multi-label classification (KK, MK, LS, SK), pp. 438–443.

ICPR-2016-HuangWLLBC #automation #clustering #estimation #learning #parametricity

Ensemble-driven support vector clustering: From ensemble learning to automatic parameter estimation (DH, CDW, JHL, YL0, SB, YC), pp. 444–449.

ICPR-2016-BandyopadhyayM #axiom #clustering #incremental #performance

Axioms to characterize efficient incremental clustering (SB, MNM), pp. 450–455.

ICPR-2016-GuanZXCT

WENN for individualized cleaning in imbalanced data (HG, YZ, MX, HDC, XT), pp. 456–461.

ICPR-2016-GuoCL #learning #multi

Multi-label learning with globAl densiTy fusiOn Mapping features (YG, FC, GL0), pp. 462–467.

ICPR-2016-HouP #clustering #kernel

A new density kernel in density peak based clustering (JH, MP), pp. 468–473.

ICPR-2016-KaremF #concept #learning #multi

Multiple Instance Learning with multiple positive and negative target concepts (AK, HF), pp. 474–479.

ICPR-2016-FioriMF #classification #design #multi

An optimal multiclass classifier design (MF, MDM, AF), pp. 480–485.

ICPR-2016-KawanishiDIMF #classification #learning #robust

Misclassification tolerable learning for robust pedestrian orientation classification (YK, DD, II, HM, HF), pp. 486–491.

ICPR-2016-YildizU #classification #incremental #order #using

Incremental construction of rule ensembles using classifiers produced by different class orderings (OTY, AU), pp. 492–497.

ICPR-2016-NguyenNLP #distributed

Distributed data augmented support vector machine on Spark (TDN, VN0, TL, DQP), pp. 498–503.

ICPR-2016-HsuCH #representation #using #verification

Object verification in two views using Sparse representation (SCH, ICC, CLH), pp. 504–509.

ICPR-2016-MygdalisTP #geometry

Exploiting local and global geometric data relationships in Support Vector Data Description (VM, AT, IP), pp. 515–519.

ICPR-2016-SaikiaSSKG #analysis #kernel #learning #multi #using

Multiple kernel learning using data envelopment analysis and feature vector selection and projection (GS, SS, VVS, RDK, PG), pp. 520–524.

ICPR-2016-RedkoB #kernel #learning

Kernel alignment for unsupervised transfer learning (IR, YB), pp. 525–530.

ICPR-2016-VinhEPBLR #modelling #random #robust #using

Training robust models using Random Projection (XVN, SME, SP, JB0, CL, KR), pp. 531–536.

ICPR-2016-Saha0PV #learning #problem #visual notation

Transfer learning for rare cancer problems via Discriminative Sparse Gaussian Graphical model (BS, SG0, DQP, SV), pp. 537–542.

ICPR-2016-YangSZ #detection #network

A joint facial point detection method of deep convolutional network and shape regression (TY, CS, NZ), pp. 543–548.

ICPR-2016-GarciaHSFTB #segmentation #semantics

Semantic segmentation priors for object discovery (GMG, FH, HS, SF, CT, SB), pp. 549–554.

ICPR-2016-ZhangWY #correlation #image #using

Theoretical criterion for image matching using GPT correlation (SZ, TW, YY), pp. 555–560.

ICPR-2016-TakabeTKSMNY #consistency #detection #using

Moving object detection from a point cloud using photometric and depth consistencies (AT, HT, NK, TS, TM, SN, NY), pp. 561–566.

ICPR-2016-YangLWW #empirical #performance

An Empirical Study of Deformable Part Model with fast feature pyramid (JY, GL, WW, RW), pp. 567–572.

ICPR-2016-LeZZLS #detection #robust

Robust hand detection in Vehicles (THNL, CZ, YZ, KL, MS), pp. 573–578.

ICPR-2016-LiH #approach #detection #image #performance

A fast approach for traffic panel detection from natural scene images (ZML, LLH), pp. 579–584.

ICPR-2016-PangN #3d #detection #multi #network

3D point cloud object detection with multi-view convolutional neural network (GP, UN), pp. 585–590.

ICPR-2016-Yamada #detection #network

Pedestrian detection with a resolution-aware convolutional network (KY), pp. 591–596.

ICPR-2016-LangenkamperN #architecture #classification #detection #learning #online #realtime

COATL - a learning architecture for online real-time detection and classification assistance for environmental data (DL, TWN), pp. 597–602.

ICPR-2016-BulatovS #detection #segmentation

Segmentation methods for detection of stationary vehicles in combined elevation and optical data (DB, HS), pp. 603–608.

ICPR-2016-KimP #approach #detection #network #using

A shape preserving approach for salient object detection using convolutional neural networks (JK, VP), pp. 609–614.

ICPR-2016-ChenWHF #detection #estimation #learning

Deep learning for integrated hand detection and pose estimation (TYC, MYW, YHH, LCF), pp. 615–620.

ICPR-2016-ChoiKPS #detection #multi #network

Multi-spectral pedestrian detection based on accumulated object proposal with fully convolutional networks (HC, SK, KP, KS), pp. 621–626.

ICPR-2016-WarisIG #using

Object proposals using CNN-based edge filtering (MAW, AI, MG), pp. 627–632.

ICPR-2016-YangN #detection #multi #network

A multi-scale cascade fully convolutional network face detector (ZY, RN), pp. 633–638.

ICPR-2016-HuangWL #detection

Egocentric hand detection via region growth (SH, WW, KL), pp. 639–644.

ICPR-2016-FengSZ #detection #multi

Scene text detection based on multi-scale SWT and edge filtering (YF, YS, YZ0), pp. 645–650.

ICPR-2016-EggertWZL #detection

Saliency-guided selective magnification for company logo detection (CE, AW, DZ, RL), pp. 651–656.

ICPR-2016-PeiYKY #detection #multi

Multi-orientation scene text detection with multi-information fusion (WYP, CY, LJK, XCY), pp. 657–662.

ICPR-2016-SunSH #automation #image

Automatic building extraction from oblique aerial images (XS, SS, ZH), pp. 663–668.

ICPR-2016-GabrE #detection #runtime

Enhancing the runtime of JUDOCA detector (MG, RE), pp. 669–674.

ICPR-2016-Aldana-IuitMCM #performance

In the Saddle: Chasing fast and repeatable features (JAI, DM, OC, JM), pp. 675–680.

ICPR-2016-KuranukiP #detection

Minimal filtered channel features for pedestrian detection (YK, IP), pp. 681–686.

ICPR-2016-ToyamaMS #clustering #performance #using

Fast template matching using Brick Partitioning and initial threshold (FT, HM, KS), pp. 687–691.

ICPR-2016-LanglardSLCD #multi #recognition

A multiscale method for shape recognition of overlapping elliptical particles (MDL, HAS, FL, SC, JD), pp. 692–697.

ICPR-2016-BlondelPPLL #collaboration #detection

Dynamic collaboration of far-infrared and visible spectrum for human detection (PB, AP, CP, RL, DL), pp. 698–703.

ICPR-2016-ChenYDLZ #recognition

Quaternion-type moments combining both color and depth information for RGB-D object recognition (BC, JY, MD, TL, XZ), pp. 704–708.

ICPR-2016-ZhangZZB #detection #symmetry

Symmetry-based object proposal for text detection (XZ, ZZ, CZ, XB), pp. 709–714.

ICPR-2016-BrownF #detection #smarttech #using

Enhanced face detection using body part detections for wearable cameras (LMB, QF), pp. 715–720.

ICPR-2016-GunjiNTKK #3d #recognition #scalability

3D object recognition from large-scale point clouds with global descriptor and sliding window (NG, HN, KT, TK, TK), pp. 721–726.

ICPR-2016-MohagheghKSSN #estimation #image #using

Single image depth estimation using joint local-global features (HM, NK, SMRS, SS, KN), pp. 727–732.

ICPR-2016-FaulhammerZPV #multi

A multi-modal RGB-D object recognizer (TF, MZ, JP, MV), pp. 733–738.

ICPR-2016-ZhaoMFQH #performance #predict #using

Fast motion deblurring using gyroscopes and strong edge prediction (JZ, JM, BF, SQ, FH), pp. 739–744.

ICPR-2016-LeeS #image #programming #search-based

Learning-based single image dehazing via genetic programming (CL, LS0), pp. 745–750.

ICPR-2016-YangJPL #image #learning #taxonomy

Enhancement of Low Light Level Images with coupled dictionary learning (JY, XJ, CP, CLL), pp. 751–756.

ICPR-2016-ShkvarkoLAG #data fusion #multi

Intelligent neural computing-based way for multi-sensor imaging radar data fusion (YVS, JALR, SRSA, GGT), pp. 757–762.

ICPR-2016-Oskarsson #using

Characterizing the structure tensor using gamma distributions (MO), pp. 763–768.

ICPR-2016-HanSG #analysis #image

A hyperspectral image restoration method based on analysis sparse filter (CH, NS, CG), pp. 769–774.

ICPR-2016-NikonorovPBYYKS #comparative #evaluation #lens

Comparative evaluation of deblurring techniques for Fresnel lens computational imaging (AVN, MVP, SAB, YVY, PYY, NLK, RVS, VF), pp. 775–780.

ICPR-2016-GhoraiMC #image #kernel #statistics #using

Patch sparsity based image inpainting using local patch statistics and steering kernel descriptor (MG, SM, BC), pp. 781–786.

ICPR-2016-Ponce-Hinestroza #adaptation #using

Using a MRF-BP model with color adaptive training for underwater color restoration (ANPH, LATM, PDJ), pp. 787–792.

ICPR-2016-MollerNN16a #clustering #detection #image #using

Change detection in marine observatory image streams using Bi-Domain Feature Clustering (TM, IN, TWN), pp. 793–798.

ICPR-2016-ZhangW

An MCMC-based prior sub-hypergraph matching in presence of outliers (RZ, WW), pp. 799–804.

ICPR-2016-AbdulmunemLS #3d #recognition

3D GLOH features for human action recognition (AA, YKL, XS), pp. 805–810.

ICPR-2016-HuLL #learning #named #representation #semantics #video

Video2vec: Learning semantic spatio-temporal embeddings for video representation (ShH, YL, BL), pp. 811–816.

ICPR-2016-NGuyenNC #effectiveness #image #recognition

Effective surface normals based action recognition in depth images (XSN, TPN, FC), pp. 817–822.

ICPR-2016-QianCS #recognition

Mutually incoherent pose bases for Action recognition (YQ, WC, IFS), pp. 823–828.

ICPR-2016-Troya-GalvisGB #analysis #classification #collaboration #image #segmentation

Collaborative segmentation and classification for remote sensing image analysis (ATG, PG, LBÉ), pp. 829–834.

ICPR-2016-KulhareSPP #process #recognition

Key frame extraction for salient activity recognition (SK, SS, SP, RWP), pp. 835–840.

ICPR-2016-SukhwaniJ

Frame level annotations for tennis videos (MS, CVJ), pp. 841–846.

ICPR-2016-YaoXG #image #multi #rank

A rank minimization-based late fusion method for multi-label image annotation (YY0, XX0, PG0), pp. 847–852.

ICPR-2016-Nakazawa #image #random #using

Noise stable image registration using RANdom RESAmple Consensus (AN), pp. 853–858.

ICPR-2016-ZhangXLPQ #detection #image #robust

Robust road detection from a single image (JZ, SYX, KL, HP, AKQ), pp. 859–864.

ICPR-2016-SinghTSV #detection

Detection of glare in night photography (MS, RKT, KS, AV), pp. 865–870.

ICPR-2016-KBS #video

Vector R-ordering based selection of segments for video skimming (VVK, RB, DS), pp. 871–876.

ICPR-2016-KaurKS #predict #video

Prediction based seam carving for video retargeting (HK, SK, DS), pp. 877–882.

ICPR-2016-ZhengLZW #image #multi #using

Multi-focus image fusion using quaternion wavelet transform (XNZ, XL, ZZ, XJW), pp. 883–888.

ICPR-2016-YuWSH #invariant #recognition #using

View invariant gait recognition using only one uniform model (SY, QW, LS, YH), pp. 889–894.

ICPR-2016-DevanneWDBBP #analysis #learning

Learning shape variations of motion trajectories for gait analysis (MD, HW, MD, SB, ADB, PP), pp. 895–900.

ICPR-2016-BalaziaS16a #learning #recognition #robust

Learning robust features for gait recognition by Maximum Margin Criterion (MB, PS), pp. 901–906.

ICPR-2016-ConlyDA #gesture #recognition #scalability

Leveraging intra-class variations to improve large vocabulary gesture recognition (CC, AD, VA), pp. 907–912.

ICPR-2016-LiangLWZ #estimation

Human pose estimation based on human limbs (GL, XL, JW0, NZ), pp. 913–918.

ICPR-2016-GhorbelBBSL #performance #recognition

A fast and accurate motion descriptor for human action recognition applications (EG, RB, JB, XS, SL), pp. 919–924.

ICPR-2016-KatsageorgiouZH #analysis #behaviour #data-driven #interactive

Unsupervised mouse behavior analysis: A data-driven study of mice interactions (VMK, MZ, HH, VF0, FP, DS, VM), pp. 925–930.

ICPR-2016-WangHG #classification #learning #novel

A novel fingerprint classification method based on deep learning (RW, CH, TG), pp. 931–936.

ICPR-2016-ZhangZJYT

Define a fingerprint Orientation Field pattern (NZ0, YZ, XJ, XY0, JT0), pp. 937–942.

ICPR-2016-LinK #identification

Improving cross sensor interoperability for fingerprint identification (CL, AK0), pp. 943–948.

ICPR-2016-KostadinovVDFH #linear

Local Active Content Fingerprint: Solutions for general linear feature maps (DK, SV, MD, SF, TH), pp. 949–954.

ICPR-2016-PhamTM #framework #pattern matching #pattern recognition #recognition

A proposed pattern recognition framework for EEG-based smart blind watermarking system (TDP, DT, WM), pp. 955–960.

ICPR-2016-DesrosiersDD #analysis #generative #novel #statistics

Novel generative model for facial expressions based on statistical shape analysis of landmarks trajectories (PAD, MD, MD), pp. 961–966.

ICPR-2016-TianAC #adaptation #recognition

Shannon information based adaptive sampling for action recognition (QT, TA, JJC), pp. 967–972.

ICPR-2016-AiMHLL #gesture #precise

High precision gesture sensing via quantitative characterization of the Doppler effect (HA, YM, LH, ZL, ML), pp. 973–978.

ICPR-2016-PeiM #3d #estimation #interactive #mobile #performance

Fast 3D hand estimation for mobile interactions (YP, GM), pp. 979–984.

ICPR-2016-BoulahiaAKM #3d #named #recognition

HIF3D: Handwriting-Inspired Features for 3D skeleton-based action recognition (SYB, ÉA, RK, FM), pp. 985–990.

ICPR-2016-GemerenPV #interactive

Locating human interactions with discriminatively trained deformable pose+motion parts (CVG, RP, RCV), pp. 991–996.

ICPR-2016-BorghiVC #3d #gesture #multi #performance #recognition

Fast gesture recognition with Multiple Stream Discrete HMMs on 3D skeletons (GB, RV, RC), pp. 997–1002.

ICPR-2016-StearnsOCFRCF #image #locality

Localization of skin features on the hand and wrist from small image patches (LS, UO, BJC, LF, DR, RC, JEF), pp. 1003–1010.

ICPR-2016-GoswamiRSV #classification #normalisation

Improving classifier fusion via Pool Adjacent Violators normalization (GG, NKR, RS0, MV), pp. 1011–1016.

ICPR-2016-TianMO #detection #embedded #low cost #recognition #using

Spoofing detection for embedded face recognition system using a low cost stereo camera (GT, TM, YO), pp. 1017–1022.

ICPR-2016-OlivaresVG #automation

Automatic leaf shape category discovery (LO, JV, FG), pp. 1023–1028.

ICPR-2016-LiWS #performance #towards

Towards protecting biometric templates without sacrificing performance (JL0, YW, TS), pp. 1029–1034.

ICPR-2016-SiddiquiBDAVSR #anti #multi

Face anti-spoofing with multifeature videolet aggregation (TAS, SB, TID, AA0, MV, RS0, NKR), pp. 1035–1040.

ICPR-2016-Liu #hybrid #mining #scalability

Exposing seam carving forgery under recompression attacks by hybrid large feature mining (QL), pp. 1041–1046.

ICPR-2016-FerrariLBB #3d #effectiveness #recognition

Effective 3D based frontalization for unconstrained face recognition (CF, GL, SB, ADB), pp. 1047–1052.

ICPR-2016-KhorsandiKSHSWN #gesture #recognition

Radon transform inspired method for hand gesture recognition (MAK, NK, SMRS, MH, SS, KW, KN), pp. 1053–1058.

ICPR-2016-NguyenY #approach #artificial reality #named #novel

StereoTag: A novel stereogram-marker-based approach for Augmented Reality (MN, AY), pp. 1059–1064.

ICPR-2016-OgawaMYA #sketching

Sketch simplification by classifying strokes (TO, YM, TY, KA), pp. 1065–1070.

ICPR-2016-HsiaoC #algorithm #identification #orthogonal #re-engineering #recognition

Over-atoms accumulation orthogonal matching pursuit reconstruction algorithm for fish recognition and identification (YHH, CCC), pp. 1071–1076.

ICPR-2016-LiuZH #authentication #effectiveness #smarttech

An effective voiceprint based identity authentication system for Mandarin smartphone users (JHL, YXZ, YCH), pp. 1077–1082.

ICPR-2016-Lamar-LeonBGG #persistent #recognition #robust

Persistent homology-based gait recognition robust to upper body variations (JLL, RAB, EBGR, RGD), pp. 1083–1088.

ICPR-2016-CarvajalWSL #automation #contest #predict #towards

Towards Miss Universe automatic prediction: The evening gown competition (JC, AW, CS, BCL), pp. 1089–1094.

ICPR-2016-ZhaoYWL #approach #recognition

Landmark manifold: Revisiting the Riemannian manifold approach for facial emotion recognition (KZ, SY, AW, BCL), pp. 1095–1100.

ICPR-2016-AlvenKLLU #multi #segmentation

Shape-aware multi-atlas segmentation (JA, FK, ML, VL, JU), pp. 1101–1106.

ICPR-2016-FariaCLI #dependence #recognition #using

Information fusion for cocaine dependence recognition using fMRI (FAF, FAMC, CsRL, JSI), pp. 1107–1112.

ICPR-2016-DaiMZ #evolution #image #performance #segmentation #set

A Bregman divergence based Level Set Evolution for efficient medical image segmentation (SD, HM, SZ), pp. 1113–1118.

ICPR-2016-WuZLMS #graph #named #novel

EvaToon: A novel graph matching system for evaluating cartoon drawings (YW, XZ, TL, GM, LS), pp. 1119–1124.

ICPR-2016-QuLFT #effectiveness #learning #retrieval

Improving PGF retrieval effectiveness with active learning (JQ, XL, SF, ZT), pp. 1125–1130.

ICPR-2016-MaLW #database #online #recognition #word

A new database for online handwritten Mongolian word recognition (LLM, JL, JW0), pp. 1131–1136.

ICPR-2016-QuWL #recognition #representation #using

In-air handwritten Chinese character recognition using discriminative projection based on locality-sensitive sparse representation (XQ, WW, KL), pp. 1137–1140.

ICPR-2016-SuJWSW #network #novel #recognition #segmentation

Novel character segmentation method for overlapped Chinese handwriting recognition based on LSTM neural networks (TS, SJ, QW, LS, RW), pp. 1141–1146.

ICPR-2016-CabreraFS #evaluation #multi #variability

Approaching the intra-class variability in multi-script static signature evaluation (MDC, MAF, RS), pp. 1147–1152.

ICPR-2016-AdakCB #identification #testing

Writer identification by training on one script but testing on another (CA, BBC, MB), pp. 1153–1158.

ICPR-2016-MontenegroA #artificial reality #estimation #human-computer #using

Gaze estimation using EEG signals for HCI in augmented and virtual reality headsets (JMFM, VA), pp. 1159–1164.

ICPR-2016-RapczynskiWA #estimation #latency #realtime

Continuous low latency heart rate estimation from painful faces in real time (MR, PW, AAH), pp. 1165–1170.

ICPR-2016-TamboB #behaviour #predict

Temporal dynamics of tip fluorescence predict cell growth behavior in pollen tubes (ALT, BB), pp. 1171–1176.

ICPR-2016-RaySC #image #locality #recognition

Recognition based text localization from natural scene images (AR, AS, SC), pp. 1177–1182.

ICPR-2016-SukS #analysis #detection #retrieval

Solar flare retrieval, detection and analysis (TS, SS), pp. 1183–1188.

ICPR-2016-MorariuTPDT #optimisation

Sequential vs. batch machine-learning with evolutionary hyperparameter optimization for segmenting aortic dissection thrombus (CAM, MT, JP, DSD, KT), pp. 1189–1194.

ICPR-2016-AntonyMOM #network #using

Quantifying radiographic knee osteoarthritis severity using deep convolutional neural networks (JA, KM, NEO, KM), pp. 1195–1200.

ICPR-2016-DasguptaYO #learning #sequence

Regularized dynamic Boltzmann machine with Delay Pruning for unsupervised learning of temporal sequences (SD, TY, TO), pp. 1201–1206.

ICPR-2016-0003CNBH #dependence

Measuring dependency via intrinsic dimensionality (SR0, OC, VN, JB0, MEH), pp. 1207–1212.

ICPR-2016-KalraSRT #learning #network #using

Learning opposites using neural networks (SK, AS, SR, HRT), pp. 1213–1218.

ICPR-2016-ZhongGS #classification

A DBN-crf for spectral-spatial classification of hyperspectral data (PZ0, ZG, CBS), pp. 1219–1224.

ICPR-2016-MartinelFM #distributed #identification

Distributed and Unsupervised Cost-Driven Person Re-Identification (NM, GLF, CM), pp. 1225–1230.

ICPR-2016-AnZH #detection #online

Online RGB-D tracking via detection-learning-segmentation (NA, XZ, ZGH), pp. 1231–1236.

ICPR-2016-BarathH #energy

Energy-based topological outlier filtering (DB, LH), pp. 1237–1242.

ICPR-2016-GladhDKF #visual notation

Deep motion features for visual tracking (SG, MD, FSK, MF), pp. 1243–1248.

ICPR-2016-YangSGLL

Facial depth map enhancement via neighbor embedding (SY0, SS, QG, XL, JL0), pp. 1249–1254.

ICPR-2016-YouXLZCTZ #image #matrix #rank

Single image super-resolution with non-local balanced low-rank matrix restoration (XY, WX, JL, PZ0, YmC, YT, NZ), pp. 1255–1260.

ICPR-2016-YB #3d #optimisation #using #video

Rate distortion optimization using SSIM for 3D video coding (HY, PKB), pp. 1261–1266.

ICPR-2016-0005LH #optimisation

Accelerated sparse optimization for missing data completion (ZX0, YL, JH), pp. 1267–1272.

ICPR-2016-RoyDB #classification #documentation #image #network

Generalized stacking of layerwise-trained Deep Convolutional Neural Networks for document image classification (SR, AD, UB), pp. 1273–1278.

ICPR-2016-LiPS #image #streaming #summary

Streaming news image summarization (HL0, SP, HS), pp. 1279–1284.

ICPR-2016-AugereauFK #analysis #automation #estimation #towards

Towards an automated estimation of English skill via TOEIC score based on reading analysis (OA, HF, KK), pp. 1285–1290.

ICPR-2016-NairKNG #documentation #network #segmentation #using

Segmentation of highly unstructured handwritten documents using a neural network technique (RRN, BUK, IN, VG), pp. 1291–1296.

ICPR-2016-MassichRLCWSM #overview #perspective

Classifying DME vs normal SD-OCT volumes: A review (JM, MR, GL, CYlC, TYW, DS, FM), pp. 1297–1302.

ICPR-2016-ChenZW #approach #learning #network #summary #video

Wireless capsule endoscopy video summarization: A learning approach based on Siamese neural network and support vector machine (JC, YZ, YW0), pp. 1303–1308.

ICPR-2016-NouredaneshTBT #image #retrieval

Radon-Gabor barcodes for medical image retrieval (MN, HRT, EB, JT), pp. 1309–1314.

ICPR-2016-HoSSEA #approach #estimation #learning #parametricity

A temporal deep learning approach for MR perfusion parameter estimation in stroke (KCH, FS, KVS, SES, CWA), pp. 1315–1320.

ICPR-2016-WangWH #analysis #network #using

Network entropy analysis using the Maxwell-Boltzmann partition function (JW, RCW0, ERH), pp. 1321–1326.

ICPR-2016-GligorijevicPZ #community #detection #graph #multi

Fusion and community detection in multi-layer graphs (VG, YP, SZ), pp. 1327–1332.

ICPR-2016-TianC #estimation

Cross-heterogeneous-database age estimation with co-representation among them (QT, SC), pp. 1333–1338.

ICPR-2016-Bai0CH16a #graph #matrix #novel

A novel entropy-based graph signature from the average mixing matrix (LB0, LR0, LC, ERH), pp. 1339–1344.

ICPR-2016-HaralickDSK #clustering #linear

Inexact MDL for linear manifold clusters (RMH, AD, XS, NYK), pp. 1345–1351.

ICPR-2016-YorukOA #estimation #multi #performance #recognition

An efficient Hough transform for multi-instance object recognition and pose estimation (EY, KTO, CBA), pp. 1352–1357.

ICPR-2016-Maldonado-Ramirez #recognition #visual notation

A bag of relevant regions for visual place recognition in challenging environments (AMR, LATM, MC), pp. 1358–1363.

ICPR-2016-LuYLLZ #detection

Edge chain detection by applying Helmholtz principle on gradient magnitude map (XL, JY, LL0, YL, WZ), pp. 1364–1369.

ICPR-2016-WangZJ #recognition #taxonomy

Taxonomy augmented object recognition (XW0, YZ, QJ), pp. 1370–1375.

ICPR-2016-KerautretKDL16a #detection

Centerline detection on partial mesh scans by confidence vote in accumulation map (BK, AK, IDR, JOL), pp. 1376–1381.

ICPR-2016-Ohn-BarT #detection #locality #modelling #multi

Detection and localization with multi-scale models (EOB, MMT), pp. 1382–1387.

ICPR-2016-ZelenkaK #image

Restoration of images with wavefront aberrations (CZ, RK), pp. 1388–1393.

ICPR-2016-Konno0OYKK #self

Depth map upsampling by self-guided residual interpolation (YK, MT0, MO, YY, KK, MK), pp. 1394–1399.

ICPR-2016-WangLX #adaptation #image #rank #representation

Adaptive boosting for image denoising: Beyond low-rank representation and sparse coding (BW, TL0, ZX), pp. 1400–1405.

ICPR-2016-SantraC #image

Day/night unconstrained image dehazing (SS, BC), pp. 1406–1411.

ICPR-2016-Timofte #image

Anchored fusion for image restoration (RT), pp. 1412–1417.

ICPR-2016-FoareLT16a #calculus #functional #image #segmentation #using

Image restoration and segmentation using the Ambrosio-Tortorelli functional and Discrete Calculus (MF, JOL, HT), pp. 1418–1423.

ICPR-2016-WuARN #performance #recognition

Computationally efficient template-based face recognition (YW0, WAA, SR, PN), pp. 1424–1429.

ICPR-2016-JhuangLT #3d #network #using #verification

Face verification with three-dimensional point cloud by using deep belief networks (DHJ, DTL, CHT), pp. 1430–1435.

ICPR-2016-Martinez-DiazCH #encoding #performance #recognition #using #video

Efficient video face recognition by using Fisher Vector encoding of binary features (YMD, LC, NH, HMV, LES), pp. 1436–1441.

ICPR-2016-PengRP #learning #network #recognition #using

Learning face recognition from limited training data using deep neural networks (XP, NKR, SP), pp. 1442–1447.

ICPR-2016-XuZAC #verification

Template regularized sparse coding for face verification (HX, JZ, AA, RC), pp. 1448–1454.

ICPR-2016-Alonso-Fernandez #multi #recognition #using

Compact multi-scale periocular recognition using SAFE features (FAF, AM, JB), pp. 1455–1460.

ICPR-2016-BillingsAB #analysis #detection #image

Ultrasound image analysis for myopathy detection (SB, JA, PB), pp. 1461–1465.

ICPR-2016-KaurDCM #hybrid #image #learning

Hybrid deep learning for Reflectance Confocal Microscopy skin images (PK, KJD, GOC, MCM), pp. 1466–1471.

ICPR-2016-MarronePFPSS #fuzzy #segmentation #using

Breast segmentation using Fuzzy C-Means and anatomical priors in DCE-MRI (SM0, GP, RF, AP, MS, CS), pp. 1472–1477.

ICPR-2016-PalCGCC #learning #multi #using

Severity grading of psoriatic plaques using deep CNN based multi-task learning (AP, AC, UG, AC, RC), pp. 1478–1483.

ICPR-2016-JermanPLSC #analysis #automation #identification

Automatic cutting plane identification for computer-aided analysis of intracranial aneurysms (TJ, FP, BL, ZS, AC), pp. 1484–1489.

ICPR-2016-StanitsasCLTMP #evaluation #recognition

Evaluation of feature descriptors for cancerous tissue recognition (PS, AC, XL, AT, VM, NP), pp. 1490–1495.

ICPR-2016-KalantidisFKBS #congruence #image #visual notation

Visual congruent ads for image search (YK, AF, LK, RBY, DAS), pp. 1496–1505.

ICPR-2016-Iwata #distance #set

Reducing the computational cost of shape matching with the distance set (KI0), pp. 1506–1511.

ICPR-2016-LimK #approach #feature model #multi #optimisation

Convex optimization approach for multi-label feature selection based on mutual information (HL, DWK), pp. 1512–1517.

ICPR-2016-Robles-KellyW #graph #image #using

Semi-supervised image labelling using barycentric graph embeddings (ARK, RW), pp. 1518–1523.

ICPR-2016-HajduHBLEHT #algorithm #approximate #grid #network #using

Measuring regularity of network patterns by grid approximations using the LLL algorithm (AH, BH, RB, IL, GE, LH, RT), pp. 1524–1529.

ICPR-2016-NienkotterJ #problem #string

Distance-preserving vector space embedding for the closest string problem (AN, XJ0), pp. 1530–1535.

ICPR-2016-MinelloTH #evolution #network #quantum

Quantum thermodynamics of time evolving networks (GM, AT, ERH), pp. 1536–1541.

ICPR-2016-GrenierBV #predict

Taking into account stereoisomerism in the prediction of molecular properties (PAG, LB, DV), pp. 1542–1547.

ICPR-2016-GaliMF #metric #similarity

Similarity measures for title matching (NG, RMI, PF), pp. 1548–1553.

ICPR-2016-MaoFWH #identification #kernel #performance

Fast kernel SVM training via support vector identification (XM, ZF, OW, WH), pp. 1554–1559.

ICPR-2016-KhanH #adaptation #learning #polynomial #using

Adapting instance weights for unsupervised domain adaptation using quadratic mutual information and subspace learning (MNAK, DRH), pp. 1560–1565.

ICPR-2016-GuoCY #adaptation #approach

A simple approach for unsupervised domain adaptation (XG0, WC, JY), pp. 1566–1570.

ICPR-2016-XueB #learning #multi

Multi-task learning for one-class SVM with additional new features (YX, PB), pp. 1571–1576.

ICPR-2016-OliveauS #classification #image #semantics

Semantic-free attributes for image classification (QO, HS), pp. 1577–1582.

ICPR-2016-YeLYZ #clustering #kernel #multi

Co-regularized kernel k-means for multi-view clustering (YY, XL, JY, EZ), pp. 1583–1588.

ICPR-2016-KimP16a #network #using

Discovering characteristic landmarks on ancient coins using convolutional networks (JK, VP), pp. 1595–1600.

ICPR-2016-HasegawaH #classification #image #named #network #using

PLSNet: A simple network using Partial Least Squares regression for image classification (RH, KH), pp. 1601–1606.

ICPR-2016-YiHLCC #adaptation #rank #re-engineering #representation #taxonomy

Simultaneous Dual-Views Reconstruction with Adaptive Dictionary and Low-Rank Representation (SY, ZH, YL, YMC, WC), pp. 1607–1611.

ICPR-2016-SunKK #classification #multi

Multi-label classification with meta-label-specific features (LS, MK, KK), pp. 1612–1617.

ICPR-2016-RaymondI #identification

Bus trajectory identification by map-matching (RR, TI), pp. 1618–1623.

ICPR-2016-MaoZCLHY #2d

Two-dimensional PCA hashing and its extension (MM, ZZ, ZC, HL, XH, RY), pp. 1624–1629.

ICPR-2016-MoazzenT #approximate #clustering #dataset

Sampling based approximate spectral clustering ensemble for partitioning datasets (YM, KT), pp. 1630–1635.

ICPR-2016-KimKAK #markov #modelling #process #recognition

Integrating hidden Markov models based on Mixture-of-Templates and k-NN2 ensemble for activity recognition (YJK, YK, JA, DK0), pp. 1636–1641.

ICPR-2016-BicegoL #nearest neighbour #revisited

Weighted K-Nearest Neighbor revisited (MB, ML), pp. 1642–1647.

ICPR-2016-ValevYK #approach #geometry #pattern matching #pattern recognition #problem #recognition

A new geometrical approach for solving the supervised pattern recognition problem (VV, NY, AK), pp. 1648–1652.

ICPR-2016-GaoJ #hybrid #markov

Hybrid Markov Blanket discovery (TG, QJ), pp. 1653–1658.

ICPR-2016-GuoDFS #detection #robust #using

A robust UAV landing site detection system using mid-level discriminative patches (XG, SD, CF, SS), pp. 1659–1664.

ICPR-2016-FanWH #adaptation #learning #multi

Multi-stage multi-task feature learning via adaptive threshold (YF, YW, TZH), pp. 1666–1671.

ICPR-2016-OhY #algorithm #graph #learning

Enhancing label inference algorithms considering vertex importance in graph-based semi-supervised learning (BO, JY), pp. 1671–1676.

ICPR-2016-KrijtheL16a #classification

Optimistic semi-supervised least squares classification (JHK, ML), pp. 1677–1682.

ICPR-2016-MezumanW #bound #finite

A tight convex upper bound on the likelihood of a finite mixture (EM, YW), pp. 1683–1688.

ICPR-2016-SousaB #consistency #learning

Constrained Local and Global Consistency for semi-supervised learning (CARdS, GEAPAB), pp. 1689–1694.

ICPR-2016-BogunR

Object-aware tracking (IB, ER), pp. 1695–1700.

ICPR-2016-BougleuxGB #distance #edit distance #graph #polynomial

Graph edit distance as a quadratic program (SB, BG, LB), pp. 1701–1706.

ICPR-2016-MiyazakiO #graph #recognition

Graph model boosting for structural data recognition (TM, SO), pp. 1707–1712.

ICPR-2016-LiuNZWL #automation #clustering #multi

Unsupervised automatic attribute discovery method via multi-graph clustering (LL, FN, TZ, AW, BCL), pp. 1713–1718.

ICPR-2016-TripodiVP #clustering #matrix

Context aware nonnegative matrix factorization clustering (RT, SV, MP), pp. 1719–1724.

ICPR-2016-ChenCDHLSFB0 #3d

Finding rigid sub-structure patterns from 3D point-sets (ZC, DC, HD, ZH, ZL, NS, AJF, RB, JX0), pp. 1725–1730.

ICPR-2016-DongH

Sequential factorization for nonrigid structure from motion via LBFGS (QD, HH), pp. 1731–1736.

ICPR-2016-NieS #novel

A novel photometric stereo method with nonisotropic point light sources (YN, ZS), pp. 1737–1742.

ICPR-2016-KawasakiHF #grid

Registration and entire shape acquisition for grid based active one-shot scanning techniques (HK, TH, RF), pp. 1743–1749.

ICPR-2016-SalemKPHB #3d #estimation #image

Three dimensional pose estimation of mouse from monocular images in compact systems (GS, JK, TP, MHH, XPBA), pp. 1750–1755.

ICPR-2016-AbuzainaNC #3d #estimation

3D motion estimation by evidence gathering (AA, MSN, JNC), pp. 1756–1761.

ICPR-2016-BrauJ #3d #approach #estimation

A Bayesian part-based approach to 3D human pose and camera estimation (EB, HJ0), pp. 1762–1767.

ICPR-2016-FukanoMISSI #energy #higher-order #image #re-engineering

Room reconstruction from a single spherical image by higher-order energy minimization (KF, YM, SI, ESS, AS, HI0), pp. 1768–1773.

ICPR-2016-WuLZN #modelling #re-engineering #using

Model-based face reconstruction using SIFT flow registration and spherical harmonics (FW, SL, TZ, KNN), pp. 1774–1779.

ICPR-2016-MuthuswamyR #detection

Salient object detection in tracking shots (KM, DR), pp. 1780–1785.

ICPR-2016-NaimMSLKG #constraints

Aligning movies with scripts by exploiting temporal ordering constraints (IN, AAM0, YCS, JL, HAK, DG), pp. 1786–1791.

ICPR-2016-LeHWO #detection #performance

Temporally subsampled detection for accurate and efficient face tracking and diarization (NL, AH, DW0, JMO), pp. 1792–1797.

ICPR-2016-DelforouziTSG #image

Unknown object tracking in 360-degree camera images (AD, SAHT, KS, MG), pp. 1798–1803.

ICPR-2016-PuZZ #multi #network

Structure and appearance preserving network flow for multi-object tracking (SP, HZ, KZ), pp. 1804–1808.

ICPR-2016-TakadaHJ #using

Human tracking in crowded scenes using target information at previous frames (HT, KH, PJ), pp. 1809–1814.

ICPR-2016-0003BP #3d #detection #symmetry

Detection and characterization of Intrinsic symmetry of 3D shapes (AM0, SMB, FP), pp. 1815–1820.

ICPR-2016-ChenGLZY #detection

Appearance changes detection during tracking (WC, XG0, XL, EZ, JY), pp. 1821–1826.

ICPR-2016-FeiginRA #framework #image #statistics

Statistical consensus matching framework for image registration (MF, BJR, BWA), pp. 1827–1832.

ICPR-2016-NahaW #comprehension

Beyond verbs: Understanding actions in videos with text (SN, YW0), pp. 1833–1838.

ICPR-2016-BartoliLSB #estimation #profiling #using

User interest profiling using tracking-free coarse gaze estimation (FB, GL, LS, ADB), pp. 1839–1844.

ICPR-2016-LeiT #modelling #using

Modeling human-skeleton motion patterns using conditional deep Boltzmann machine (PL, ST), pp. 1845–1850.

ICPR-2016-PhamPCC #3d #realtime #robust

Robust real-time performance-driven 3D face tracking (HXP, VP, JC, TJC), pp. 1851–1856.

ICPR-2016-KilicarslanZR #detection

Pedestrain detection from motion (MK, JYZ, KR), pp. 1857–1863.

ICPR-2016-Ben-ArtziHWP #geometry #similarity

Epipolar geometry based on line similarity (GBA, TH, MW, SP), pp. 1864–1869.

ICPR-2016-KilicarslanZ #using #video

Bridge motion to collision alarming using driving video (MK, JYZ), pp. 1870–1875.

ICPR-2016-SidibeRM #detection #multi #on the #using

On spatio-temporal saliency detection in videos using multilinear PCA (DS, MR, FM), pp. 1876–1880.

ICPR-2016-WangZQL #detection #framework

RGB-D saliency detection under Bayesian framework (STW, ZZ, HBQ, BL), pp. 1881–1886.

ICPR-2016-ZhouLL #estimation

Depth estimation with cascade occlusion culling filter for light-field cameras (WZ, AL, LL), pp. 1887–1892.

ICPR-2016-FerreiraG #3d #lens #performance

Accurate and fast micro lenses depth maps from a 3D point cloud in light field cameras (RF, NG), pp. 1893–1898.

ICPR-2016-QianCKNM #learning

Deep structured-output regression learning for computational color constancy (YQ, KC0, JKK, JN, JM), pp. 1899–1904.

ICPR-2016-DahlanH

Absorptive scattering model for rough laminar surfaces (HAD, ERH), pp. 1905–1910.

ICPR-2016-HilsenbeckMKHA #independence #recognition

Hierarchical Hough forests for view-independent action recognition (BH, DM, HK, WH0, MA), pp. 1911–1916.

ICPR-2016-Osuna-CoutinoMA #image #recognition

Dominant plane recognition in interior scenes from a single image (JAdJOC, JMC, MOAE, WWMC), pp. 1923–1928.

ICPR-2016-LiuHWLL #image #performance #retrieval #segmentation #using

Efficient segmentation for Region-based Image Retrieval using Edge Integrated Minimum Spanning Tree (YL0, LH0, SW, XL, BL), pp. 1929–1934.

ICPR-2016-ShimodaY #segmentation

Weakly-supervised segmentation by combining CNN feature maps and object saliency maps (WS, KY), pp. 1935–1940.

ICPR-2016-Matsakis

Affine properties of the relative position PHI-descriptor (PM), pp. 1941–1946.

ICPR-2016-CaetanoSS #matrix #novel

Optical Flow Co-occurrence Matrices: A novel spatiotemporal feature descriptor (CC, JAdS, WRS), pp. 1947–1952.

ICPR-2016-TairaTO #learning #robust #synthesis

Robust feature matching by learning descriptor covariance with viewpoint synthesis (HT, AT, MO), pp. 1953–1958.

ICPR-2016-DaiDCLY #multi #rank #representation #segmentation #using

Object segmentation using low-rank representation with multiple block-diagonal priors (LD, JD, JC, JL0, JY0), pp. 1959–1964.

ICPR-2016-HuangWLL #named

USEQ: Ultra-fast superpixel extraction via quantization (CRH, WAW, SYL, YYL), pp. 1965–1970.

ICPR-2016-MoriKAS #robust

Robust region extraction of moving objects in dynamic background (SM, YK, TA, TS), pp. 1971–1976.

ICPR-2016-LiaoWL #order

Feature descriptor based on local intensity order relations of pixel group (WHL, CCW, MCL), pp. 1977–1981.

ICPR-2016-XianXCZD #effectiveness #interactive #named #segmentation

EISeg: Effective interactive segmentation (MX, FX, HDC, YZ, JD), pp. 1982–1987.

ICPR-2016-ChatouxLF #case study #comparative

Comparative study of descriptors with dense key points (HC, FL, CFM), pp. 1988–1993.

ICPR-2016-ClementKW

Bags of spatial relations and shapes features for structural object description (MC, CK, LW), pp. 1994–1999.

ICPR-2016-SalaunMM16a #detection #multi #robust

Multiscale line segment detector for robust and accurate SfM (YS, RM, PM), pp. 2000–2005.

ICPR-2016-NguyenVPG #classification

An integrated descriptor for texture classification (VLN, NSV, HHP, PHG), pp. 2006–2011.

ICPR-2016-GonzalezVT #classification #invariant #learning

Learning rotation invariant convolutional filters for texture classification (DM, MV, DT), pp. 2012–2017.

ICPR-2016-Brandtberg #analysis #classification #fourier #fuzzy #multi #order #rank #using

Virtual hexagonal and multi-scale operator for fuzzy rank order texture classification using one-dimensional generalised Fourier analysis (TB), pp. 2018–2024.

ICPR-2016-HaindlH #3d

Three-dimensional Gaussian mixture texture model (MH, VH), pp. 2025–2030.

ICPR-2016-GaoCZFZ #image #segmentation #using

Texture image segmentation using fused features and active contour (MG, HC, SZ, BF0, LZ), pp. 2036–2041.

ICPR-2016-OnZEB #multi #pattern matching #pattern recognition #recognition #using

Spatio-temporal pattern recognition of dendritic spines and protein dynamics using live multichannel fluorescence microscopy (VO, AZ, IE, BB), pp. 2042–2047.

ICPR-2016-WangZWGSH #identification #learning #metric #similarity

Contextual Similarity Regularized Metric Learning for person re-identification (JW0, JZ, ZW, CG, NS, RH0), pp. 2048–2053.

ICPR-2016-EnPNHJ #documentation #image #locality

Pattern localization in historical document images via template matching (SE, CP, SN, LH, FJ), pp. 2054–2059.

ICPR-2016-LeeL #predict #process

Human activity prediction based on Sub-volume Relationship Descriptor (DGL, SWL), pp. 2060–2065.

ICPR-2016-MaioranoP #detection

Granular trajectory based anomaly detection for surveillance (FM, AP), pp. 2066–2072.

ICPR-2016-OnishiN #interactive #people #twitter

Mutual interaction model between the number of people in real space and the number of tweets in virtual space (MO, SN), pp. 2073–2078.

ICPR-2016-SuzuuchiK #analysis #behaviour #multi

Location-associated indoor behavior analysis of multiple persons (SS, MK), pp. 2079–2084.

ICPR-2016-NishiyamaNYYIS #identification #physics #using

Person re-identification using co-occurrence attributes of physical and adhered human characteristics (MN, SN, TY, HY, YI, KS), pp. 2085–2090.

ICPR-2016-PratesS #identification #kernel

Kernel Hierarchical PCA for person re-identification (RFdCP, WRS), pp. 2091–2096.

ICPR-2016-SouzaSC #comprehension #learning #semantics

Building semantic understanding beyond deep learning from sound and vision (FDMdS, SS, GCC), pp. 2097–2102.

ICPR-2016-BaiCEH #kernel

An edge-based matching kernel on commute-time spanning trees (LB0, LC, FE, ERH), pp. 2103–2108.

ICPR-2016-CoteDA

Look who is not talking: Assessing engagement levels in panel conversations (MC, AD, ABA), pp. 2109–2114.

ICPR-2016-StephensB #modelling #process #recognition

Human group activity recognition based on modelling moving regions interdependencies (KS, AGB), pp. 2115–2120.

ICPR-2016-YousefiKDCR #3d #experience #gesture #interactive #mobile

3D gesture-based interaction for immersive experience in mobile VR (SY, MK, YD, JC, NR), pp. 2121–2126.

ICPR-2016-FilipovychDRB #image #multi #recognition #sequence

Pollen recognition in optical microscopy by matching multifocal image sequences (RF, AD, ER, MB), pp. 2127–2132.

ICPR-2016-ShigetaMKSTMI #segmentation #using

A bone marrow cavity segmentation method using wavelet-based texture feature (HS, TM, JK, SS, HT, HM, MI), pp. 2133–2138.

ICPR-2016-AmeurVC #classification #recognition

Sub-classification strategies for tree species recognition (RBA, LV, DC), pp. 2139–2144.

ICPR-2016-LiHZXZ #classification

HEp-2 specimen classification via deep CNNs and pattern histogram (HL0, HH, WSZ, XX, JZ), pp. 2145–2149.

ICPR-2016-WimmerUH #classification #novel

A novel filterbank especially designed for the classification of colonic polyps (GW, AU, MH), pp. 2150–2155.

ICPR-2016-AfridiRS #framework #latency #learning #named

L-CNN: Exploiting labeling latency in a CNN learning framework (MJA, AR, EMS), pp. 2156–2161.

ICPR-2016-KumarDCT #data-driven

Spatially constrained sparse regression for the data-driven discovery of Neuroimaging biomarkers (KK, CD, AC, MT), pp. 2162–2167.

ICPR-2016-GordonL #machine learning #modelling

Exposing and modeling underlying mechanisms in ALS with machine learning (JG0, BL), pp. 2168–2173.

ICPR-2016-SahooA0 #approach #automation #clustering #generative #multi #using

Automatic generation of biclusters from gene expression data using multi-objective simulated annealing approach (PS, SA, SS0), pp. 2174–2179.

ICPR-2016-BarddalGBE #benchmark #classification #data type #metric

A benchmark of classifiers on feature drifting data streams (JPB, HMG, AdSBJ, FE), pp. 2180–2185.

ICPR-2016-BarddalGGBE #learning #nearest neighbour

Overcoming feature drifts via dynamic feature weighted k-nearest neighbor learning (JPB, HMG, JG, AdSBJ, FE), pp. 2186–2191.

ICPR-2016-RaiNCD #clustering #graph #multi #using

Partial Multi-View Clustering using Graph Regularized NMF (NR, SN, SC, OD), pp. 2192–2197.

ICPR-2016-JeongKKN #detection

Facial landmark detection based on an ensemble of local weighted regressors during real driving situation (MJ, JYK, BK, JYN), pp. 2198–2203.

ICPR-2016-MiyauchiMTMFK #modelling #self

Angle- and volume-preserving mapping of organ volume model based on modified Self-organizing Deformable Model (SM, KM, TT, YM, TF, RK), pp. 2204–2209.

ICPR-2016-DutaNAIS #recognition #using

Boosting VLAD with double assignment using deep features for action recognition in videos (ICD, TAN0, KA, BI, NS), pp. 2210–2215.

ICPR-2016-SilvaBF #feature model #online

Online Weighted One-Class Ensemble for feature selection in background/foreground separation (CS, TB, CF), pp. 2216–2221.

ICPR-2016-OgawaMDCFH #adaptation #multi #performance #predict

A new efficient measure for accuracy prediction and its application to multistream-based unsupervised adaptation (TO, SHRM, ED, JC, NHF, HH), pp. 2222–2227.

ICPR-2016-RakicevicRPP #estimation #multi #random

Multi-modal Neural Conditional Ordinal Random Fields for agreement level estimation (NR, OR, SP, MP), pp. 2228–2233.

ICPR-2016-DentamaroCG #realtime

Real time Artificial Auditory Systems for cluttered environments (GD, AC, CG), pp. 2234–2239.

ICPR-2016-KannappanLT #automation #evaluation #summary #video

A pertinent evaluation of automatic video summary (SK, YL, BT), pp. 2240–2245.

ICPR-2016-WuWJ #learning #multi #recognition

Multiple Facial Action Unit recognition by learning joint features and label relations (SW, SW, QJ), pp. 2246–2251.

ICPR-2016-Zhen0WDAD #recognition

Magnifying subtle facial motions for 4D Expression Recognition (QZ, DH0, YW, HD, BBA, MD), pp. 2252–2257.

ICPR-2016-PatelHZ #recognition

Selective deep features for micro-expression recognition (DP, XH, GZ), pp. 2258–2263.

ICPR-2016-ZhongSL #adaptation #off the shelf #predict #recognition

Transferring from face recognition to face attribute prediction through adaptive selection of off-the-shelf CNN representations (YZ, JS, HL0), pp. 2264–2269.

ICPR-2016-HafriJLT #segmentation

Dual active contours model for HR-pQCT cortical bone segmentation (MH, RJ, EL, HT), pp. 2270–2275.

ICPR-2016-RiabchenkoMAITG #classification #fine-grained

Learned vs. engineered features for fine-grained classification of aquatic macroinvertebrates (ER, KM, IA0, AI, VT, MG, SK), pp. 2276–2281.

ICPR-2016-XuLHWLWHC #3d #image #multi #retrieval #using #word

Bag of temporal co-occurrence words for retrieval of focal liver lesions using 3D multiphase contrast-enhanced CT images (YX, LL, HH, DW, YL, JW0, XHH, YWC), pp. 2282–2287.

ICPR-2016-JhuoWCL #framework

A feature fusion framework for hashing (IHJ, LW, WHC, DTL), pp. 2288–2293.

ICPR-2016-PluimMEM #image #validation

The truth is hard to make: Validation of medical image registration (JPWP, SEAM, KAJE, KM), pp. 2294–2300.

ICPR-2016-ChakeriFH #clustering

Spectral sparsification in spectral clustering (AC, HF, LOH), pp. 2301–2306.

ICPR-2016-Liu16a #classification #learning #multi #network #scalability

Hierarchical learning for large multi-class network classification (LL), pp. 2307–2312.

ICPR-2016-SinoaraRR #classification #semantics

Semantic role-based representations in text classification (RAS, RGR, SOR), pp. 2313–2318.

ICPR-2016-Norov-ErdeneKSK #classification #locality #multi #problem

Locality in multi-label classification problems (BNE, MK, LS, KK), pp. 2319–2324.

ICPR-2016-ZemeneTPP #clustering #detection #set #using

Simultaneous clustering and outlier detection using dominant sets (EZ, YTT, AP0, MP), pp. 2325–2330.

ICPR-2016-ComiterCKT #automation #clustering #distributed #implementation #parametricity

Lambda means clustering: Automatic parameter search and distributed computing implementation (MZC, MC, HTK, ST), pp. 2331–2337.

ICPR-2016-MatsuzakiUSS #2d #3d #constraints #geometry #retrieval #using #verification

Geometric verification using semi-2D constraints for 3D object retrieval (KM, YU, SS, SS), pp. 2338–2343.

ICPR-2016-BulatovKR #energy #generative #higher-order

Energy minimization of discrete functions with higher-order potentials for depth map generation (DB, BK, FR), pp. 2344–2349.

ICPR-2016-MorinakaSSIK #3d #parametricity #re-engineering

3D reconstruction under light ray distortion from parametric focal cameras (SM, FS, JS, KI, NK), pp. 2350–2355.

ICPR-2016-YodaNTKYK #image #multi #using

Dynamic photometric stereo method using multi-tap CMOS image sensor (TY, HN, RiT, KK, KY, SK), pp. 2356–2361.

ICPR-2016-KimCLM #3d #invariant #modelling #video

Expression invariant 3D face modeling from an RGB-D video (DK, JC, JTL, GGM), pp. 2362–2367.

ICPR-2016-ChenZC #image #segmentation

Partial membership latent Dirichlet allocation for image segmentation (CC, AZ, JTC), pp. 2368–2373.

ICPR-2016-GiraudTP #linear #named #using

SCALP: Superpixels with Contour Adherence using Linear Path (RG, VTT, NP), pp. 2374–2379.

ICPR-2016-MarkusPA #learning #optimisation

Learning local descriptors by optimizing the keypoint-correspondence criterion (NM, ISP, JA), pp. 2380–2385.

ICPR-2016-ItoMYA #interactive #segmentation

Interactive region segmentation for manga (KI, YM, TY, KA), pp. 2386–2391.

ICPR-2016-KhodabandehMVMP #learning #segmentation #video

Unsupervised learning of supervoxel embeddings for video Segmentation (MK, SM, AV, NM, EMP, SS, GM), pp. 2392–2397.

ICPR-2016-LiSH #image #precise #segmentation

Precise hand segmentation from a single depth image (ML, LS0, QH), pp. 2398–2403.

ICPR-2016-FrohlichKTTSW #2d #3d #visual notation

Region based fusion of 3D and 2D visual data for Cultural Heritage objects (RF, ZK, AT, LT, SS, YW), pp. 2404–2409.

ICPR-2016-OsmanliogluOHS #analysis #approximate #performance #problem

Efficient approximation of labeling problems with applications to immune repertoire analysis (YO, SO, UH, AS), pp. 2410–2415.

ICPR-2016-PassalisT #embedded #learning #retrieval #word

Bag of Embedded Words learning for text retrieval (NP, AT), pp. 2416–2421.

ICPR-2016-SharmaCH #architecture #framework #semantics

A unified framework for semantic matching of architectural floorplans (DS, CC, GH), pp. 2422–2427.

ICPR-2016-MatsukawaS #identification #using

Person re-identification using CNN features learned from combination of attributes (TM, ES), pp. 2428–2433.

ICPR-2016-DangCLOT #documentation #image #invariant #retrieval

Polygon-shape-based Scale and Rotation Invariant Features for camera-based document image retrieval (QBD, MC, MML, JMO, CDT), pp. 2434–2439.

ICPR-2016-BayramogluKH #classification #image #independence #learning

Deep learning for magnification independent breast cancer histopathology image classification (NB, JK, JH), pp. 2440–2445.

ICPR-2016-GattupalliCL #approach

A computational approach to relative aesthetics (VG, PSC, BL), pp. 2446–2451.

ICPR-2016-JinN #image #matter #order

Annotation order matters: Recurrent Image Annotator for arbitrary length image tagging (JJ, HN), pp. 2452–2457.

ICPR-2016-PengZ #network

Mutual information-based RBM neural networks (KHP, HZ), pp. 2458–2463.

ICPR-2016-Teerapittayanon #named #network #performance

BranchyNet: Fast inference via early exiting from deep neural networks (ST, BM, HTK), pp. 2464–2469.

ICPR-2016-GuY #approximate #on the #parametricity

On the magnitude of parameters of RBMs being universal approximators (LG, LY), pp. 2470–2474.

ICPR-2016-Forstner #learning #modelling #semantics

A future for learning semantic models of man-made environments (WF), pp. 2475–2485.

ICPR-2016-GhaderiA #learning #network

Selective unsupervised feature learning with Convolutional Neural Network (S-CNN) (AG, VA), pp. 2486–2490.

ICPR-2016-QuachtranHS #detection #learning #using

Detection of Intracranial Hypertension using Deep Learning (BQ, RBH, FS), pp. 2491–2496.

ICPR-2016-Williams #classification #network #using

Underwater target classification in synthetic aperture sonar imagery using deep convolutional neural networks (DPW), pp. 2497–2502.

ICPR-2016-RotaSCP #analysis #education #forensics #image #learning #question #student

Bad teacher or unruly student: Can deep learning say something in Image Forensics analysis? (PR, ES, VC, CP), pp. 2503–2508.

ICPR-2016-MaltoniL

Semi-supervised tuning from temporal coherence (DM, VL0), pp. 2509–2514.

ICPR-2016-KohjimaMS #matrix #multi

Non-negative multiple matrix factorization with Euclidean and kullback-leibler mixed divergences (MK, TM, HS), pp. 2515–2520.

ICPR-2016-MarcaciniCD #distance #on the

On combining Websensors and DTW distance for kNN Time Series Forecasting (RMM, JCC, JD), pp. 2521–2525.

ICPR-2016-Valverde-Rebaza #network #predict #social

Exploiting social and mobility patterns for friendship prediction in location-based social networks (JCVR, MR, PP, AdAL), pp. 2526–2531.

ICPR-2016-Prado-RomeroA #detection

Detecting contextual collective anomalies at a Glance (MAPR, AGA), pp. 2532–2537.

ICPR-2016-LuoTYZ #adaptation #approximate #matrix

Dual approximated nuclear norm based matrix regression via adaptive line search scheme (LL, QT, JY0, YZ), pp. 2538–2543.

ICPR-2016-RidiGH #modelling

Aggregation procedure of Gaussian Mixture Models for additive features (AR, CG, JH), pp. 2544–2549.

ICPR-2016-PuZZDY #approximate #clustering #matrix #multi #robust

Multiview clustering based on Robust and Regularized Matrix Approximation (JP, QZ0, LZ, BD, JY), pp. 2550–2555.

ICPR-2016-DupontMG #detection #recognition

Detecting low-quality reference time series in stream recognition (MD, PFM, NG), pp. 2556–2561.

ICPR-2016-ZemeneAP #retrieval #set

Constrained dominant sets for retrieval (EZ, LTA, MP), pp. 2568–2573.

ICPR-2016-JoyR0V #big data #optimisation #using

Hyperparameter tuning for big data using Bayesian optimisation (TTJ, SR, SG0, SV), pp. 2574–2579.

ICPR-2016-KatsukiI #set

Bayesian regression selecting valuable subset from mixed bag training data (TK, MI), pp. 2580–2585.

ICPR-2016-FagundesSS

Quantile regression of interval-valued data (RAdAF, RMCRdS, YMGS), pp. 2586–2591.

ICPR-2016-ShankarDG #learning #network

Reinforcement Learning via Recurrent Convolutional Neural Networks (TS, SKD, PG), pp. 2592–2597.

ICPR-2016-PreslesD #classification #invariant

A distance-based shape descriptor invariant to similitude and its application to shape classification (BP, JD), pp. 2598–2603.

ICPR-2016-MeyL #approach #self

A soft-labeled self-training approach (AM, ML), pp. 2604–2609.

ICPR-2016-GwonCK #network

Deep Sparse-coded Network (DSN) (YG, MC, HTK), pp. 2610–2615.

ICPR-2016-VoTPV #classification #detection #modelling

Model-based classification and novelty detection for point pattern data (BNV, NQT, DQP, BTV), pp. 2622–2627.

ICPR-2016-Lan0DAH #bound #matrix

A PAC bound for joint matrix completion based on Partially Collective Matrix Factorization (CL, XL0, YD, JSA, JH), pp. 2628–2633.

ICPR-2016-BaiCWJ0H #classification #clustering #graph #kernel

Shape classification with a vertex clustering graph kernel (LB0, LC, YW0, XJ0, XB0, ERH), pp. 2634–2639.

ICPR-2016-RaytchevKKTK #learning

Ensemble-based local learning for high-dimensional data regression (BR, YK, MK, TT, KK), pp. 2640–2645.

ICPR-2016-YangL #learning #nondeterminism #using

Active learning using uncertainty information (YY, ML), pp. 2646–2651.

ICPR-2016-WangL #named #state machine

D-LSM: Deep Liquid State Machine with unsupervised recurrent reservoir tuning (QW0, PL0), pp. 2652–2657.

ICPR-2016-YanMK #generative

Generating commentaries for tennis videos (FY0, KM, JK), pp. 2658–2663.

ICPR-2016-Lobato-RiosHCT #comparison #linear #network #quality

Linear model optimizer vs Neural Networks: A comparison for improving the quality and saving of LED-Lighting control systems (VLR, VdRHC, JACO, JFMT), pp. 2664–2669.

ICPR-2016-HuangY #3d #network #using

Point cloud labeling using 3D Convolutional Neural Network (JH0, SY), pp. 2670–2675.

ICPR-2016-JamesC #classification #social #social media

Evolutionary data purification for social media classification (SJ, JPC), pp. 2676–2681.

ICPR-2016-NilssonO #classification #complexity #pattern matching #pattern recognition #recognition

Estimates of Classification Complexity for Myoelectric Pattern Recognition (NN, MOC), pp. 2682–2687.

ICPR-2016-JiaoZ #learning #multi #taxonomy #using

Multiple Instance Dictionary Learning using Functions of Multiple Instances (CJ, AZ), pp. 2688–2693.

ICPR-2016-OrriteRM #distance #learning #process #sequence #using

One-shot learning of temporal sequences using a distance dependent Chinese Restaurant Process (CO, MR, CM), pp. 2694–2699.

ICPR-2016-MoutafisLK #learning #metric

Regression-based metric learning (PM, ML, IAK), pp. 2700–2705.

ICPR-2016-YunLYKC #detection

Attention-inspired moving object detection in monocular dashcam videos (KY, JL, SY, SWK, JYC0), pp. 2706–2711.

ICPR-2016-RampalSI #estimation #performance

Fast and accurate scale estimation method for object tracking (KR, KS, HI), pp. 2712–2715.

ICPR-2016-WangLLCL #learning #visual notation

Visual tracking via sparsity pattern learning (YW, YL0, ZL, LFC, HL), pp. 2716–2721.

ICPR-2016-DasBC #set

An intensity- and region-guided narrow-band level set model for contour tracking (SD, SMB, ASC), pp. 2722–2727.

ICPR-2016-XiaoY #performance

Efficient tracking with distinctive target colors and silhouette (CX, AY), pp. 2728–2733.

ICPR-2016-LiZYK #adaptation

Adaptive and compressive target tracking based on feature point matching (FL, YZ, WQY0, RK), pp. 2734–2739.

ICPR-2016-TakahashiIKOM #multi #robust #using

Robust volleyball tracking system using multi-view cameras (MT, KI, MK, HO, TM), pp. 2740–2745.

ICPR-2016-QuachDLB16a #3d

Depth-based 3D hand pose tracking (KGQ, CND, KL, TDB), pp. 2746–2751.

ICPR-2016-WangJ #artificial reality #realtime

Real time eye gaze tracking with Kinect (KW, QJ), pp. 2752–2757.

ICPR-2016-SongHZMQ

Edge-guided depth map enhancement (XS, HH, FZ, XM, XQ), pp. 2758–2763.

ICPR-2016-ZhangHYK #clique #visual notation

Maximum clique based RGB-D visual odometry (YZ, ZH, JY0, HK), pp. 2764–2769.

ICPR-2016-KitaK

Virtual flattening of clothing item held in the air (YK, NK), pp. 2770–2776.

ICPR-2016-YuenMT #algorithm #dataset #evaluation #on the

On looking at faces in an automobile: Issues, algorithms and evaluation on naturalistic driving dataset (KY, SM, MMT), pp. 2777–2782.

ICPR-2016-MartinROT #case study #coordination

Preparatory coordination of head, eyes and hands: Experimental study at intersections (SM, AR, EOB, MMT), pp. 2783–2788.

ICPR-2016-Perez-YusLG #hybrid #novel

A novel hybrid camera system with depth and fisheye cameras (APY, GLN, JJG), pp. 2789–2794.

ICPR-2016-CardosoMA #analysis #performance #problem

Plücker correction problem: Analysis and improvements in efficiency (JRC, PM, HA), pp. 2795–2800.

ICPR-2016-HaddadLTS #recognition

Initialized Iterative Closest Point for bone recognition in ultrasound volumes (OH, JL, JT, ES), pp. 2801–2806.

ICPR-2016-YokozukaTMB #refinement

Accurate depth-map refinement by per-pixel plane fitting for stereo vision (MY, KT, OM, AB), pp. 2807–2812.

ICPR-2016-AbarghoueiGB #3d #fourier

Back to Butterworth - a Fourier basis for 3D surface relief hole filling within RGB-D imagery (AAA, GPdLG, TPB), pp. 2813–2818.

ICPR-2016-BachaAB #probability #recognition #using #visual notation

Event recognition in photo albums using probabilistic graphical model and feature relevance (SB, MSA, NB), pp. 2819–2823.

ICPR-2016-RubioYSM #bound #named #segmentation

BASS: Boundary-Aware Superpixel Segmentation (AR, LY, ESS, FMN), pp. 2824–2829.

ICPR-2016-PalaniappanPAVF #detection #using

Moving object detection for vehicle tracking in Wide Area Motion Imagery using 4D filtering (KP, MP, HA, RV, JF, FB, AB, SS, EB, RMR, GS), pp. 2830–2835.

ICPR-2016-SwamiDKV #detection #image #robust

A robust flash image shadow detection method and seamless recovery of shadow regions (KS, SKD, GK, AV), pp. 2836–2841.

ICPR-2016-NahaW16a #learning #segmentation #using

Object figure-ground segmentation using zero-shot learning (SN, YW0), pp. 2842–2847.

ICPR-2016-ChienKSF #online #visual notation

Visual odometry driven online calibration for monocular LiDAR-camera systems (HJC, RK, NS, UF), pp. 2848–2853.

ICPR-2016-SerinoB #3d #using

Using local convexities as anchor points for 3D curve skeletonization (LS, GSdB), pp. 2854–2859.

ICPR-2016-DahlanHS

Reflectance-aware optical flow (HAD, ERH, WAPS), pp. 2860–2865.

ICPR-2016-ChakrabortyPK #information management #recognition #speech #using

Spontaneous speech emotion recognition using prior knowledge (RC, MP, SKK), pp. 2866–2871.

ICPR-2016-ZhengCZZL #independence #network #using

Text-independent voice conversion using deep neural network based phonetic level features (HZ, WC, TZ, SZ, ML0), pp. 2872–2877.

ICPR-2016-ZhangLQ #network #using

Wake-up-word spotting using end-to-end deep neural network system (SZ, WL, YQ0), pp. 2878–2883.

ICPR-2016-SakaiMK #optimisation

Unmixing three types of lung sounds by convex optimization (TS, SM, SK), pp. 2884–2888.

ICPR-2016-ZhangQ #adaptation #agile #modelling #network

Rapid feature space MLLR speaker adaptation for deep neural network acoustic modeling (SZ, YQ0), pp. 2889–2894.

ICPR-2016-ZhaoZWJ #learning #multi

Multilingual articulatory features augmentation learning (YZ, RZ, XW0, QJ), pp. 2895–2899.

ICPR-2016-PironkovDD #automation #learning #multi #recognition #speech

Speaker-aware Multi-Task Learning for automatic speech recognition (GP, SD, TD), pp. 2900–2905.

ICPR-2016-ZhangGST #network #recognition

Application of pronunciation knowledge on phoneme recognition by LSTM neural network (BZ, YG, YS, BT), pp. 2906–2911.

ICPR-2016-LiLTPL #fine-grained #recognition #retrieval

Cross-scenario clothing retrieval and fine-grained style recognition (ZL, YL, WT, YP, YL), pp. 2912–2917.

ICPR-2016-TzelepiT #image #learning #retrieval

Exploiting supervised learning for finetuning deep CNNs in content based image retrieval (MT, AT), pp. 2918–2923.

ICPR-2016-ZhangT #automation #encoding #generative #video

Automatic video description generation via LSTM with joint two-stream encoding (CZ, YT), pp. 2924–2929.

ICPR-2016-WangZMLCL #difference #image #retrieval

Mutli-channel micro-structure difference descriptor for image retrieval (XW, CZ, DM, CL, YC, ZL), pp. 2930–2935.

ICPR-2016-Ye0L #3d #network #retrieval #sketching

3D sketch-based 3D model retrieval with convolutional neural network (YY, BL0, YL), pp. 2936–2941.

ICPR-2016-LuZJDTSX0 #query

Smart query expansion scheme for CDVS based on illumination and key features (TL, CZ, HJ, LD, LT, JS, XX, WG0), pp. 2942–2947.

ICPR-2016-KannaoG #segmentation

Story segmentation in TV news broadcast (RK, PG), pp. 2948–2953.

ICPR-2016-LiangSWMWSG #image #learning #optimisation #performance #precise #retrieval #similarity

Optimizing top precision performance measure of content-based image retrieval by learning similarity function (RZL, LS, HW, JM, JJYW, QS, YG), pp. 2954–2958.

ICPR-2016-AghaeiDR #detection #interactive #social

With whom do I interact? Detecting social interactions in egocentric photo-streams (MA, MD, PR), pp. 2959–2964.

ICPR-2016-AhmedS #named #novel #realtime #video

StableFlow: A novel real-time method for digital video stabilization (AA, MSS), pp. 2965–2970.

ICPR-2016-PandaDR #multi #network #summary #video

Video summarization in a multi-view camera network (RP, AD, AKRC), pp. 2971–2976.

ICPR-2016-NguyenEAB #named

HOOFR: An enhanced bio-inspired feature extractor (DDN, AE, EA, SB), pp. 2977–2982.

ICPR-2016-OrtellsM #case study #detection

Detection of duplicate identities in streams of biometric samples: A gait-based case study (JO, RAM), pp. 2983–2988.

ICPR-2016-HafemannSO #using #verification

Analyzing features learned for Offline Signature Verification using Deep CNNs (LGH, RS, LSO), pp. 2989–2994.

ICPR-2016-ZhangHMCP #3d #analysis #detection #image

Face spoofing detection based on 3D lighting environment analysis of image pair (XZ, XH, MM, CC0, SP), pp. 2995–3000.

ICPR-2016-AgarwalSV #classification

Fingerprint sensor classification via Mélange of handcrafted features (AA0, RS0, MV), pp. 3001–3006.

ICPR-2016-YangWL

The GIST of aligning faces (SY, AW, BCL), pp. 3007–3012.

ICPR-2016-FeiWZYZ #image #multi

Local multiple directional pattern of palmprint image (LF, JW, ZZ0, KY0, ZZ), pp. 3013–3018.

ICPR-2016-XuK #geometry #retrieval

A geometric-based tattoo retrieval system (XX, AWKK), pp. 3019–3024.

ICPR-2016-BertoliniOS #difference #identification #multi #using

Multi-script writer identification using dissimilarity (DB, LSO, RS), pp. 3025–3030.

ICPR-2016-PrimoracTBS #recognition

Audio-visual biometric recognition via joint sparse representations (RP, RT, MB, FAS), pp. 3031–3035.

ICPR-2016-MurakamiKT #on the #strict

On restricting modalities in likelihood-ratio based biometric score fusion (TM, YK, KT), pp. 3036–3042.

ICPR-2016-Chun #adaptation #authentication #using

Small scale single pulse ECG-based authentication using GLRT that considers T wave shift and adaptive template update with prior information (SYC), pp. 3043–3048.

ICPR-2016-ItoA #authentication #using

A score calculation method using positional information of feature points for biometric authentication (KI, TA), pp. 3049–3054.

ICPR-2016-SunBTTH #detection #learning #locality #using

Tattoo detection and localization using region-based deep learning (ZS, JB, PT, MT, AH), pp. 3055–3060.

ICPR-2016-Gonzalez-SosaDV #estimation #gender

Image-based gender estimation from body and face across distances (EGS, AD, RVR, JLD, FB, JF), pp. 3061–3066.

ICPR-2016-Martinho-Corbishley #identification #semantics

Retrieving relative soft biometrics for semantic identification (DMC, MSN, JNC), pp. 3067–3072.

ICPR-2016-SatoMKTKT #automation #gesture

Automated help system for novice older users from touchscreen gestures (DS0, TM, TK, YT, TK, HT), pp. 3073–3078.

ICPR-2016-RichterLB #automation #visual notation #word

Knowing when you don't: Bag of visual words with reject option for automatic visual inspection of bulk materials (MR0, TL, JB), pp. 3079–3084.

ICPR-2016-GarrettRS #3d #artificial reality #process

GPU-accelerated descriptor extraction process for 3D registration in Augmented Reality (TG, RR, JWS), pp. 3085–3090.

ICPR-2016-DaoodRB #classification #multi #recognition #using

Pollen recognition using a multi-layer hierarchical classifier (AD, ER, MB), pp. 3091–3096.

ICPR-2016-KsibiMA #identification

Topological weighted fisher vectors for person re-identification (SK, MM, CBA), pp. 3097–3102.

ICPR-2016-Rowekamp #performance #using

Fast thresholding of high dimensional Euclidean distances using binary squaring (JHR), pp. 3103–3108.

ICPR-2016-GranaBBV #benchmark #component #metric

YACCLAB - Yet Another Connected Components Labeling Benchmark (CG, FB, LB, RV), pp. 3109–3114.

ICPR-2016-SarafianosNK #estimation #predict

Predicting privileged information for height estimation (NS, CN, IAK), pp. 3115–3120.

ICPR-2016-RozsaGRB #question #robust

Are facial attributes adversarially robust? (AR, MG, EMR, TEB), pp. 3121–3127.

ICPR-2016-ShwetaE0B #architecture #identification #interactive #learning

A deep learning architecture for protein-protein Interaction Article identification (S, AE, SS0, PB), pp. 3128–3133.

ICPR-2016-ChowdhuryBMKS #image #network #performance #retrieval #using

An efficient radiographic Image Retrieval system using Convolutional Neural Network (MC, SRB, RM, MKK, ÖS), pp. 3134–3139.

ICPR-2016-BolanosR #locality #recognition

Simultaneous food localization and recognition (MB, PR), pp. 3140–3145.

ICPR-2016-BorgaAL #image #learning #segmentation

Semi-supervised learning of anatomical manifolds for atlas-based segmentation of medical images (MB, TA, ODL), pp. 3146–3149.

ICPR-2016-TizhooshMZD #image #retrieval #using

Barcodes for medical image retrieval using autoencoded Radon transform (HRT, CM, SZ, SD), pp. 3150–3155.

ICPR-2016-Li0RNVAL #multi #predict

Multiple adverse effects prediction in longitudinal cancer treatment (CL0, SG0, SR, VN0, SV, DA, TL), pp. 3156–3161.

ICPR-2016-OrueG #graph #process #recognition #using

Face recognition using activities of directed graphs in spatial pyramid (JPMO, WNG), pp. 3162–3167.

ICPR-2016-NguyenKDCPC16a #fault #segmentation

Segmentation of defects on log surface from terrestrial lidar data (VTN, BK, IDR, FC, AP, TC), pp. 3168–3173.

ICPR-2016-TranVPV #clustering

Clustering for point pattern data (NQT, BNV, DQP, BTV), pp. 3174–3179.

ICPR-2016-WanLT #similarity

Simplifying Gaussian mixture model via model similarity (YW, XL, YT), pp. 3180–3185.

ICPR-2016-Nilsson #consistency #learning #taxonomy

Sparse coding with unity range codes and label consistent discriminative dictionary learning (MN), pp. 3186–3191.

ICPR-2016-ZhaoIBJ #fault #predict #using

Wind turbine fault prediction using soft label SVM (RZ, MRAI, KPB, QJ), pp. 3192–3197.

ICPR-2016-SharabatiX #approach #performance #polynomial

Fast local polynomial regression approach for speckle noise removal (WKS, BX), pp. 3198–3203.

ICPR-2016-Bodis-SzomoruRG #performance #re-engineering

Efficient volumetric fusion of airborne and street-side data for urban reconstruction (ABS, HR, LVG), pp. 3204–3209.

ICPR-2016-KobayashiO #component #image #multi

Separating reflection components in images under multispectral and multidirectional light sources (NK, TO), pp. 3210–3215.

ICPR-2016-LeonardMHC #2d #composition #similarity

A 2D shape structure for decomposition and part similarity (KL, GM, SH, AC), pp. 3216–3221.

ICPR-2016-ZhuangYH #approach #modelling #retrieval #scalability #video

DLSTM approach to video modeling with hashing for large-scale video retrieval (NZ, JY0, KAH), pp. 3222–3227.

ICPR-2016-XuSARS #learning #multi #recognition #retrieval #taxonomy

Multi-Paced Dictionary Learning for cross-domain retrieval and recognition (DX0, JS, XAP, ER0, NS), pp. 3228–3233.

ICPR-2016-LiuGX #constraints #network #synthesis

Texture synthesis through convolutional neural networks and spectrum constraints (GL0, YG, GSX), pp. 3234–3239.

ICPR-2016-ShanXS #detection #video

A new method for spatiotemporal textual saliency detection in video (SS, HX, FS), pp. 3240–3245.

ICPR-2016-HeLYHHDL #benchmark #framework #metric #recognition

Context-aware mathematical expression recognition: An end-to-end framework and a benchmark (WH, YL, FY, HH, JH, ED, CLL), pp. 3246–3251.

ICPR-2016-SunHH #clustering

Structural feature-based event clustering for short text streams (ZS, JH, HH), pp. 3252–3257.

ICPR-2016-CoteA #analysis #documentation #evaluation #image #statistics

Layered ground truth: Conveying structural and statistical information for document image analysis and evaluation (MC, ABA), pp. 3258–3263.

ICPR-2016-YeZL #classification #documentation #network #online #random

Joint training of conditional random fields and neural networks for stroke classification in online handwritten documents (JYY, YMZ, CLL), pp. 3264–3269.

ICPR-2016-SunHLK #learning #multi #network #recognition

Multiple Instance Learning Convolutional Neural Networks for object recognition (MS, TXH, MCL, AKR), pp. 3270–3275.

ICPR-2016-FengLXYM #network #traversal

Face hallucination by deep traversal network (ZXF, JHL, XX, DY, LM), pp. 3276–3281.

ICPR-2016-ZhuWLZ #gender #learning #lightweight #network #recognition

Learning a lightweight deep convolutional network for joint age and gender recognition (LZ, KW, LL, LZ0), pp. 3282–3287.

ICPR-2016-DushkoffMP #algorithm

A temporally coherent neural algorithm for artistic style transfer (MD, RM, RWP), pp. 3288–3293.

ICPR-2016-HaneP #3d #overview #re-engineering #semantics

An overview of recent progress in volumetric semantic 3D reconstruction (CH, MP), pp. 3294–3307.

ICPR-2016-HuangYZZ #classification #reduction #robust

Rough Neighborhood Covering Reduction for robust classification (WH, XY, CZ, NZ), pp. 3308–3313.

ICPR-2016-TaxW #precise

Class-dependent, non-convex losses to optimize precision (DMJT, FW), pp. 3314–3319.

ICPR-2016-DubosBAS #classification

ROC-based cost-sensitive classification with a reject option (CD, SB, SA, RS), pp. 3320–3325.

ICPR-2016-Sahbi #detection #image #interactive

Misalignment resilient CCA for interactive satellite image change detection (HS), pp. 3326–3331.

ICPR-2016-Kamkar0LPV #graph #predict #using

Stable clinical prediction using graph support vector machines (IK, SG0, CL0, DQP, SV), pp. 3332–3337.

ICPR-2016-YeWH #generative #graph #using

Analyzing graph time series using a generative model (CY, RCW0, ERH), pp. 3338–3343.

ICPR-2016-IshiiSIMSIN #classification #detection #multi

Detection by classification of buildings in multispectral satellite imagery (TI, ESS, SI, YM, AS, HI0, RN), pp. 3344–3349.

ICPR-2016-Ohn-BarT16a #detection

To boost or not to boost? On the limits of boosted trees for object detection (EOB, MMT), pp. 3350–3355.

ICPR-2016-AzzopardiFAP

Increased generalization capability of trainable COSFIRE filters with application to machine vision (GA, LFR, EA, NP), pp. 3356–3361.

ICPR-2016-GouWWWJ #detection

Learning-by-synthesis for accurate eye detection (CG, YW0, KW, FYW0, QJ), pp. 3362–3367.

ICPR-2016-QinJYW #image #recognition #using

Building facade recognition from aerial images using Delaunay Triangulation induced feature perceptual grouping (XQ, MJ, XY, JW0), pp. 3368–3373.

ICPR-2016-GalaiNB #mobile

Crossmodal point cloud registration in the Hough space for mobile laser scanning data (BG, BN, CB), pp. 3374–3379.

ICPR-2016-Ren0YZH0 #detection #novel #recognition

A novel text structure feature extractor for Chinese scene text detection and recognition (XR, KC0, XY, YZ0, JH, JS0), pp. 3380–3385.

ICPR-2016-BappyR #recognition

Inter-dependent CNNs for joint scene and object recognition (JHB, AKRC), pp. 3386–3391.

ICPR-2016-Ohn-BarT16b #question #what

What makes an on-road object important? (EOB, MMT), pp. 3392–3397.

ICPR-2016-WangZYP #classification #detection

Anomaly detection in crowded scenes by SL-HOF descriptor and foreground classification (SW, EZ, JY, FP), pp. 3398–3403.

ICPR-2016-EumD #evaluation #multi #using

Content selection using frontalness evaluation of multiple frames (SE, DSD), pp. 3404–3409.

ICPR-2016-HeCL #identification #re-engineering

Cross-view transformation based sparse reconstruction for person re-identification (WXH, YCC, JHL), pp. 3410–3415.

ICPR-2016-StunerCP #network #recognition #word

Cascading BLSTM networks for handwritten word recognition (BS, CC0, TP), pp. 3416–3421.

ICPR-2016-0001PL #correlation #independence #verification

Compact correlated features for writer independent signature verification (AD0, UP0, JL0), pp. 3422–3427.

ICPR-2016-DuWZH #markov #network #recognition

Deep neural network based hidden Markov model for offline handwritten Chinese text recognition (JD, ZRW, JFZ, JSH), pp. 3428–3433.

ICPR-2016-WichtFH #keyword #learning

Deep learning features for handwritten keyword spotting (BW, AF0, JH), pp. 3434–3439.

ICPR-2016-ZhongZYL #network #recognition

Handwritten Chinese character recognition with spatial transformer and deep residual networks (ZZ, XYZ, FY, CLL), pp. 3440–3445.

ICPR-2016-Julca-AguilarHM #classification

Subexpression and dominant symbol histograms for spatial relation classification in mathematical expressions (FDJA, NSTH, HM, CVG), pp. 3446–3451.

ICPR-2016-TocaPC #classification

AutoMarkov DNNs for object classification (CT, CP, MC), pp. 3452–3457.

ICPR-2016-AbdicFBARMS #approach #detection #learning

Detecting road surface wetness from audio: A deep learning approach (IA, LF, DEB, WA, BR, EM, BWS), pp. 3458–3463.

ICPR-2016-McCaneS #network #performance

Deep networks are efficient for circular manifolds (BM, LS), pp. 3464–3469.

ICPR-2016-TabernikKWL #composition #network #towards

Towards deep compositional networks (DT, MK, JLW, AL), pp. 3470–3475.

ICPR-2016-DasguptaN #classification #fine-grained #multi

Leveraging multiple tasks to regularize fine-grained classification (RD, AMN), pp. 3476–3481.

ICPR-2016-Liu0 #complexity #online

One-pass online SVM with extremely small space complexity (YL, JX0), pp. 3482–3487.

ICPR-2016-CorniaBSC #multi #network #predict

A deep multi-level network for saliency prediction (MC, LB, GS0, RC), pp. 3488–3493.

ICPR-2016-NieZJ #data transformation #network #representation

Latent regression Bayesian network for data representation (SN, YZ, QJ), pp. 3494–3499.

ICPR-2016-YamashitaFYF #detection #multi #network #using

Pedestrian and part position detection using a regression-based multiple task deep convolutional neural network (TY, HF, YY, HF), pp. 3500–3505.

ICPR-2016-XuT #3d #learning #network

Beam search for learning a deep Convolutional Neural Network of 3D shapes (XX, ST), pp. 3506–3511.

ICPR-2016-PathirageLL #recognition

Discriminant auto encoders for face recognition with expression and pose variations (CSNP, LL0, WL), pp. 3512–3517.

ICPR-2016-Burlina #named #performance

MRCNN: A stateful Fast R-CNN (PB), pp. 3518–3523.

ICPR-2016-0001CLL #named #recognition

MSR-CNN: Applying motion salient region based descriptors for action recognition (ZT0, JC, YL, BL), pp. 3524–3529.

ICPR-2016-TobiasDRMF #case study #mobile #network #recognition

Convolutional Neural Networks for object recognition on mobile devices: A case study (LT, AD, FR0, GM, RF), pp. 3530–3535.

ICPR-2016-GhoshC #feature model

Deep feature extraction in the DCT domain (AG, RC), pp. 3536–3541.

ICPR-2016-Pham0PV #network #performance

Faster training of very deep networks via p-norm gates (TP, TT0, DQP, SV), pp. 3542–3547.

ICPR-2016-Uchida0O #network

Coupled convolution layer for convolutional neural network (KU, MT0, MO), pp. 3548–3553.

ICPR-2016-WangLP #network #visual notation

Finetuning Convolutional Neural Networks for visual aesthetics (YW, YL, FP), pp. 3554–3559.

ICPR-2016-Triantafyllidou #detection #incremental #learning #network

Face detection based on deep convolutional neural networks exploiting incremental facial part learning (DT, AT), pp. 3560–3565.

ICPR-2016-NogueiraMCSS #image #learning #semantics

Learning to semantically segment high-resolution remote sensing images (KN, MDM, JC, WRS, JAdS), pp. 3566–3571.

ICPR-2016-KabkabHC #network #on the #performance

On the size of Convolutional Neural Networks and generalization performance (MK, EMH, RC), pp. 3572–3577.

ICPR-2016-NookaCVSP #adaptation #classification #network

Adaptive hierarchical classification networks (SPN, SC, KV, SS, RWP), pp. 3578–3583.

ICPR-2016-NieGJ #feature model #framework #integer #programming

An information theoretic feature selection framework based on integer programming (SN, TG, QJ), pp. 3584–3589.

ICPR-2016-YoshiyasuY #reduction

Nonlinear dimensionality reduction by curvature minimization (YY, EY), pp. 3590–3596.

ICPR-2016-ZhugeHNY #clustering #feature model #graph #using

Unsupervised feature extraction using a learned graph with clustering structure (WZ, CH, FN, DY), pp. 3597–3602.

ICPR-2016-KudoKHT #multi #visualisation

Simultaneous visualization of samples, features and multi-labels (MK, KK, MH, HT), pp. 3603–3608.

ICPR-2016-TasakiLC #estimation

Simplex-based dimension estimation of topological manifolds (HT, RL, JC), pp. 3609–3614.

ICPR-2016-ZhengYYY #feature model #learning #robust

Robust unsupervised feature selection by nonnegative sparse subspace learning (WZ, HY, JY0, JY), pp. 3615–3620.

ICPR-2016-SuCHH #detection #image #modelling #recognition #symmetry #using

Moment-based symmetry detection for scene modeling and recognition using RGB-D images (JYS, SCC, JWH, THH), pp. 3621–3626.

ICPR-2016-KatsukiMI #recognition

Unsupervised object counting without object recognition (TK, TM, TI), pp. 3627–3632.

ICPR-2016-NguyenNVP #clustering #multi #named #parametricity #semistructured data

MCNC: Multi-Channel Nonparametric Clustering from heterogeneous data (TBN, VN0, SV, DQP), pp. 3633–3638.

ICPR-2016-CarbonneauGG #identification #learning #multi #random #using

Witness identification in multiple instance learning using random subspaces (MAC, EG, GG), pp. 3639–3644.

ICPR-2016-OzanKG #approximate #nearest neighbour

Joint K-Means quantization for Approximate Nearest Neighbor Search (ECO, SK, MG), pp. 3645–3649.

ICPR-2016-HouXX0 #classification #graph #learning

Semi-supervised learning competence of classifiers based on graph for dynamic classifier selection (CH, YX, ZX, JS0), pp. 3650–3654.

ICPR-2016-UlmB #learning

Learning tubes (MU, NB), pp. 3655–3660.

ICPR-2016-SubramanianR0SV #multi #parametricity

Bayesian nonparametric Multiple Instance Regression (SS, SR, SG0, PBS, CSV, SV), pp. 3661–3666.

ICPR-2016-GaoYGC #approach #constraints #network #using

Bayesian approach to learn Bayesian networks using data and constraints (XGG, YY, ZgG, DQC0), pp. 3667–3672.

ICPR-2016-KanehiraSH #learning #multi #scalability

True-negative label selection for large-scale multi-label learning (AK, AS, TH), pp. 3673–3678.

ICPR-2016-Kobayashi #data-driven #image #learning #similarity

Learning data-driven image similarity measure (TK), pp. 3679–3684.

ICPR-2016-WangTLW #classification #representation #robust

Information-theoretic atomic representation for robust pattern classification (YW, YYT, LL, PSPW), pp. 3685–3690.

ICPR-2016-VargaS #automation #image #network

Fully automatic image colorization based on Convolutional Neural Network (DV, TS), pp. 3691–3696.

ICPR-2016-ZhangOLO #recognition

Integrating deep features for material recognition (YZ0, MO, XL0, TO), pp. 3697–3702.

ICPR-2016-PistellatoABT #multi #robust

Robust joint selection of camera orientations and feature projections over multiple views (MP, AA, FB, AT), pp. 3703–3708.

ICPR-2016-BylowOK #3d #online #re-engineering #robust

Robust online 3D reconstruction combining a depth sensor and sparse feature points (EB, CO, FK), pp. 3709–3714.

ICPR-2016-CosmoABTRC #approach #image #multi

A game-theoretical approach for joint matching of multiple feature throughout unordered images (LC, AA, FB, AT, ER, DC), pp. 3715–3720.

ICPR-2016-LiCWY #image #optimisation #self

Optimization of radial distortion self-calibration for structure from motion from uncalibrated UAV images (YL, YC, DW, YY), pp. 3721–3726.

ICPR-2016-CuiSH #robust

Robust global translation averaging with feature tracks (HC, SS, ZH), pp. 3727–3732.

ICPR-2016-LuoGPWY #locality #mobile #multi #using

Accurate localization for mobile device using a multi-planar city model (YL, TG, HP, YW, JY), pp. 3733–3738.

ICPR-2016-BergamascoCSAT #estimation #multi #segmentation

Dense multi-view homography estimation and plane segmentation (FB, LC, MS, AA, AT), pp. 3739–3744.

ICPR-2016-EichhardtH #using

Improvement of camera calibration using surface normals (IE, LH), pp. 3745–3750.

ICPR-2016-RoyTL #learning #network

Context-regularized learning of fully convolutional networks for scene labeling (AR, ST, LJL), pp. 3751–3756.

ICPR-2016-Guo0WLW #modelling #recognition

An attention model based on spatial transformers for scene recognition (SG, LL0, WW0, SL, LW0), pp. 3757–3762.

ICPR-2016-JohnKGNMI #learning #modelling #performance #segmentation #using

Fast road scene segmentation using deep learning and scene-based models (VJ, KK, CG, HTN, SM, KI), pp. 3763–3768.

ICPR-2016-AytekinIKG #graph #segmentation

Salient object segmentation based on linearly combined affinity graphs (ÇA, AI, SK, MG), pp. 3769–3774.

ICPR-2016-NaminAP #2d #3d #higher-order #segmentation #semantics #using

2D-3D semantic segmentation using cardinality as higher-order loss (SRN, JMA, LP), pp. 3775–3780.

ICPR-2016-GasparettoCTW

Non-rigid dense bijective maps (AG, LC, AT, RCW0), pp. 3781–3786.

ICPR-2016-MinciulloC #analysis #automation #detection

Fully automated shape analysis for detection of Osteoarthritis from lateral knee radiographs (LM, TFC), pp. 3787–3791.

ICPR-2016-SantaK #algebra #framework #image

An algebraic framework for deformable image registration (ZS, ZK), pp. 3792–3797.

ICPR-2016-FleischmannK #interactive #performance

Fast projector-camera calibration for interactive projection mapping (OF, RK), pp. 3798–3803.

ICPR-2016-NaharJ #estimation

Dense disparity estimation based on feature matching and IGMRF regularization (SN, MVJ), pp. 3804–3809.

ICPR-2016-PalmerBEHA

Calibration, positioning and tracking in a refractive and reflective scene (TP, GB, MTE, LAH, KÅ), pp. 3810–3815.

ICPR-2016-Lourakis #performance

An efficient solution to absolute orientation (MIAL), pp. 3816–3819.

ICPR-2016-PellicanoAH #estimation #robust #video

Robust wide baseline pose estimation from video (NP, EA, SLHM), pp. 3820–3825.

ICPR-2016-Nguyen #automation #generative #image #using

Automatic generation of a realistic looking single image stereogram using stereo vision (MN), pp. 3826–3831.

ICPR-2016-YanRZC #approach #clustering #set

A constrained clustering based approach for matching a collection of feature sets (JY, ZR, HZ, SMC), pp. 3832–3837.

ICPR-2016-AhmedK #learning #multi #taxonomy

Coupled multiple dictionary learning based on edge sharpness for single-image super-resolution (JA, RK), pp. 3838–3843.

ICPR-2016-ZhangSLTWF #adaptation

Adaptive Hashing with Sparse Modification (LZ, QS, DL, XT, PSW, GCF), pp. 3844–3849.

ICPR-2016-AgustssonTG #learning

Regressor Basis Learning for anchored super-resolution (EA, RT, LVG), pp. 3850–3855.

ICPR-2016-LiGYZ #identification

Person re-identification via person DPM based partition (SL, CG, HY, JZ), pp. 3856–3861.

ICPR-2016-RaytchevKTK #kernel #recognition #representation #using

Higher-level representation of local spatio-temporal features for human action recognition using Subspace Matching Kernels (BR, HK, TT, KK), pp. 3862–3867.

ICPR-2016-KovvuriNS #detection #modelling

Segment-based models for event detection and recounting (RK, RN, CGMS), pp. 3868–3873.

ICPR-2016-SamarasMP #identification #robust

Robustness in blind camera identification (SS, VM, IP), pp. 3874–3879.

ICPR-2016-0013LS #3d #approach #retrieval #semantics #sketching

A semantic tree-based approach for sketch-based 3D model retrieval (BL0, YL, JS), pp. 3880–3885.

ICPR-2016-QinSLPT #categorisation #detection #recognition #video

Video scene text frames categorization for text detection and recognition (LQ, PS, TL, UP0, CLT), pp. 3886–3891.

ICPR-2016-ZhangZHH #image

Face image super-resolution via weighted patches regression (YZ, ZZ, GH, ERH), pp. 3892–3897.

ICPR-2016-ElTantawyS #matrix #novel #physics #using

A novel method for segmenting moving objects in aerial imagery using matrix recovery and physical spring model (AE, MSS), pp. 3898–3903.

ICPR-2016-AsplundHTS #approach

A new approach to mathematical morphology on one dimensional sampled signals (TA, CLLH, MJT, RS), pp. 3904–3909.

ICPR-2016-ZhaoSJ #classification #identification #robust

Robust signal identification for dynamic pattern classification (RZ, GS, QJ), pp. 3910–3915.

ICPR-2016-HosseinKhaniKSH #image #random #realtime

Real-time removal of random value impulse noise in medical images (ZH, NK, SMRS, MH, SS, KW, KN), pp. 3916–3921.

ICPR-2016-ZhengTZW #estimation #graph #reduction

Maximal level estimation and unbalance reduction for graph signal downsampling (XZ, YYT, JZ0, PSPW), pp. 3922–3926.

ICPR-2016-AhnKK #quality #visual notation

Patch-based visual microphone for improving quality of sound (JA, YJK, DK0), pp. 3927–3932.

ICPR-2016-VandoniHA #detection #process

Crack detection based on a Marked Point Process model (JV, SLHM, EA), pp. 3933–3938.

ICPR-2016-ZhangCUL #algorithm #performance

MLPF algorithm for tracking fast moving target against light interference (LZ, YC, ZU, TL), pp. 3939–3944.

ICPR-2016-MoralesROOOI #analysis #estimation #video

Outdoor omnidirectional video completion via depth estimation by motion analysis (CM, MR, YO, SO, TO, KI), pp. 3945–3950.

ICPR-2016-ZhangZ #detection #effectiveness #video

Effective real-scenario Video Copy Detection (YZ, XZ), pp. 3951–3956.

ICPR-2016-ShiWXW #adaptation #image #using

OTSU guided adaptive binarization of CAPTCHA image using gamma correction (CS, YW, BX, CW), pp. 3962–3967.

ICPR-2016-TakezawaHT #detection #documentation #image #using

Camera-captured document image perspective distortion correction using vanishing point detection based on Radon transform (YT, MH, ST), pp. 3968–3974.

ICPR-2016-ShangWHF0N #segmentation

Character region segmentation based on Stroke Stable Regions (HS, LW, TH, WF0, JS0, SN), pp. 3975–3980.

ICPR-2016-LyuSZB #image #multi #network

Distinguishing text/non-text natural images with Multi-Dimensional Recurrent Neural Networks (PL, BS, CZ, XB), pp. 3981–3986.

ICPR-2016-TounsiMA #framework #learning #recognition #taxonomy

Supervised dictionary learning in BoF framework for Scene Character recognition (MT, IM, AMA), pp. 3987–3992.

ICPR-2016-YuLC #multi #using

Recognizing text in historical maps using maps from multiple time periods (RY, ZL, YYC), pp. 3993–3998.

ICPR-2016-LiuKWK #classification #recognition #word

Scene text recognition with CNN classifier and WFST-based word labeling (XL, TK, XW, KK), pp. 3999–4004.

ICPR-2016-IwataOWK #detection #recognition #retrieval #video

Recognition and transition frame detection of Arabic news captions for video retrieval (SI, WO, TW, FK), pp. 4005–4010.

ICPR-2016-XieSJFZ #network #recognition

Fully convolutional recurrent network for handwritten Chinese text recognition (ZX, ZS, LJ, ZF, SZ), pp. 4011–4016.

ICPR-2016-KesimanPBO #case study #feature model #image #recognition

Study on feature extraction methods for character recognition of Balinese script on palm leaf manuscript images (MWAK, SP, JCB, JMO), pp. 4017–4022.

ICPR-2016-KhareSKCLB #classification #metric #quality #video

A quad tree based method for blurred and non-blurred video text frames classification through quality metrics (VK, PS, AK, CSC, TL, MB), pp. 4023–4028.

ICPR-2016-HuynhXG #image #representation #segmentation

Morphology-based hierarchical representation with application to text segmentation in natural images (LDH, YX, TG), pp. 4029–4034.

ICPR-2016-JenckelBD #documentation #learning #named #sequence

anyOCR: A sequence learning based OCR system for unlabeled historical documents (MJ, SSB, AD0), pp. 4035–4040.

ICPR-2016-TripathyCNP #invariant #multi #recognition

A scale and rotation invariant scheme for multi-oriented Character Recognition (NT, TC, MN, UP0), pp. 4041–4046.

ICPR-2016-UchidaS #question #what

What does scene text tell us? (SU, YS), pp. 4047–4052.

ICPR-2016-MeiDSB #identification #network

Scene text script identification with Convolutional Recurrent Neural Networks (JM, LD, BS, XB), pp. 4053–4058.

ICPR-2016-KieuCV #documentation #image

Local blur correction for document images (VCK, FC, NV), pp. 4059–4064.

ICPR-2016-NagyS

Table headers: An entrance to the data mine (GN, SCS), pp. 4065–4070.

ICPR-2016-KooliB #documentation #graph #recognition

Inexact graph matching for entity recognition in OCRed documents (NK, AB), pp. 4071–4076.

ICPR-2016-CorbelliBGC #analysis #classification #documentation #layout

Historical document digitization through layout analysis and deep content classification (AC, LB, CG, RC), pp. 4077–4082.

ICPR-2016-YangJNL #network #normalisation #online #recognition #using

Rotation-free online handwritten character recognition using dyadic path signature features, hanging normalization, and deep neural network (WY, LJ, HN, TL), pp. 4083–4088.

ICPR-2016-YangWWJ #multi #recognition

Multiple facial action unit recognition enhanced by facial expressions (JY, SW, SW, QJ), pp. 4089–4094.

ICPR-2016-BhagavatulaAS #estimation #using

Pose estimation using Spectral and Singular Value recomposition (CB, RA, MS), pp. 4095–4100.

ICPR-2016-ZhengCBPC #verification

VLAD encoded Deep Convolutional features for unconstrained face verification (JZ, JCC, NB, VMP, RC), pp. 4101–4106.

ICPR-2016-MaoZCLHY16a #collaboration #learning #recognition #taxonomy

Group and collaborative dictionary pair learning for face recognition (MM, ZZ, ZC, HL, XH, RY), pp. 4107–4111.

ICPR-2016-LuCC #adaptation #metric #verification

Regularized metric adaptation for unconstrained face verification (BL, JCC, RC), pp. 4112–4117.

ICPR-2016-VoSL #ranking #recognition

Facial expression recognition by re-ranking with global and local generic features (DMV, AS, THL), pp. 4118–4123.

ICPR-2016-AcevedoNBM #recognition

Facial expression recognition based on static and dynamic approaches (DA, PN, MEB, MM), pp. 4124–4129.

ICPR-2016-SaeedA #framework #locality #recognition

A framework for joint facial expression recognition and point localization (AS, AAH), pp. 4130–4135.

ICPR-2016-KimV #classification #semantics #using

Deep Action Unit classification using a binned intensity loss and semantic context model (EK, SV), pp. 4136–4141.

ICPR-2016-HuangL #hybrid #recognition

Hybrid hypergraph construction for facial expression recognition (YH, HL), pp. 4142–4147.

ICPR-2016-ZamzamiPGKAS #analysis #approach #automation #multimodal

An approach for automated multimodal analysis of infants' pain (GZ, CYP, DBG, RK, TA, YS0), pp. 4148–4153.

ICPR-2016-WeissenbergRDG #np-hard #optimisation #problem

Dilemma First Search for effortless optimization of NP-hard problems (JW, HR, RD, LVG), pp. 4154–4159.

ICPR-2016-WangB #network #predict

Link prediction via Supervised Dynamic Network Formation (YW0, LB0), pp. 4160–4165.

ICPR-2016-LuoLQ #analysis #bound #optimisation #probability

Bound analysis of natural gradient descent in stochastic optimization setting (ZL, DL, YQ), pp. 4166–4171.

ICPR-2016-AydinA #evolution #mining #sequence

Spatiotemporal event sequence mining from evolving regions (BA, RAA), pp. 4172–4177.

ICPR-2016-XiangXZH #constraints #image

Locally warping-based image stitching by imposing line constraints (TX, GSX, LZ, NH), pp. 4178–4183.

ICPR-2016-ZhangGSSL #robust #using

Robust tensor factorization using maximum correntropy criterion (MZ, YG, CS, JLS, JL), pp. 4184–4189.

ICPR-2016-Altamirano-Gomez #algebra #detection #geometry

Conformal Geometric Algebra method for detection of geometric primitives (GEAG, EBC), pp. 4190–4195.

ICPR-2016-GuanCSRR #image #multimodal #stack

Image stack surface area minimization for groupwise and multimodal affine registration (BHG, JC, MS, SR, AR0), pp. 4196–4201.

ICPR-2016-AncutiAVGB #multi

Multi-scale underwater descattering (CA, COA, CDV, RG, ACB), pp. 4202–4207.

ICPR-2016-Ogino0SO #video

Super high dynamic range video (YO, MT0, TS, MO), pp. 4208–4213.

ICPR-2016-GhaemmaghamiNYS #adaptation #visual notation

Sparse-coded cross-domain adaptation from the visual to the brain domain (PG, MN, YY0, NS), pp. 4214–4219.

ICPR-2016-KhelifiM #approach #image #multi #problem #segmentation

A multi-objective approach based on TOPSIS to solve the image segmentation combination problem (LK, MM), pp. 4220–4225.

ICPR-2016-SagonasPARZ #automation #robust

Back to the future: A fully automatic method for robust age progression (CS, YP, SA, NR, SZ), pp. 4226–4231.

ICPR-2016-SvobodaMB #learning #recognition

Palmprint recognition via discriminative index learning (JS, JM, MMB), pp. 4232–4237.

ICPR-2016-YangA #behaviour #online

Analyzing user behavior in online advertising with facial expressions (SY, LA), pp. 4238–4243.

ICPR-2016-LiKZYP #anti #detection

Generalized face anti-spoofing by detecting pulse from face videos (XL, JK, GZ, PCY, MP), pp. 4244–4249.

ICPR-2016-JordaoSS #approach #detection #multi

A late fusion approach to combine multiple pedestrian detectors (AJ, JSdS, WRS), pp. 4250–4255.

ICPR-2016-LiB #3d #problem #robust

Selection of robust features for the Cover Source Mismatch problem in 3D steganalysis (ZL0, AGB), pp. 4256–4261.

ICPR-2016-SunHL #detection #image #using

Context based face spoofing detection using active near-infrared images (XS0, LH0, CL), pp. 4262–4267.

ICPR-2016-Alonso-PerezERS #identification

A foveation technique applied to face de-identification (VAP, REC, JMRC, LES), pp. 4268–4273.