BibSLEIGH — Proceedings of the 24th International Conference on Pattern Recognition

Proceedings of the 24th International Conference on Pattern Recognition
ICPR, 2018.

KER

@proceedings{ICPR-2018,
	ee            = "https://ieeexplore.ieee.org/xpl/conhome/8527858/proceeding",
	ee            = "https://www.computer.org/csdl/proceedings/icpr/2018/3788/00/index.html",
	isbn          = "978-1-5386-3788-3",
	publisher     = "{IEEE Computer Society}",
	title         = "{Proceedings of the 24th International Conference on Pattern Recognition}",
	year          = 2018,
}

Contents (653 items)

ICPR-2018-DingZXBBLDPZ #contest #detection #image: ICPR2018 Contest on Object Detection in Aerial Images (ODAI-18) (JD, ZZ, GSX, XB, SJB, JL, MD, MP, LZ), pp. 1–6.
ICPR-2018-LingLZG #classification #image #learning #network: Semi-Supervised Learning via Convolutional Neural Network for Hyperspectral Image Classification (ZL, XL, WZ, SG), pp. 1–6.
ICPR-2018-ShiZWTYZ #lens #modelling #network: Radial Lens Distortion Correction by Adding a Weight Layer with Inverted Foveal Models to Convolutional Neural Networks (YS, DZ, JW, XT, XY, HZ), pp. 1–6.
ICPR-2018-HeLYZLGZWZJ #contest #image #multi #robust #web: ICPR2018 Contest on Robust Reading for Multi-Type Web Images (MH, YL, ZY, SZ0, CL, FG, QZ, YW, XZ, LJ), pp. 7–12.
ICPR-2018-ArtaudSDOD #contest #detection #exclamation: Find it! Fraud Detection Contest Report (CA, NS, AD, JMO, VPD), pp. 13–18.
ICPR-2018-TrusheimCM #black box: Boosting Black-Box Variational Inference by Incorporating the Natural Gradient (FT, AC, AM), pp. 19–24.
ICPR-2018-LiuF #classification #sentiment: Introduce More Characteristics of Samples into Cross-domain Sentiment Classification (WL, XF), pp. 25–30.
ICPR-2018-JiangL #classification #collaboration #representation: Discriminative Collaborative Representation and Its Application to Audio Signal Classification (YJ, FHFL), pp. 31–36.
ICPR-2018-LiCQWW #adaptation #learning #network #semantics: Cross-domain Semantic Feature Learning via Adversarial Adaptation Networks (RL, WmC0, SQ, HSW, SW), pp. 37–42.
ICPR-2018-BiFW #constraints #learning #metric: Cayley- Klein Metric Learning with Shrinkage-Expansion Constraints (YB, BF, FW), pp. 43–48.
ICPR-2018-BhaskaruniML #framework #predict #testing: Estimating Prediction Qualities without Ground Truth: A Revisit of the Reverse Testing Framework (DB, FPM, CL), pp. 49–54.
ICPR-2018-MaGWW #kernel #named #symmetry: RotateConv: Making Asymmetric Convolutional Kernels Rotatable (JM, WG, WW0, LW0), pp. 55–60.
ICPR-2018-ManessiR #learning: Learning Combinations of Activation Functions (FM, AR), pp. 61–66.
ICPR-2018-ZhuZZ #learning: Learning Evasion Strategy in Pursuit-Evasion by Deep Q-network (JZ, WZ, ZZ), pp. 67–72.
ICPR-2018-ShiWDYL #generative #network: Data Augmentation with Improved Generative Adversarial Networks (HS, LW, GD, FY, XL), pp. 73–78.
ICPR-2018-LiuMZ #named #performance #quality: Artsy-GAN: A style transfer system with improved quality, diversity and performance (HL, PNM, DZ), pp. 79–84.
ICPR-2018-LinLJ #named #predict #ranking: R2-ResNeXt: A ResNeXt-Based Regression Model with Relative Ranking for Facial Beauty Prediction (LL, LL, LJ), pp. 85–90.
ICPR-2018-HanXZL #composition #image #learning #network: Learning Intrinsic Image Decomposition by Deep Neural Network with Perceptual Loss (GH, XX, WSZ, JL), pp. 91–96.
ICPR-2018-RoyT #higher-order #learning #using: Learning to Learn Second-Order Back-Propagation for CNNs Using LSTMs (AR, ST), pp. 97–102.
ICPR-2018-ChooSJC #classification #multi #network: Multi-scale Recurrent Encoder-Decoder Network for Dense Temporal Classification (SKC, WS, DjJ, NIC), pp. 103–108.
ICPR-2018-Robles-KellyW #image #network: A Convolutional Neural Network for Pixelwise Illuminant Recovery in Colour and Spectral Images (ARK, RW), pp. 109–114.
ICPR-2018-LiZLL #bottom-up #bound #constraints #estimation #multi: Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint (ML, ZZ, JL, XL), pp. 115–120.
ICPR-2018-BolelliBCG #component: Connected Components Labeling on DRAGs (FB, LB, MC, CG), pp. 121–126.
ICPR-2018-HuangWDSL #image #learning #lightweight: Lightweight Deep Residue Learning for Joint Color Image Demosaicking and Denoising (TH, FW, WD, GS, XL0), pp. 127–132.
ICPR-2018-LingLZL #estimation #image #network #performance: Joint Haze-relevant Features Selection and Transmission Estimation via Deep Belief Network for Efficient Single Image Dehazing (ZL, XL, WZ, ML), pp. 133–139.
ICPR-2018-PereraAP #generative #multi #named #network #using: In2I: Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks (PP, MA, VMP), pp. 140–146.
ICPR-2018-ChengLYT #image #named #network #recursion: SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks (XC, XL0, JY0, YT), pp. 147–152.
ICPR-2018-YueZYSH #estimation #image: Deep Joint Noise Estimation and Removal for High ISO JPEG Images (HY, SZ, JY, XS, CH), pp. 153–158.
ICPR-2018-ZhangW #linear #reduction: Linear Discriminative Sparsity Preserving Projections for Dimensionality Reduction (JZ, JW), pp. 159–164.
ICPR-2018-XuPYL #network #process #recognition: Human Activity Recognition Based On Convolutional Neural Network (WX, YP, YY, YL), pp. 165–170.
ICPR-2018-ZhuZ #detection #network: A Comprehensive Study on Upper-Body Detection with Deep Neural Networks (YZ, LZ), pp. 171–176.
ICPR-2018-HeGG #learning #network: Structure Learning of Bayesian Networks by Finding the Optimal Ordering (CCH, XGG, ZgG), pp. 177–182.
ICPR-2018-MaierSSWSCF #learning #network #precise #towards #using: Precision Learning: Towards Use of Known Operators in Neural Networks (AKM, FS, CS, TW, SS, JHC, RF), pp. 183–188.
ICPR-2018-JohnKGKM #estimation #using: Free Space, Visible and Missing Lane Marker Estimation using the PsiNet and Extra Trees Regression (VJ, NMK, CG, KK, SM), pp. 189–194.
ICPR-2018-RathoreBKRP #approximate #clustering #heatmap #scalability: Approximate Cluster Heat Maps of Large High-Dimensional Data (PR, JCB, DK, SR, MP), pp. 195–200.
ICPR-2018-ChenLT #algorithm #approximate #detection #memory management: An Approximate Bayesian Long Short- Term Memory Algorithm for Outlier Detection (CC, XL, GT), pp. 201–206.
ICPR-2018-SunCWX #coordination #learning #metric #online #parallel #rank: Online Low-Rank Metric Learning via Parallel Coordinate Descent Method (GS, YC, QW0, XX), pp. 207–212.
ICPR-2018-LuoZLW #clustering #graph #image #learning: Graph Embedding-Based Ensemble Learning for Image Clustering (XL, LZ0, FL, BW), pp. 213–218.
ICPR-2018-LiuGCL #generative #network: An Extensive Study of Cycle-Consistent Generative Networks for Image-to-Image Translation (YL0, YG, WC, MSL), pp. 219–224.
ICPR-2018-WuXFPL #network #predict: Local and Global Bayesian Network based Model for Flood Prediction (YW, WX, JF, SP, TL), pp. 225–230.
ICPR-2018-YinLZ #clustering #multi: Multi-Source Clustering based on spectral recovery (HY, FL, LZ), pp. 231–236.
ICPR-2018-HouMZ #algorithm #classification: A Voting-Near-Extreme-Learning-Machine Classification Algorithm (HRH, QHM, XNZ), pp. 237–241.
ICPR-2018-ZhangFQS #generative #image #network: Wasserstein Generative Recurrent Adversarial Networks for Image Generating (CZ, YF, BQ, JS), pp. 242–247.
ICPR-2018-YanWSLZ #image #learning #network #using: Image Captioning using Adversarial Networks and Reinforcement Learning (SY, FW, JSS, WL, BZ), pp. 248–253.
ICPR-2018-UchiyamaO #random: Transparent Random Dot Markers (HU, YO), pp. 254–259.
ICPR-2018-LuC #information management #visual notation: A Deep Graphical Model for Layered Knowledge Transfer (WL, FLC), pp. 260–265.
ICPR-2018-XuW #network: Target Group Distribution Pattern Discovery via Convolutional Neural Network (XX, WW), pp. 266–271.
ICPR-2018-Yip0 #multi #recognition: Grouped Multi-Task CNN for Facial Attribute Recognition (CY, HH0), pp. 272–277.
ICPR-2018-WuYSZ #identification #learning #ranking: Joint Semi-supervised Learning and Re-ranking for Vehicle Re-identification (FW, SY, JSS, BZ), pp. 278–283.
ICPR-2018-HanZG #classification #composition #multi #network: Multi-Frequency Decomposition with Fully Convolutional Neural Network for Time Series Classification (YH, SZ, ZG), pp. 284–289.
ICPR-2018-GengLH #graph #novel #symmetry: A Novel Asymmetric Embedding Model for Knowledge Graph Completion (ZG, ZL, YH), pp. 290–295.
ICPR-2018-NiuS0 #graph #learning: Enhancing Knowledge Graph Completion with Positive Unlabeled Learning (JN, ZS, WZ0), pp. 296–301.
ICPR-2018-HumayooC #adaptation: Model-free Knockoffs for SLOPE-Adaptive Variable Selection with Controlled False Discovery Rate (MH, XC), pp. 302–307.
ICPR-2018-KingkanH #generative: Generating Mesh-based Shapes From Learned Latent Spaces of Point Clouds with VAE-GAN (CK, KH), pp. 308–313.
ICPR-2018-Chen #clustering #scalability #similarity: Scalable spectral clustering with cosine similarity (GC), pp. 314–319.
ICPR-2018-JeongJLCY0 #estimation #network: Selective Ensemble Network for Accurate Crowd Density Estimation (JJ, HJ, JL, JC, SY, JYC0), pp. 320–325.
ICPR-2018-YangY #network: Enhanced Network Embedding with Text Information (SY, BY), pp. 326–331.
ICPR-2018-Do0V #graph #multi: Knowledge Graph Embedding with Multiple Relation Projections (KD, TT0, SV), pp. 332–337.
ICPR-2018-YangC0X #adaptation: Unsupervised Domain Adaptation for Neural Machine Translation (ZY0, WC0, FW0, BX0), pp. 338–343.
ICPR-2018-FariaS #analysis #approach #graph #image: A Graph-based Approach for Static Ensemble Selection in Remote Sensing Image Analysis (FAF, SS), pp. 344–349.
ICPR-2018-TavakolianH #automation #estimation #representation: Deep Spatiotemporal Representation of the Face for Automatic Pain Intensity Estimation (MT, AH), pp. 350–354.
ICPR-2018-ZhengZ #approach #classification #network: Accelerating the Classification of Very Deep Convolutional Network by A Cascading Approach (WZ, ZZ), pp. 355–360.
ICPR-2018-ChengNTZ #predict: Prediction Defaults for Networked-guarantee Loans (DC, ZN, YT, LZ0), pp. 361–366.
ICPR-2018-LiZO #identification #video: Identification of ASD Children based on Video Data (JL0, YZ, GO), pp. 367–372.
ICPR-2018-ZhangZW #classification #lightweight #named #network: LD-CNN: A Lightweight Dilated Convolutional Neural Network for Environmental Sound Classification (XZ, YZ, WW), pp. 373–378.
ICPR-2018-NieS #knowledge base: Joint Knowledge Base Embedding with Neighborhood Context (BN, SS), pp. 379–384.
ICPR-2018-WuTL #multi: Privileged Multi-Target Support Vector Regression (GW, YT, DL), pp. 385–390.
ICPR-2018-HuangZL #clustering #embedded #multi: Spectral Embedded Clustering on Multi-Manifold (SH, LZ, FL), pp. 391–396.
ICPR-2018-GuiH #adaptation: Unsupervised Domain Adaptation by regularizing Softmax Activation (CG, JH), pp. 397–402.
ICPR-2018-YeDW #classification #graph: Graph-based Semi-supervised Classification with CRF and RNN (ZY, YD, FW), pp. 403–408.
ICPR-2018-Fan #network: Deep Epitome for Unravelling Generalized Hamming Network (LF), pp. 409–416.
ICPR-2018-GuoHSY #classification #multi #rank: Low Rank Multi-Label Classification with Missing Labels (BG, CH, JS, DY), pp. 417–422.
ICPR-2018-AltinelOO #energy #image: Deep Structured Energy-Based Image Inpainting (FA, MO, TO), pp. 423–428.
ICPR-2018-ChangWZ #linear #network #performance #self: Piecewise Linear Units for Fast Self-Normalizing Neural Networks (YC, XW, SZ), pp. 429–434.
ICPR-2018-LawW #representation #visual notation: Representing Relative Visual Attributes with a Reference-Point-Based Decision Model (MTL, PW), pp. 435–440.
ICPR-2018-YuLH #comparison #network: Curvature-based Comparison of Two Neural Networks (TY, HL, JEH), pp. 441–447.
ICPR-2018-Wang0H #evolution #graph: Directed Graph Evolution from Euler-Lagrange Dynamics (JW, RCW0, ERH), pp. 448–453.
ICPR-2018-SunLHW #algorithm #array #classification #multi: A New ECOC Algorithm for Multiclass Microarray Data Classification (MS, KL, QH, BW), pp. 454–458.
ICPR-2018-PanNZ #matrix #optimisation #orthogonal: Structured Convex Optimization Method for Orthogonal Nonnegative Matrix Factorization (JP, MKN, XZ), pp. 459–464.
ICPR-2018-DornaikaTZ #flexibility #graph #robust: Robust and Flexible Graph-based Semi-supervised Embedding (FD, YET, RZ), pp. 465–470.
ICPR-2018-MaLHY #estimation #hybrid #network #using: Image-based Air Pollution Estimation Using Hybrid Convolutional Neural Network (JM, KL, YH, JY), pp. 471–476.
ICPR-2018-CheQ #estimation #network #segmentation: Dynamic Projected Segmentation Networks For Hand Pose Estimation (YC, YQ), pp. 477–482.
ICPR-2018-LiLXD #named: CascadeNet: Modified ResNet with Cascade Blocks (XL, WL0, XX, QD), pp. 483–488.
ICPR-2018-LuSO #image: Dual-Resolution U-Net: Building Extraction from Aerial Images (KL, YS, SHO), pp. 489–494.
ICPR-2018-CaiLWY #estimation #multi #network: Joint Head Pose Estimation with Multi-task Cascaded Convolutional Networks for Face Alignment (ZC, QL, SW, BY), pp. 495–500.
ICPR-2018-LuoD #reduction: Maximum Gradient Dimensionality Reduction (XL, RJD), pp. 501–506.
ICPR-2018-ZengZQQB0 #image #learning: Single Image Super-Resolution With Learning Iteratively Non-Linear Mapping Between Low- and High-Resolution Sparse Representations (KZ, HZ, YQ, XQ, LB, ZC0), pp. 507–512.
ICPR-2018-WangBZZ #generative #network: Generating Facial Line-drawing with Convolutional Neural Networks (YW, XB, LZ, SZ), pp. 513–516.
ICPR-2018-GrelssonF #exponential #learning #linear #network: Improved Learning in Convolutional Neural Networks with Shifted Exponential Linear Units (ShELUs) (BG, MF), pp. 517–522.
ICPR-2018-RuedaF #learning #process #recognition #representation: Learning Attribute Representation for Human Activity Recognition (FMR, GAF), pp. 523–528.
ICPR-2018-0010KSZSSB: Reflective Field for Pixel-Level Tasks (LZ0, XK, PS, GZ, JS, SAAS, MB), pp. 529–534.
ICPR-2018-WenFLZWF #adaptation #locality: Adaptive Locality Preserving based Discriminative Regression (JW, LF, ZL, ZZ0, JW, XF), pp. 535–540.
ICPR-2018-ZhouMMB #detection #learning: Learning Training Samples for Occlusion Edge Detection and Its Application in Depth Ordering Inference (YZ0, JM, AM, XB), pp. 541–546.
ICPR-2018-CuiZZH #learning #multi #network #recognition #using: Multi-source Learning for Skeleton -based Action Recognition Using Deep LSTM Networks (RC, AZ, SZ, GH0), pp. 547–552.
ICPR-2018-UittenbogaardSV: Conditional Transfer with Dense Residual Attention: Synthesizing traffic signs from street-view imagery (RU, CS, JAV, BB, PHNdW), pp. 553–559.
ICPR-2018-AfonsoPSP #classification #learning #using: Improving Optimum- Path Forest Classification Using Unsupervised Manifold Learning (LCSA, DCGP, ANdS, JPP), pp. 560–565.
ICPR-2018-SokehAMR #segmentation #video: Superframes, A Temporal Video Segmentation (HSS, VA, DM, PR), pp. 566–571.
ICPR-2018-SantacruzS #distance #edit distance #generative #graph #testing: Graph Edit Distance Testing through Synthetic Graphs Generation (PS, FS), pp. 572–577.
ICPR-2018-LuLLZZ #detection #fuzzy: Botnet Detection based on Fuzzy Association Rules (JL, FL, QHL, MZ, XZ), pp. 578–584.
ICPR-2018-SuHK #analysis #classification #component #multi #performance #using: Efficient Text Classification Using Tree-structured Multi-linear Principal Component Analysis (YS, YH, CCJK), pp. 585–590.
ICPR-2018-TayanovKS #classification #learning #predict #using: Prediction-based classification using learning on Riemannian manifolds (VT, AK, CYS), pp. 591–596.
ICPR-2018-ZhuZZ18a #recognition: Two-Stream Gated Fusion ConvNets for Action Recognition (JZ, WZ, ZZ), pp. 597–602.
ICPR-2018-ZhaoZGTW: Rethinking ReLU to Train Better CNNs (GZ, ZZ, HG, PT, JW), pp. 603–608.
ICPR-2018-NguyenLNP #multi #pattern matching #pattern recognition #recognition: Bayesian Multi-Hyperplane Machine for Pattern Recognition (KN, TL, TDN, DQP), pp. 609–614.
ICPR-2018-FangYZZ #network: Diversified Dual Domain-Adversarial Neural Networks (YF, QY, WZ, ZZ), pp. 615–620.
ICPR-2018-SunZJLWY #adaptation #learning #robust #taxonomy: Robust Discriminative Projective Dictionary Pair Learning by Adaptive Representations (YS, ZZ0, WJ, GL, MW0, SY), pp. 621–626.
ICPR-2018-WangWCK #classification #image #learning #metric #multi #set: Multiple Manifolds Metric Learning with Application to Image Set Classification (RW, XJW, KXC, JK), pp. 627–632.
ICPR-2018-XiaoW #animation #network #speech: Dense Convolutional Recurrent Neural Network for Generalized Speech Animation (LX, ZW), pp. 633–638.
ICPR-2018-Pham0V #graph #memory management #network #predict #process: Graph Memory Networks for Molecular Activity Prediction (TP, TT0, SV), pp. 639–644.
ICPR-2018-ZhuZZ18b #learning #recognition #representation: End-to-end Video-level Representation Learning for Action Recognition (JZ, ZZ, WZ), pp. 645–650.
ICPR-2018-ChenWWK #approximate #classification #image #kernel #set: Riemannian kernel based Nyström method for approximate infinite-dimensional covariance descriptors with application to image set classification (KXC, XJW, RW, JK), pp. 651–656.
ICPR-2018-ManessiRBNS #automation #network: Automated Pruning for Deep Neural Network Compression (FM, AR, SB, PN, RS), pp. 657–664.
ICPR-2018-ZhangLXQ #named #network: LHONE: Label Homophily Oriented Network Embedding (LZ, XL, JX, YQ), pp. 665–670.
ICPR-2018-LiHY0CHWL #network #segmentation: Skin Lesion Segmentation via Dense Connected Deconvolutional Network (HL, XH, ZY, FZ0, JZC, LH, TW, BL), pp. 671–675.
ICPR-2018-YuS0 #generative: Generating Adversarial Examples With Conditional Generative Adversarial Net (PY, KS, JL0), pp. 676–681.
ICPR-2018-ZhangWGWXL #detection #effectiveness #learning #network: An Effective Deep Learning Based Scheme for Network Intrusion Detection (HZ, CQW, SG, ZW, YX, YL), pp. 682–687.
ICPR-2018-LiuHH #classification #network: Lifting Scheme Based Deep Network Model for Remote Sensing Imagery Classification (XL, BH, CH), pp. 688–693.
ICPR-2018-WangZTL #classification #representation #robust: Cauchy Matching Pursuit for Robust Sparse Representation and Classification (YW, CZ, YYT, LL), pp. 694–698.
ICPR-2018-XieHLHYL #classification #network: Deeply Supervised Residual Network for HEp-2 Cell Classification (HX, YH, HL, TH, ZY, BL), pp. 699–703.
ICPR-2018-ZhaoYT #network #order #predict #using: Pen Tip Motion Prediction for Handwriting Drawing Order Recovery using Deep Neural Network (BZ, MY, JT), pp. 704–709.
ICPR-2018-Windeatt #analysis #classification #optimisation #using: Optimising Ensemble of Two-Class classifiers using Spectral Analysis (TW), pp. 710–715.
ICPR-2018-PassalisT #information management #network #similarity #using: Neural Network Knowledge Transfer using Unsupervised Similarity Matching (NP, AT), pp. 716–721.
ICPR-2018-SohrabRGI: Subspace Support Vector Data Description (FS, JR, MG, AI), pp. 722–727.
ICPR-2018-LiuZKDYWLJY #classification #image: Data Augmentation via Latent Space Interpolation for Image Classification (XL0, YZ, LK, ZD, JY, JW, SL, PJ, JY), pp. 728–733.
ICPR-2018-PramerdorferKL #3d #bound #classification #multi #network: Multi-View Classification and 3D Bounding Box Regression Networks (CP, MK, MVL), pp. 734–739.
ICPR-2018-NabilIMSQS #detection #network #random: Deep Recurrent Electricity Theft Detection in AMI Networks with Random Tuning of Hyper-parameters (MN, MI0, MMEAM, MS, KAQ, ES), pp. 740–745.
ICPR-2018-LiangYLH #classification #using: A Segmented Local Offset Method for Imbalanced Data Classification Using Quasi-Linear Support Vector Machine (PL, XY, WL, JH), pp. 746–751.
ICPR-2018-BallottaBVC #detection #image #network: Fully Convolutional Network for Head Detection with Depth Images (DB, GB, RV, RC), pp. 752–757.
ICPR-2018-LiuDJQ #classification #image #network #visual notation: Visual Tree Convolutional Neural Network in Image Classification (YL, YD, RJ, PQ), pp. 758–763.
ICPR-2018-JiaZXZH #classification #feature model: Superpixel-Based Feature Extraction and Fusion Method for Hyperspectral and LiDAR Classification (SJ, MZ, JX, JZ, QH), pp. 764–769.
ICPR-2018-YuanWXZ #empirical #estimation #learning #multi: Multiple- Instance Learning with Empirical Estimation Guided Instance Selection (LY, XW, HX, LZ), pp. 770–775.
ICPR-2018-KokakiTKHO #modelling #using: Sequential Fish Catch Forecasting Using Bayesian State Space Models (YK, NT, TK, KH, TO), pp. 776–781.
ICPR-2018-JiaXD #classification #image: Extended Morphological Profile-based Gabor Wavelets for Hyperspectral Image Classification (SJ, HX, XD), pp. 782–787.
ICPR-2018-ZhangLYGGZ #classification #fine-grained: Fine-Grained Age Group Classification in the wild (KZ0, NL, XY, XG, CG, ZZ), pp. 788–793.
ICPR-2018-CaoCHP #identification #learning #metric: Region-specific Metric Learning for Person Re-identification (MC, CC0, XH, SP), pp. 794–799.
ICPR-2018-WangZLYQW #adaptation #rank #representation #robust: Robust Adaptive Low-Rank and Sparse Embedding for Feature Representation (LW, ZZ0, GL, QY, JQ, MW0), pp. 800–805.
ICPR-2018-LiL #learning #metric: Riemannian Metric Learning based on Curvature Flow (YL, RL), pp. 806–811.
ICPR-2018-ZhangSW #linear #network #problem: Cascade Deep Networks for Sparse Linear Inverse Problems (HZ, HS, WW), pp. 812–817.
ICPR-2018-XuDS #estimation #feature model #kernel: Semi-supervised Feature Selection by Mutual Information Based on Kernel Density Estimation (SX, JD, HS), pp. 818–823.
ICPR-2018-Wang #named #network: ReNN: Rule-embedded Neural Networks (HW), pp. 824–829.
ICPR-2018-LuoCCTTKH #using: Oil Price Forecasting Using Supervised GANs with Continuous Wavelet Transform Features (ZL, JC, XJC, KT, TT, TK, SH), pp. 830–835.
ICPR-2018-CaoLZSLS #detection #named #network #performance: ThinNet: An Efficient Convolutional Neural Network for Object Detection (SC, YL, CZ, QSS, PL, SS), pp. 836–841.
ICPR-2018-LinHLC #estimation #image #layout: Indoor Scene Layout Estimation from a Single Image (HJL, SWH, SHL, CKC), pp. 842–847.
ICPR-2018-MeiJSH #dependence #detection #multi: Region and Temporal Dependency Fusion for Multi-label Action Unit Detection (CM, FJ, RS, QH), pp. 848–853.
ICPR-2018-WangM #automation #generative: A method of automatically generating Labanotation from human motion capture data (JW, ZM), pp. 854–859.
ICPR-2018-ZhaoMS #classification #image #named #network: Retraining: A Simple Way to Improve the Ensemble Accuracy of Deep Neural Networks for Image Classification (KZ, TM, ES), pp. 860–867.
ICPR-2018-WangYGC #classification #feature model: Feature Selection Ensemble for Symbolic Data Classification with AHP (MW, XY, CG, YC), pp. 868–873.
ICPR-2018-GarciaLSH #classification #complexity #metric #recommendation #using: Classifier Recommendation Using Data Complexity Measures (LPFG, ACL, MCPdS, TKH), pp. 874–879.
ICPR-2018-DuCWP #distributed #learning #named #representation: Zone2Vec: Distributed Representation Learning of Urban Zones (JD, YC, YW0, JP), pp. 880–885.
ICPR-2018-WangLH #algorithm #multi #performance: An Efficient Budget Allocation Algorithm for Multi-Channel Advertising (XW, PL, AH), pp. 886–891.
ICPR-2018-TsangDX #modelling #network: Recurrent Neural Networks for Financial Time-Series Modelling (GT, JD, XX), pp. 892–897.
ICPR-2018-WangSSL #learning #metric: Nonlinear Metric Learning through Geodesic Interpolation within Lie Groups (ZW, BS, CDS, JL), pp. 898–903.
ICPR-2018-RichtrH #similarity: Dynamic Texture Similarity Criterion (RR, MH), pp. 904–909.
ICPR-2018-GasparettoRBPCB #network: Cross-Dataset Data Augmentation for Convolutional Neural Networks Training (AG, DR, FB, MP, LC, MB, EU, AA), pp. 910–915.
ICPR-2018-Dey0GVLP #image #learning #multi #retrieval #sketching #using: Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch (SD, AD0, SKG, EV, JL0, UP0), pp. 916–921.
ICPR-2018-YuanZLQ0S #adaptation #canonical #correlation #learning #parallel #recognition: Learning Parallel Canonical Correlations for Scale-Adaptive Low Resolution Face Recognition (YY, ZZ, YL0, JPQ, BL0, XBS), pp. 922–927.
ICPR-2018-FonalZW #algorithm #classification #composition: Feature-Fusion HALS-based Algorithm for Linked CP Decomposition Model in Application to Joint EMG/MMG Signal Classification (KF, RZ, AW), pp. 928–933.
ICPR-2018-BlumenthalDBBG #distance #edit distance #graph #polynomial #problem: Quasimetric Graph Edit Distance as a Compact Quadratic Assignment Problem (DBB, ÉD, SB, LB, JG), pp. 934–939.
ICPR-2018-Yan0R #classification #framework #performance #representation #scalability: An Efficient Deep Representation Based Framework for Large-Scale Terrain Classification (YY, AR0, SR), pp. 940–945.
ICPR-2018-HuJZZS #multi #recognition: Multi-task Micro-expression Recognition Combining Deep and Handcrafted Features (CH, DJ, HZ, XZ, YS), pp. 946–951.
ICPR-2018-GaoDS #learning: Discernibility Matrix-Based Ensemble Learning (SG, JD, HS), pp. 952–957.
ICPR-2018-YuWK #retrieval: Semi-supervised Hashing for Semi-Paired Cross-View Retrieval (JY, XJW, JK), pp. 958–963.
ICPR-2018-BandyopadhyayND #approach #named: DivGroup: A Diversified Approach to Divide Collection of Patterns into Uniform Groups (SB, SN, RD, NMM), pp. 964–969.
ICPR-2018-BoubrahimiMAHA #approximate #scalability: Scalable kNN Search Approximation for Time Series Data (SFB, RM, BA, SMH, RAA), pp. 970–975.
ICPR-2018-SunZY #automation #embedded #generative #network: Pyramid Embedded Generative Adversarial Network for Automated Font Generation (DS, QZ, JY), pp. 976–981.
ICPR-2018-GuoLLL #adaptation #identification #kernel #ranking: Density-Adaptive Kernel based Re-Ranking for Person Re-Identification (RPG, CGL, YL, JL), pp. 982–987.
ICPR-2018-LiuMXP #image #network #semantics #synthesis: Semantic Image Synthesis via Conditional Cycle-Generative Adversarial Networks (XL, GM, SX, CP), pp. 988–993.
ICPR-2018-JiangL18a #analysis #reduction: Generalized Fisher Discriminant Analysis as A Dimensionality Reduction Technique (YJ, FHFL), pp. 994–999.
ICPR-2018-SahaVJ #learning #named: Class2Str: End to End Latent Hierarchy Learning (SS, GV, CVJ), pp. 1000–1005.
ICPR-2018-KungMZ #adaptation #array #network: Adaptive Tiling: Applying Fixed-size Systolic Arrays To Sparse Convolutional Neural Networks (HTK, BM, SQZ), pp. 1006–1011.
ICPR-2018-HouP #algorithm: A Game- Theoretic Hyper-Graph Matching Algorithm (JH, MP), pp. 1012–1017.
ICPR-2018-ZhangJCXP #approach #graph #kernel #learning #network: Kernel-Weighted Graph Convolutional Network: A Deep Learning Approach for Traffic Forecasting (QZ, QJ, JC, SX, CP), pp. 1018–1023.
ICPR-2018-XuWZWZR0CH #network: Depth-based Subgraph Convolutional Neural Networks (CX, DW, ZZ, BW, DZ, GR, LB0, LC, ERH), pp. 1024–1029.
ICPR-2018-CuiB00JH #graph #hybrid #kernel #learning #network: A Deep Hybrid Graph Kernel Through Deep Learning Networks (LC, LB0, LR0, YW0, YJ0, ERH), pp. 1030–1035.
ICPR-2018-AntensteinerSP #3d #framework #multi #precise: Variational Fusion of Light Field and Photometric Stereo for Precise 3D Sensing within a Multi-Line Scan Framework (DA, SS, TP), pp. 1036–1042.
ICPR-2018-KimuraSDNKBI #3d #representation #using: Representing a Partially Observed Non-Rigid 3D Human Using Eigen-Texture and Eigen-Deformation (RK, AS, FLD, YN, HK, AB, KI), pp. 1043–1048.
ICPR-2018-ElanattilMSFC #re-engineering: Non-rigid Reconstruction with a Single Moving RGB-D Camera (SE, PM, SS, CF, MC), pp. 1049–1055.
ICPR-2018-ShuiWYHGLZ #3d #multi #network #segmentation: 3D Shape Segmentation Based on Viewpoint Entropy and Projective Fully Convolutional Networks Fusing Multi-view Features (PS, PW, FY, BH, YG, KL, YZ0), pp. 1056–1061.
ICPR-2018-WuY0Y #robust #using: Robust ECG Biometrics Using Two-Stage Model (BW, GY, LY0, YY), pp. 1062–1067.
ICPR-2018-ZhengWXHG #adaptation #detection #multi #self: A Noise-Robust Self-Adaptive Multitarget Speaker Detection System (SZ, JW, JX, WNH, JRG), pp. 1068–1072.
ICPR-2018-LiHLHS #consistency #generative #network: Global and Local Consistent Age Generative Adversarial Networks (PL, YH, QL0, RH, ZS), pp. 1073–1078.
ICPR-2018-DiSP #gender #named: GP-GAN: Gender Preserving GAN for Synthesizing Faces from Landmarks (XD, VAS, VMP), pp. 1079–1084.
ICPR-2018-JollyIKU #design #how #network #question: How do Convolutional Neural Networks Learn Design? (SJ, BKI, RK, SU), pp. 1085–1090.
ICPR-2018-LocBO #documentation #image #network #security #using: Document Images Watermarking for Security Issue using Fully Convolutional Networks (CVL, JCB, JMO), pp. 1091–1096.
ICPR-2018-BaraldiCGC #documentation #towards #visual notation: Aligning Text and Document Illustrations: Towards Visually Explainable Digital Humanities (LB, MC, CG, RC), pp. 1097–1102.
ICPR-2018-KonwerBBBB0P #generative #network #using: Staff line Removal using Generative Adversarial Networks (AK, AKB, AB, AKB, PB, PPR0, UP0), pp. 1103–1108.
ICPR-2018-LiZHW #encoding #recognition: Deep Temporal Feature Encoding for Action Recognition (LL, ZZ, YH0, LW0), pp. 1109–1114.
ICPR-2018-GuptaMSM #image #learning #order #ranking #similarity: Learning an Order Preserving Image Similarity through Deep Ranking (NG, SM, SS, SM), pp. 1115–1120.
ICPR-2018-WangZL #detection #generative #network: Anomaly Detection via Minimum Likelihood Generative Adversarial Networks (CW, YMZ, CLL), pp. 1121–1126.
ICPR-2018-WuZ #generative #network: Deep Generative Adversarial Networks for the Sparse Signal Denoising (KW, CZ), pp. 1127–1132.
ICPR-2018-WangCZ #robust: Spatially Coherent Matching for Robust Registration (GW, YC, HZ), pp. 1133–1138.
ICPR-2018-YangDWL #learning: Masked Label Learning for Optical Flow Regression (GY, ZD, SW, ZL), pp. 1139–1144.
ICPR-2018-ZuGBT #performance #scalability: Saliency guided fast interpolation for large displacement optical flow (YZ, KG, XB, WT), pp. 1145–1150.
ICPR-2018-HaindlH #parametricity: BTF Compound Texture Model with Non- Parametric Control Field (MH, VH), pp. 1151–1156.
ICPR-2018-NgoPKD: Convexity invariance of voxel objects under rigid motions (PN, NP, YK, IDR), pp. 1157–1162.
ICPR-2018-SongLXG #classification #encoding #multi #robust: Multi-Scale Cross-Band Encoding of Sectored Local Binary Pattern for Robust Texture Classification (TS, LL, LX, CG), pp. 1163–1168.
ICPR-2018-ChenLW #locality: Locality Preserving Discriminative Complex-Valued Latent Variable Model (SHC, YSL, JCW), pp. 1169–1174.
ICPR-2018-PucherK #distance #edit distance #segmentation: Segmentation Edit Distance (DP, WGK), pp. 1175–1180.
ICPR-2018-NadeemHS #algorithm #automation #detection #image #segmentation #using: An automated airway segmentation algorithm for CT images using topological leakage detection and volume freezing (SAN, EAH, PKS), pp. 1181–1186.
ICPR-2018-00040MLZLY #random #segmentation: A Method for PET-CT Lung Cancer Segmentation based on Improved Random Walk (ZL0, YS0, CM, QL, YZ, HL, DY), pp. 1187–1192.
ICPR-2018-HuangCZZXN #image #segmentation #semantics: Medical Knowledge Constrained Semantic Breast Ultrasound Image Segmentation (KH, HDC, YZ, BZ, PX, CN), pp. 1193–1198.
ICPR-2018-DharaAFWLS #interactive #segmentation: Interactive Segmentation of Glioblastoma for Post-surgical Treatment Follow-up (AKD, EA, MF, JW, EML, RS), pp. 1199–1204.
ICPR-2018-XuCG #learning #modelling #multi #random #using: Common Random Subgraph Modeling Using Multiple Instance Learning (TX, DKYC, IG), pp. 1205–1210.
ICPR-2018-GarrettR #3d #network #performance #using: Fast Descriptor Extraction for Contextless 3D Registration Using a Fully Convolutional Network (TG, RR), pp. 1211–1216.
ICPR-2018-Ye0 #classification #image #invariant #learning: Rotational Invariant Discriminant Subspace Learning For Image Classification (QY, ZZ0), pp. 1217–1222.
ICPR-2018-QiuXC #flexibility #linear #named #network: FReLU: Flexible Rectified Linear Units for Improving Convolutional Neural Networks (SQ, XX, BC), pp. 1223–1228.
ICPR-2018-ZhangWG #adaptation #learning #multi #representation: Adaptive Latent Representation for Multi-view Subspace Learning (YZ, XW, XG), pp. 1229–1234.
ICPR-2018-MerchantSKM #dataset #image #using: Appearance-based data augmentation for image datasets using contrast preserving sampling (AKM, TQS, BK, RM), pp. 1235–1240.
ICPR-2018-JawadAH #graph: Local Binary Patterns for Graph Characterization (MJ, FA, ERH), pp. 1241–1246.
ICPR-2018-ZouLZ #adaptation #clustering #multi: Nonnegative and Adaptive Multi-view Clustering (PZ, FL, LZ), pp. 1247–1252.
ICPR-2018-LabaoN #approximate #policy: Stabilizing Actor Policies by Approximating Advantage Distributions from K Critics (ABL, PCN), pp. 1253–1258.
ICPR-2018-XiaoLLLK #algorithm #network: Single-image Dehazing Algorithm Based on Convolutional Neural Networks (JX, LL, EL, JL, RK), pp. 1259–1264.
ICPR-2018-PengLMSL #detection #image #learning #sequence #video: Driving Maneuver Detection via Sequence Learning from Vehicle Signals and Video Images (XP, RL, YLM, SS, YL), pp. 1265–1270.
ICPR-2018-GaoCZLL #3d #network: Background Subtraction via 3D Convolutional Neural Networks (YG, HC, XZ0, LL, ZL), pp. 1271–1276.
ICPR-2018-WangSH #algorithm #black box #generative #using: Universal Perturbation Generation for Black-box Attack Using Evolutionary Algorithms (SW, YS, YH), pp. 1277–1282.
ICPR-2018-XiaoDYLZW #adaptation #graph #probability: Probabilistic Graph Embedding for Unsupervised Domain Adaptation (PX, BD, SY, XL, YZ, JW0), pp. 1283–1288.
ICPR-2018-TongT #image #network #recognition: Reservoir Computing with Untrained Convolutional Neural Networks for Image Recognition (ZT, GT), pp. 1289–1294.
ICPR-2018-MaO0TL #classification: EMD-Based Entropy Features for micro-Doppler Mini-UAV Classification (XM, BSO, LS0, KAT, ZL), pp. 1295–1300.
ICPR-2018-WuLXFPL #network #predict: Context-Aware Attention LSTM Network for Flood Prediction (YW, ZL, WX, JF, SP, TL), pp. 1301–1306.
ICPR-2018-LiL18a #kernel #multi #online: An Online Kernel Selection Wrapper via Multi-Armed Bandit Model (JL, SL), pp. 1307–1312.
ICPR-2018-SharmaCJ #correlation #modelling: Variational Bayes Block Sparse Modeling with Correlated Entries (SS, SC, J), pp. 1313–1318.
ICPR-2018-ChenYY #classification #image #network: Semi-supervised convolutional neural networks with label propagation for image classification (LC, SY, MY0), pp. 1319–1324.
ICPR-2018-GuoD #3d #distance #estimation #matrix: Occluded Joints Recovery in 3D Human Pose Estimation based on Distance Matrix (XG, YD), pp. 1325–1330.
ICPR-2018-ZhuX #approximate #graph #learning #scalability: Scalable Semi-Supervised Learning by Graph Construction with Approximate Anchors Embedding (HZ, MX), pp. 1331–1336.
ICPR-2018-LiZCF #editing: Facial Attribute Editing by Latent Space Adversarial Variational Autoencoders (DL, MZ, WC, GF), pp. 1337–1342.
ICPR-2018-ParkAMLCP0PK #generative #named #network: MMGAN: Manifold-Matching Generative Adversarial Networks (NP, AA, JRAM, KL, JC, DKP, TC0, HP, YK), pp. 1343–1348.
ICPR-2018-YiXWF #adaptation #multi #recognition: Multi-source Domain Adaptation for Face Recognition (HY, ZX, YW, ZF), pp. 1349–1354.
ICPR-2018-FabbriBLVCC: Domain Translation with Conditional GANs: from Depth to RGB Face-to-Face (MF, GB, FL, RV, SC, RC), pp. 1355–1360.
ICPR-2018-ZhaoSJ #integer #linear #locality #programming #using: Temporal Pattern Localization using Mixed Integer Linear Programming (RZ, GS, QJ), pp. 1361–1365.
ICPR-2018-CuradoELH #named #ranking: net4Lap: Neural Laplacian Regularization for Ranking and Re-Ranking (MC, FE, MAL, ERH), pp. 1366–1371.
ICPR-2018-SunLL #multi: Part-based Multi-stream Model for Vehicle Searching (YS, ML, JL), pp. 1372–1377.
ICPR-2018-Aldana-LopezCZG #approach #learning #network: Dynamic Learning Rate for Neural Networks: A Fixed-Time Stability Approach (RAL, LECM, JZ, DGG, AC), pp. 1378–1383.
ICPR-2018-LiciottiPPFZ #network #segmentation #semantics #using: Convolutional Networks for Semantic Heads Segmentation using Top-View Depth Data in Crowded Environment (DL, MP, RP, EF, PZ), pp. 1384–1389.
ICPR-2018-BiciciKA #network: Conditional Information Gain Networks (UCB, CK, LA), pp. 1390–1395.
ICPR-2018-JiaSZ: Face Aging with Improved Invertible Conditional GANs (LJ, YS, YZ0), pp. 1396–1401.
ICPR-2018-DehzangiS #analysis #process #recognition #reduction #robust #using: IMU-Based Robust Human Activity Recognition using Feature Analysis, Extraction, and Reduction (OD, VS), pp. 1402–1407.
ICPR-2018-WitmerB #classification #image #learning #multi #using: Multi-label Classification of Stem Cell Microscopy Images Using Deep Learning (AW, BB), pp. 1408–1413.
ICPR-2018-QiuLL #clustering #named #nearest neighbour: D-NND: A Hierarchical Density Clustering Method via Nearest Neighbor Descent (TQ, CL, YL), pp. 1414–1419.
ICPR-2018-JiLLX #estimation #image: Deep Age Estimation Model Stabilization from Images to Videos (ZJ, CL, KL, JX), pp. 1420–1425.
ICPR-2018-ZhangCQZW #identification: Person Re-Identification with Weighted Spatial-Temporal Features (DZ, RC, ZQ, WZ, QW), pp. 1426–1431.
ICPR-2018-EleziTVP #learning #network: Transductive Label Augmentation for Improved Deep Network Learning (IE, AT, SV, MP), pp. 1432–1437.
ICPR-2018-LuoY #architecture #network #performance #segmentation: Fast Skin Lesion Segmentation via Fully Convolutional Network with Residual Architecture and CRF (WL, MY), pp. 1438–1443.
ICPR-2018-Chen18a #analysis #feature model #robust: Improved Robust Discriminant Analysis for Feature Extraction (XC), pp. 1444–1449.
ICPR-2018-Chen18b #approach #self: An Improved Self-Representation Approach for Missing Value Imputation (XC), pp. 1450–1455.
ICPR-2018-0001ZZWL #analysis: Convolutional Discriminant Analysis (GZ0, YZ, XYZ, HW, XL), pp. 1456–1461.
ICPR-2018-ZhongYZ #network: Merging Neurons for Structure Compression of Deep Networks (GZ0, HY, HZ0), pp. 1462–1467.
ICPR-2018-KouwL: Effects of sampling skewness of the importance-weighted risk estimator on model selection (WMK, ML), pp. 1468–1473.
ICPR-2018-CombinidoMA #approach #image #network #using: A Convolutional Neural Network Approach for Estimating Tropical Cyclone Intensity Using Satellite-based Infrared Images (JSC, JRM, JA), pp. 1474–1480.
ICPR-2018-DehzangiT #detection #network #representation #using: Driver Distraction Detection using MEL Cepstrum Representation of Galvanic Skin Responses and Convolutional Neural Networks (OD, MT), pp. 1481–1486.
ICPR-2018-HouCLWX #network #predict: Predicting Traffic Flow via Ensemble Deep Convolutional Neural Networks with Spatio-temporal Joint Relations (JH, JC, SL, JW, QX), pp. 1487–1492.
ICPR-2018-LiuLKDYZYJY #classification #collaboration #framework #optimisation #representation: A joint optimization framework of low-dimensional projection and collaborative representation for discriminative classification (XL0, ZL, LK, ZD, JY, YZ, CY0, PJ, JY), pp. 1493–1498.
ICPR-2018-RosenfeldU #classification #concept: Action Classification via Concepts and Attributes (AR, SU), pp. 1499–1505.
ICPR-2018-ZhuangTYMZJX #image #learning #named #representation #segmentation #semantics: RelationNet: Learning Deep-Aligned Representation for Semantic Image Segmentation (YZ, LT, FY, CM, ZZ, HJ, XX), pp. 1506–1511.
ICPR-2018-0011XWS #image #re-engineering: Color Image Reconstruction with Perceptual Compressive Sensing (JD0, XX, CW, GS), pp. 1512–1517.
ICPR-2018-HeKWZQGTH: Local Compact Binary Patterns for Background Subtraction in Complex Scenes (WH, YK, JW, GZ, QQ, LG, BT, FH), pp. 1518–1523.
ICPR-2018-WuYWWX #detection #recognition: Facial Expression Recognition for Different Pose Faces Based on Special Landmark Detection (WW, YY, YW, XW, DX), pp. 1524–1529.
ICPR-2018-BoudraYB #identification #metaprogramming #statistics: Plant identification from bark: A texture description based on Statistical Macro Binary Pattern (SB, IY, AB), pp. 1530–1535.
ICPR-2018-Miyamoto: Passenger in vehicle counting method of HOV/HOT system (SM), pp. 1536–1541.
ICPR-2018-GaoSXL #classification #image #kernel #linear #set: Kernel Dual Linear Regression for Face Image Set Classification (XG, QS, HX, YL), pp. 1542–1547.
ICPR-2018-YangCZ #flexibility #invariant #orthogonal: Flexible Rotation Invariant Bases from Orthogonal Moments (BY, XC, YZ), pp. 1548–1553.
ICPR-2018-WangLLL #detection #multi #network: Anchor Free Network for Multi-Scale Face Detection (CW, ZL, SL, SL), pp. 1554–1559.
ICPR-2018-MaGLLZ #3d #multi #named #network #segmentation #semantics: 3DMAX-Net: A Multi-Scale Spatial Contextual Network for 3D Point Cloud Semantic Segmentation (YM, YG, YL, ML, JZ), pp. 1560–1566.
ICPR-2018-XuTY #network #recognition: Beyond Two-stream: Skeleton-based Three-stream Networks for Action Recognition in Videos (JX, KT, HY), pp. 1567–1573.
ICPR-2018-JinZWJ #behaviour #clustering #detection #representation: Sparse Representation and Weighted Clustering Based Abnormal Behavior Detection (DJ, SZ, SW, XYJ), pp. 1574–1579.
ICPR-2018-SunZWJ #behaviour #detection #learning: Weak Supervised Learning Based Abnormal Behavior Detection (XS, SZ, SW, XYJ), pp. 1580–1585.
ICPR-2018-LiXY: A New Method for Face Alignment under Extreme Poses and Occlusion (JL, QX, RY), pp. 1586–1591.
ICPR-2018-DhakaIS #behaviour #linear #modelling: Latent Linear Dynamics for Modeling Pedestrian Behaviors (DD, MI, AS), pp. 1592–1597.
ICPR-2018-LiangLJXL #benchmark #dataset #metric #multi #named #predict: SCUT-FBP5500: A Diverse Benchmark Dataset for Multi-Paradigm Facial Beauty Prediction (LL, LL, LJ, DX, ML), pp. 1598–1603.
ICPR-2018-LiH #algorithm #estimation #performance #robust #using: Fast and Robust Pose Estimation Algorithm for Bin Picking Using Point Pair Feature (ML, KH), pp. 1604–1609.
ICPR-2018-Shen0Z #3d #hybrid: Hybrid 3D Surface Description with Global Frames and Local Signatures of Histograms (ZS, XM0, XZ), pp. 1610–1615.
ICPR-2018-MahboubiBC #approach #identification #problem: A structural approach to Person Re-identification problem (AM, LB, DC), pp. 1616–1621.
ICPR-2018-MuhammadWCA #architecture #classification #image: Pre-trained VGGNet Architecture for Remote-Sensing Image Scene Classification (UM, WW, SPC, SA), pp. 1622–1627.
ICPR-2018-LiuHLG: Long-term Object Tracking with Instance Specific Proposals (HL, QH, BL, YG), pp. 1628–1633.
ICPR-2018-DuSZ #contest #identification #multi #network: Which Part is Better: Multi-Part Competition Network for person Re-Identification (PD, YS, YZ0), pp. 1634–1639.
ICPR-2018-WeiCYLL #black box #classification #image #using: Explain Black-box Image Classifications Using Superpixel-based Interpretation (YW, MCC, YY, SNL, SL), pp. 1640–1645.
ICPR-2018-QieG00W #correlation #mining: Improved Correlation Filter Tracking with Hard Negative Mining (CQ, GG, YY0, LZ0, HW), pp. 1646–1651.
ICPR-2018-LiWK #correlation: A Rigorous Solution for Closed-form Correlation Filter Tracking (DL, GW, YK), pp. 1652–1657.
ICPR-2018-HeQZJ #3d #incremental: Incremental 3D Line Segment Extraction from Semi-dense SLAM (SH, XQ, ZZ, MJ), pp. 1658–1663.
ICPR-2018-ZhangJ0QLY #consistency #robust: Robust Locality-Constrained Label Consistent K-SVD by Joint Sparse Embedding (ZZ0, WJ, SL0, JQ, GL, SY), pp. 1664–1669.
ICPR-2018-MaH #generative #network #using: Perceptual Face Completion using a Local-Global Generative Adversarial Network (RM, HH0), pp. 1670–1675.
ICPR-2018-WuZZKZC #identification #visual notation: Joint Identification-Verification Model for Visual Tracking (MW, YZ, YZ, TK, LZ, BC), pp. 1676–1682.
ICPR-2018-HuangXG #identification #incremental #kernel #null: Incremental Kernel Null Foley-Sammon Transform for Person Re-identification (XH, JX, GG), pp. 1683–1688.
ICPR-2018-FuGA #detection #learning #scalability: Simultaneous Context Feature Learning and Hashing for Large Scale Loop Closure Detection (ZF, YG, WA), pp. 1689–1694.
ICPR-2018-ZhangMWZ0 #classification #scalability #semantics #video: From Text to Video: Exploiting Mid-Level Semantics for Large-Scale Video Classification (JZ0, KM, XW0, YZ0, JF0), pp. 1695–1700.
ICPR-2018-KataokaOIS #detection #image: Occlusion Handling Human Detection with Refocused Images (HK, SO, KI, YS), pp. 1701–1706.
ICPR-2018-WuSZZSLPB #classification #fourier #image: Fourier Transform based Features for Clean and Polluted Water Image Classification (XW, PS, LZ, HZ, JS, TL, UP0, MB), pp. 1707–1712.
ICPR-2018-MengYXHHY #performance #recognition #robust: A robust and efficient method for license plate recognition (AM, WY0, ZX, HH, LH, CY), pp. 1713–1718.
ICPR-2018-Du0CHW #adaptation #network #visual notation: Object-Adaptive LSTM Network for Visual Tracking (YD, YY0, SC, YH, HW), pp. 1719–1724.
ICPR-2018-FuWZ #detection #image: Context-Aware and Depthwise-based Detection on Orbit for Remote Sensing Image (YF, FW, JZ), pp. 1725–1730.
ICPR-2018-KawanishiMXTY #estimation #using: Which Content in a Booklet is he/she Reading? Reading Content Estimation using an Indoor Surveillance Camera (YK, HM, JX, KT, HY), pp. 1731–1736.
ICPR-2018-MaL #clustering #hybrid #visual notation: Hybrid Sparse Subspace Clustering for Visual Tracking (LM, ZL), pp. 1737–1742.
ICPR-2018-ZhouKHSL #detection: A Co-occurrence Background Model with Hypothesis on Degradation Modification for Object Detection in Strong Background Changes (WZ, SK, MH, YS, DL), pp. 1743–1748.
ICPR-2018-Liu0H #integration #using: High-Quality and Memory-Efficient Volumetric Integration of Depth Maps Using Plane Priors (YL, WG0, ZH), pp. 1749–1754.
ICPR-2018-MaL18a #visual notation: Appearance Variation Insensitive State Regression for Visual Tracking (LM, ZL), pp. 1755–1760.
ICPR-2018-LiuH0 #online #optimisation #using: Online Temporal Calibration of Camera and IMU using Nonlinear Optimization (JL, ZH, WG0), pp. 1761–1766.
ICPR-2018-LiW #estimation #image #network: Local Regression Based Hourglass Network for Hand Pose Estimation from a Single Depth Image (JL, ZW), pp. 1767–1772.
ICPR-2018-SogiF #modelling #recognition #set: Action Recognition Method Based on Sets of Time Warped ARMA Models (NS, KF), pp. 1773–1778.
ICPR-2018-SuJ #analysis #image #multi #using: Multi-Spectral Fusion and Denoising of RGB and NIR Images Using Multi-Scale Wavelet Analysis (HS, CJ), pp. 1779–1784.
ICPR-2018-XinCCZYW #locality #recognition #using #visual notation: Visual Localization in Changing Environments using Place Recognition Techniques (ZX, YC, SC, JZ0, YY, YW), pp. 1785–1790.
ICPR-2018-XinCZYW #probability #recognition #sequence #visual notation: Probabilistic Voting for Sequence Based Visual Place Recognition (ZX, YC, JZ0, YY, YW), pp. 1791–1796.
ICPR-2018-QianWWL #graph: Convolutional Features-Based CRF Graph Matching for Tracking of Densely Packed Cells (WQ, YW, XW, ML0), pp. 1797–1802.
ICPR-2018-WangGZXH #correlation #named #network #visual notation: SPCNet: Scale Position Correlation Network for End-to-End Visual Tracking (QW, JG, MZ, JX, WH), pp. 1803–1808.
ICPR-2018-ZhouXZH #graph #higher-order #multi #online: Online Multi-Target Tracking with Tensor-Based High-Order Graph Matching (ZZ, JX, MZ, WH), pp. 1809–1814.
ICPR-2018-YaoDHB #detection: Dense Receptive Field for Object Detection (YY, YD, ZH, HB), pp. 1815–1820.
ICPR-2018-ZhouWD #learning #online #realtime #robust: Online Learning of Spatial-Temporal Convolution Response for Robust Real-Time Tracking (JZ, RW, JD), pp. 1821–1826.
ICPR-2018-XuHDI: Partial Descriptor Update and Isolated Point Avoidance Based Template Update for High Frame Rate and Ultra-Low Delay Deformation Matching (YX, TH, SD, TI), pp. 1827–1832.
ICPR-2018-XuD #detection #modelling #using: Human Routine Change Detection using Bayesian Modelling (YX, DD), pp. 1833–1838.
ICPR-2018-ZhangHLZ #detection #network: Attention-based Neural Network for Traffic Sign Detection (JZ, LH, JL, YZ), pp. 1839–1844.
ICPR-2018-ChangGJ #segmentation #semantics: Depth-assisted RefineNet for Indoor Semantic Segmentation (MC, FG0, RJ), pp. 1845–1850.
ICPR-2018-RenZLLWY #learning #rank #representation #robust #taxonomy: Robust Projective Low-Rank and Sparse Representation by Robust Dictionary Learning (JR, ZZ0, SL0, GL, MW0, SY), pp. 1851–1856.
ICPR-2018-ZhongJ0JX #fine-grained #image #multi #network #recognition: A Multi-part Convolutional Attention Network for Fine-Grained Image Recognition (WZ, LJ, TZ0, JJ, HX), pp. 1857–1862.
ICPR-2018-ChenDHLH #automation #classification #clustering #image #performance: Improving Image Classification Performance with Automatically Hierarchical Label Clustering (ZC, CD, LH, DL, HH), pp. 1863–1868.
ICPR-2018-GuoDGB #detection #multi #named: MSFD: Multi-Scale Receptive Field Face Detector (QG, YD, YG, HB), pp. 1869–1874.
ICPR-2018-FasogbonF: Generic calibration of cameras with non-parallel optical elements (PF, LF), pp. 1875–1881.
ICPR-2018-WuLPL #embedded #named #performance #robust: Em-SLAM: a Fast and Robust Monocular SLAM Method for Embedded Systems (YW, ZL, SP, TL), pp. 1882–1887.
ICPR-2018-XuWK #correlation #learning #representation: Non-negative Subspace Representation Learning Scheme for Correlation Filter Based Tracking (TX, XJW, JK), pp. 1888–1893.
ICPR-2018-ZhangYLQZC #detection #network: Single Shot Feature Aggregation Network for Underwater Object Detection (LZ, XY0, ZL, LQ, HZ, CC), pp. 1906–1911.
ICPR-2018-XuWJW #network #visual notation: Visual Tracking by Combining the Structure-Aware Network and Spatial-Temporal Regression (DX, LW, MJ, QW), pp. 1912–1917.
ICPR-2018-LiCY #classification #feature model #generative #image: Generative Band Feature Enhancement for Hyperspectral Image Classification (JL, FC, DY), pp. 1918–1923.
ICPR-2018-DingLZ #detection #framework: A Selective Tracking and Detection Framework with Target Enhanced Feature (XD, LL, XZ), pp. 1924–1928.
ICPR-2018-CuiS0 #incremental: Voting-based Incremental Structure-from-Motion (HC, SS, WG0), pp. 1929–1934.
ICPR-2018-KangLS #classification #image: Object Classification of Remote Sensing Images Based on Partial Randomness Supervised Discrete Hashing (TK, YL, QSS), pp. 1935–1940.
ICPR-2018-BartoliLBB #predict: Context-Aware Trajectory Prediction (FB, GL, LB, ADB), pp. 1941–1946.
ICPR-2018-TranLPHKTNP #analysis #dataset #multi: A multi-modal multi-view dataset for human fall analysis and preliminary investigation on modality (THT, TLL, DTP, VNH, VMK, QTT, TSN, CP), pp. 1947–1952.
ICPR-2018-WuZLW #image #multi #novel: A Novel Model for Multi-label Image Annotation (XW, LZ0, FL, BW), pp. 1953–1958.
ICPR-2018-VaqueroSM: Hallucinating Dense Optical Flow from Sparse Lidar for Autonomous Vehicles (VV, AS, FMN), pp. 1959–1964.
ICPR-2018-CaoGWXW #detection #learning: Gaze-Aided Eye Detection via Appearance Learning (LC, CG, KW, GX, FYW0), pp. 1965–1970.
ICPR-2018-ShevchenkoEK #detection: Fish Detection from Low Visibility Underwater Videos (VS, TE, AK), pp. 1971–1976.
ICPR-2018-YlimakiHK #3d #re-engineering #refinement #using: Accurate 3-D Reconstruction with RGB-D Cameras using Depth Map Fusion and Pose Refinement (MY, JH, JK), pp. 1977–1982.
ICPR-2018-AzzopardiFGSV #gender #image #recognition #using: Gender recognition from face images using trainable shape and color features (GA, PF, AG, AS, MV), pp. 1983–1988.
ICPR-2018-MaheMC #segmentation #semantics #visual notation: Semantic-only Visual Odometry based on dense class-level segmentation (HM, DM, AIC), pp. 1989–1995.
ICPR-2018-XuZL #feature model #multi #named #recognition: MSSVT: Multi-scale feature extraction for single face recognition (XX, LZ, FL), pp. 1996–2001.
ICPR-2018-DongTC #automation #image #using: Automatic Inspection of Aerospace Welds Using X-Ray Images (XD, CJT, TFC), pp. 2002–2007.
ICPR-2018-RotgerLMA #2d #3d: 2D-to-3D Facial Expression Transfer (GR, FL, FMN, AA), pp. 2008–2013.
ICPR-2018-MaBXC0: Segmentation-Guided Tracking with Prior Map Decision (DM, WB, YX, YC, XW0), pp. 2014–2019.
ICPR-2018-LiLWL #correlation #image #performance: Fast Single Image Dehazing via Positive Correlation (BL, YL, CW, YL0), pp. 2020–2025.
ICPR-2018-WangWLW0 #detection #identification: Temporal Action Detection by Joint Identification-Verification (WW, YW, HL, SW, JC0), pp. 2026–2031.
ICPR-2018-LiPZ #identification: Vehicle Re-Identification by Deep Feature Fusion Based on Joint Bayesian Criterion (SL, MP, LZ), pp. 2032–2037.
ICPR-2018-ZhengLFLZ #feature model #robust: Robust Attentional Pooling via Feature Selection (JZ, TYL, CF0, XL, ZZ), pp. 2038–2043.
ICPR-2018-HuiLCHY #image #multi: Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders (LH, XL0, JC, HH, JY0), pp. 2044–2049.
ICPR-2018-YangQLZZLWS #detection #estimation: A Light CNN based Method for Hand Detection and Orientation Estimation (LY, ZQ, ZL, SZ, YZ, HL0, JW, LS), pp. 2050–2055.
ICPR-2018-JiangLSWZW #identification #learning #similarity: Orientation-Guided Similarity Learning for Person Re-identification (NJ, JL, CS, YW, ZZ, WW), pp. 2056–2061.
ICPR-2018-HanXW #generative #learning #multi #network #representation: Learning Multi-view Generator Network for Shared Representation (TH0, XX, YNW), pp. 2062–2068.
ICPR-2018-Zhuang0CW #classification #learning #multi: Multi-task Learning of Cascaded CNN for Facial Attribute Classification (NZ, YY0, SC, HW), pp. 2069–2074.
ICPR-2018-PeiFR #learning #multi: Learning with Latent Label Hierarchy from Incomplete Multi-Label Data (YP, XZF, RR), pp. 2075–2080.
ICPR-2018-LyuYCZZ #classification #detection #learning: Learning Fixation Point Strategy for Object Detection and Classification (JL0, ZY, DC, YZ, HZ), pp. 2081–2086.
ICPR-2018-JaberiPF #clustering #probability #using: Probabilistic Sparse Subspace Clustering Using Delayed Association (MJ, MP, HF), pp. 2087–2092.
ICPR-2018-LiZ0 #clustering: Constrained Sparse Subspace Clustering with Side-Information (CGL, JZ, JG0), pp. 2093–2099.
ICPR-2018-WangT #clustering #estimation: Stream Clustering with Dynamic Estimation of Emerging Local Densities (ZW, GT), pp. 2100–2105.
ICPR-2018-LiMCC #benchmark #metric: A Benchmark for Full Rotation Head Tracking (YL, BM, HC, XC), pp. 2106–2111.
ICPR-2018-KartKMFC #correlation: Depth Masked Discriminative Correlation Filter (UK, JKK, JM, LF, FC), pp. 2112–2117.
ICPR-2018-0002ZT0 #named #visual notation: OWP: Objectness Weighted Patch Descriptor for Visual Tracking (BJ0, YZ, JT, BL0), pp. 2118–2123.
ICPR-2018-MaB0 #multi: Dual-SVM tracker via Multiple Support Instance and LEVER Strategy (DM, WB, XW0), pp. 2124–2129.
ICPR-2018-HosniDCA #3d #functional #recognition: 3D Gait Recognition based on Functional PCA on Kendall's Shape Space (NH, HD, FC, BBA), pp. 2130–2135.
ICPR-2018-YanKM #identification: Person Re-Identification with Vision and Language (FY0, JK, KM), pp. 2136–2141.
ICPR-2018-YuanWZ #image #question: Does A Body Image Tell Age? (BY, AW, WSZ), pp. 2142–2147.
ICPR-2018-XuSLW #retrieval: Attend and Align: Improving Deep Representations with Feature Alignment Layer for Person Retrieval (QX, YS, YL0, SW), pp. 2148–2153.
ICPR-2018-HailatK0 #learning: Deep Semi-Supervised Learning (ZH, AK, XwC0), pp. 2154–2159.
ICPR-2018-ZhangZLYZW #adaptation #composition #matrix #robust: Robust Adaptive Label Propagation by Double Matrix Decomposition (HZ, ZZ0, SL0, QY, MZ, MW0), pp. 2160–2165.
ICPR-2018-ZhongZ #performance #segmentation #semantics: Efficient Object Region Discovery for Weakly-supervised Semantic Segmentation (MZ, GZ), pp. 2166–2171.
ICPR-2018-CuradoELH18a #graph #principle: Semi-supervised Graph Rewiring with the Dirichlet Principle (MC, FE, MAL, ERH), pp. 2172–2177.
ICPR-2018-XuZH #detection: Densely Connected Single-Shot Detector (PX, XZ, KH), pp. 2178–2183.
ICPR-2018-ChenHZLQ #analysis #detection #multi #video: Video Salient Object Detection via Multiple Time-scale Analysis (YC, LH, WZ, XL, GQ), pp. 2184–2189.
ICPR-2018-YangQKCF #detection: Object Detection in Equirectangular Panorama (WY, YQ, JKK, FC, LF), pp. 2190–2195.
ICPR-2018-XieW #detection #multi #segmentation #semantics: Multi-scale Semantic Segmentation Enriched Features for Pedestrian Detection (XX, ZW), pp. 2196–2201.
ICPR-2018-ZhangLS #3d #coordination #locality: Joint Voxel and Coordinate Regression for Accurate 3D Facial Landmark Localization (HZ, QL0, ZS), pp. 2202–2208.
ICPR-2018-LiZSC #recognition: Patch-Gated CNN for Occlusion-aware Facial Expression Recognition (YL0, JZ, SS, XC), pp. 2209–2214.
ICPR-2018-GuptaB0V #image: Scattering Transform for Matching Surgically Altered Face Images (IG, IB, RS0, MV), pp. 2215–2220.
ICPR-2018-Sun0L #detection #image #multimodal: Multimodal Face Spoofing Detection via RGB-D Images (XS0, LH0, CL), pp. 2221–2226.
ICPR-2018-FengHYL #detection #segmentation: Scene Text Detection with Recurrent Instance Segmentation (WF, WH, FY, CLL), pp. 2227–2232.
ICPR-2018-SuiZYC #detection #framework #learning #novel #recognition: A Novel Integrated Framework for Learning both Text Detection and Recognition (WS, QZ, JY, WC), pp. 2233–2238.
ICPR-2018-RibaFLF #graph #learning #message passing #network: Learning Graph Distances with Message Passing Neural Networks (PR, AF0, JL0, AF), pp. 2239–2244.
ICPR-2018-ZhangDD #multi #recognition: Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition (JZ, JD, LD), pp. 2245–2250.
ICPR-2018-NieLQZJ #algorithm #classification #incremental #learning #multi: An Incremental Multi-view Active Learning Algorithm for PolSAR Data Classification (XN, YL, HQ, BZ0, ZPJ), pp. 2251–2255.
ICPR-2018-XuZL18a #incremental #kernel #learning #linear #online: A Linear Incremental Nyström Method for Online Kernel Learning (SX, XZ, SL), pp. 2256–2261.
ICPR-2018-LiuMHWLB #network: Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting (XL, MM, LH, JvdW, AML0, ADB), pp. 2262–2268.
ICPR-2018-PangDWH #learning: Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advice (KP, MD, YW, TMH), pp. 2269–2276.
ICPR-2018-SperaFBF #locality: Egocentric Shopping Cart Localization (ES, AF, SB, GMF), pp. 2277–2282.
ICPR-2018-ZhangZZ #scalability: Scalable Monocular SLAM by Fusing and Connecting Line Segments with Inverse Depth Filter (JZ, GZ, HZ), pp. 2283–2288.
ICPR-2018-YangZYCL #multi #self #visual notation: End-to-end Multi-Modal Multi-Task Vehicle Control for Self-Driving Cars with Visual Perceptions (ZY, YZ, JY, JC, JL), pp. 2289–2294.
ICPR-2018-LiTZLH: Spatial Calibration for Thermal-RGB Cameras and Inertial Sensor System (YL, JT, YZ, WL, HH), pp. 2295–2300.
ICPR-2018-AbdeldayemB #automation #detection #using: Automatically Detecting Arrhythmia-related Irregular Patterns using the Temporal and Spectro-Temporal Textures of ECG Signals (SSA, TB), pp. 2301–2307.
ICPR-2018-NguyenMT #pattern matching #pattern recognition #recognition: Impact of lossy data compression techniques on EEG-based pattern recognition systems (BN, WM, DT), pp. 2308–2313.
ICPR-2018-ZhangCSZWHJL #assessment #named #network #performance #quality: SlideNet: Fast and Accurate Slide Quality Assessment Based on Deep Neural Networks (TZ, JC, DFS, KZ, AW, PH, AJ, BCL), pp. 2314–2319.
ICPR-2018-MartinezPSLBP #functional #kernel #multi #personalisation #recognition: Multi-task multiple kernel machines for personalized pain recognition from functional near-infrared spectroscopy brain signals (DLM, KP, SCS, AJL, DB, RWP), pp. 2320–2325.
ICPR-2018-SchwarczP #2d #3d #estimation #multi: 3D Human Pose Estimation from Deep Multi-View 2D Pose (SS, TP), pp. 2326–2331.
ICPR-2018-WangYHYP #classification #image: Enhancing Pix2Pix for Remote Sensing Image Classification (XW, HY, CH, JY, CP), pp. 2332–2336.
ICPR-2018-WangXZ #detection #encoding: Global Context Encoding for Salient Objects Detection (JW, YX, GZ), pp. 2337–2342.
ICPR-2018-ZhongDL #3d #geometry #semantics: 3D Geometry-Aware Semantic Labeling of Outdoor Street Scenes (YZ, YD, HL), pp. 2343–2349.
ICPR-2018-AkdemirBS #locality #realtime #using: Real-time Vehicle Localization and Tracking Using Monocular Panomorph Panoramic Vision (BA, ANB, LMS), pp. 2350–2355.
ICPR-2018-ElmogyZEE #3d #automation #classification #framework #network: An Automated Classification Framework for Pressure Ulcer Tissues Based on 3D Convolutional Neural Network (ME, BGZ, ASE, AEB), pp. 2356–2361.
ICPR-2018-ZhouL0LL #estimation #learning: Scale and Orientation Aware EPI-Patch Learning for Light Field Depth Estimation (WZ, LL, HZ, AL, LL), pp. 2362–2367.
ICPR-2018-LeiZZXCS #algorithm #image: An Image Rain Removal algorithm based on the depth of field and sparse coding (JL, SZ, WZ, JX, YC, HS), pp. 2368–2373.
ICPR-2018-GaoMSLWX #scalability: Large Margin Structured Convolution Operator for Thermal Infrared Object Tracking (PG0, YM, KS, CL, FW0, LX), pp. 2380–2385.
ICPR-2018-YinLLCS #detection #multi #realtime: Cross Modal Multiscale Fusion Net for Real-time RGB-D Detection (KY, SL0, RL, YC, KS), pp. 2386–2391.
ICPR-2018-GuptaJAMM #detection #video: Pentuplet Loss for Simultaneous Shots and Critical Points Detection in a Video (NG, AJ, PA, SM, SM), pp. 2392–2397.
ICPR-2018-HeKMP #predict: Aggregated Sparse Attention for Steering Angle Prediction (SH, DK, YM, NP), pp. 2398–2403.
ICPR-2018-ZhangDW #multi #realtime #visual notation: Multi-layer CNN Features Aggregation for Real-time Visual Tracking (LZ, YD, YW), pp. 2404–2409.
ICPR-2018-JinZJD #locality #semantics #visual notation: Localization Based on Semantic Map and Visual Inertial Odometry (JJ, XZ, YJ, ZD), pp. 2410–2415.
ICPR-2018-WangWL #education #learning #performance: Weakly- and Semi-supervised Faster R-CNN with Curriculum Learning (JW, XW, WL0), pp. 2416–2421.
ICPR-2018-JiuSQ #image #network: Deep Context Networks for Image Annotation (MJ, HS, LQ), pp. 2422–2427.
ICPR-2018-XuGSL #multi: Non-iterative multiple data registration method based on the motion screw theory and trackable features (PX, FG, ZS, JL), pp. 2428–2432.
ICPR-2018-SadafiKHPMS #multi #using: Multiple Mice Tracking: Occlusions Disentanglement using a Gaussian Mixture Model (AS, VMK, HH, FP, VM, DS), pp. 2433–2437.
ICPR-2018-ShiLLLM #network #recognition: Weather Recognition Based on Edge Deterioration and Convolutional Neural Networks (YS, YL, JL, XL, YLM), pp. 2438–2443.
ICPR-2018-LiuDWZWZ #classification #education #image #learning: Teaching Squeeze-and-Excitation PyramidNet for Imbalanced Image Classification with GAN-based Curriculum Learning (JL, AD, CW0, HZ, NW0, BZ), pp. 2444–2449.
ICPR-2018-PistellatoCBGA #adaptation: Adaptive Albedo Compensation for Accurate Phase-Shift Coding (MP, LC, FB, AG, AA), pp. 2450–2455.
ICPR-2018-OuyangZMA #generative #image #sequence: Generating Image Sequence from Description with LSTM Conditional GAN (XO, XZ, DM, GA), pp. 2456–2461.
ICPR-2018-PistellatoBCGRA #fault: Neighborhood-Based Recovery of Phase Unwrapping Faults (MP, FB, LC, AG, DR, AA), pp. 2462–2467.
ICPR-2018-MandalSVM #named #policy #robust: CANDID: Robust Change Dynamics and Deterministic Update Policy for Dynamic Background Subtraction (MM, PS, SKV, SM), pp. 2468–2473.
ICPR-2018-JyotiD #automation #estimation #geometry #network #using: Automatic Eye Gaze Estimation using Geometric & Texture-based Networks (SJ, AD), pp. 2474–2479.
ICPR-2018-CortesCC #encoding #recognition #visual notation #word: A new bag of visual words encoding method for human action recognition (XC, DC, HC), pp. 2480–2485.
ICPR-2018-WangXLTXX #detection #multi #network: Multi-scale Fusion with Context-aware Network for Object Detection (HW, JX, LL, YT, DX, SX), pp. 2486–2491.
ICPR-2018-GuanZT #segmentation #semantics #top-down: Inception Donut Convolution for Top-down Semantic Segmentation (HG, ZZ, TT), pp. 2492–2497.
ICPR-2018-ShaoSGL #image #representation: Joint Image Restoration and Matching Based on Distance-Weighted Sparse Representation (YS, NS, CG, WL), pp. 2498–2503.
ICPR-2018-0004YW #kernel #named: Spindle-Net: CNNs for Monocular Depth Inference with Dilation Kernel Method (LH0, MY, GW), pp. 2504–2509.
ICPR-2018-MaWWW #detection #multi #named #network #performance: MDCN: Multi-Scale, Deep Inception Convolutional Neural Networks for Efficient Object Detection (WM, YW, ZW, GW), pp. 2510–2515.
ICPR-2018-HaraKS #3d #recognition #towards: Towards Good Practice for Action Recognition with Spatiotemporal 3D Convolutions (KH, HK, YS), pp. 2516–2521.
ICPR-2018-YanJY #3d #detection #generative #network: 3D Convolutional Generative Adversarial Networks for Detecting Temporal Irregularities in Videos (MY, XJ, JY), pp. 2522–2527.
ICPR-2018-PengSCCXJ #architecture #detection #multi #using: Detecting Heads using Feature Refine Net and Cascaded Multi-scale Architecture (DP, ZS, ZC, ZC, LX, LJ), pp. 2528–2533.
ICPR-2018-BaiZZLZW #recognition #segmentation: Continuous Action Recognition and Segmentation in Untrimmed Videos (RB, QZ, SZ, YL, XZ, JW), pp. 2534–2539.
ICPR-2018-LuoKW #generative #image #network #synthesis: Traffic Sign Image Synthesis with Generative Adversarial Networks (HL, QK, FW), pp. 2540–2545.
ICPR-2018-TheagarajanBC #automation #named: DeepDriver: Automated System For measuring Valence and Arousal in Car Driver Videos (RT, BB, ACC), pp. 2546–2551.
ICPR-2018-RoyBM #classification #visual notation: Discriminative Latent Visual Space For Zero-Shot Object Classification (AR, BB, VM), pp. 2552–2557.
ICPR-2018-MaXYL #generative #image: Face Image Illumination Processing Based on Generative Adversarial Nets (WM, XX, CY, JL), pp. 2558–2563.
ICPR-2018-ZhangGX #automation #detection #towards: Towards Automatic Detection of Monkey Faces (MZ, SG, XX), pp. 2564–2569.
ICPR-2018-KateFG #using #visual notation: Visual Tracking with Breeding Fireflies using Brightness from Background-Foreground Information (PK, MF, PG), pp. 2570–2575.
ICPR-2018-SongZR #bound #network: UAV Target Tracking with A Boundary-Decision Network (KS, WZ0, XR), pp. 2576–2581.
ICPR-2018-MaBCX0 #collaboration #learning #visual notation: Learning Collaborative Model for Visual Tracking (DM, WB, YC, YX, XW0), pp. 2582–2587.
ICPR-2018-MohantyDG #detection #performance #using: An Efficient System for Hazy Scene Text Detection using a Deep CNN and Patch-NMS (SM, TD, HPG), pp. 2588–2593.
ICPR-2018-RazinkovSM #algorithm #detection #named: ALFA: Agglomerative Late Fusion Algorithm for Object Detection (ER, IS, JM), pp. 2594–2599.
ICPR-2018-XueQLJ #rank: Low-Rank Tensor Completion by Truncated Nuclear Norm Regularization (SX, WQ, FL, XJ), pp. 2600–2605.
ICPR-2018-BandyopadhyayNM #axiom #network #social: A Generic Axiomatic Characterization for Measuring Influence in Social Networks (SB, RN, MNM), pp. 2606–2611.
ICPR-2018-OGorman #parametricity: Temporal Filter Parameters for Motion Pattern Maps (LO), pp. 2612–2617.
ICPR-2018-OGormanW #network #video: Balancing Video Analytics Processing and Bandwidth for Edge-Cloud Networks (LO, XW), pp. 2618–2623.
ICPR-2018-VinayavekhinCMA #comprehension #learning #using #what: Focusing on What is Relevant: Time-Series Learning and Understanding using Attention (PV, SC, AM, DJA, GDM, DK, RT), pp. 2624–2629.
ICPR-2018-YuHIU #image: Foreground Enlargement of Omnidirectional Images by Spherical Trigonometry (AsY, KH, KI, KU), pp. 2630–2635.
ICPR-2018-0005GHL #feature model #image #network #segmentation: Feature Extraction and Grain Segmentation of Sandstone Images Based on Convolutional Neural Networks (FJ0, QG, HH, NL), pp. 2636–2641.
ICPR-2018-SongXLG #classification #invariant: Completed Grayscale-Inversion and Rotation Invariant Local Binary Pattern for Texture Classification (TS, LX, LL, CG), pp. 2642–2647.
ICPR-2018-MukherjeeOP0 #identification: A Dravidian Language Identification System (HM, SMO, SP, KR0), pp. 2654–2657.
ICPR-2018-ZhangZZL #bound #detection #image #performance: Boundary-based Image Forgery Detection by Fast Shallow CNN (ZZ, YZ, ZZ, JL), pp. 2658–2663.
ICPR-2018-HanSZ #image #re-engineering: Residual HSRCNN: Residual Hyper-Spectral Reconstruction CNN from an RGB Image (XHH, BS, YZ), pp. 2664–2669.
ICPR-2018-HuiWG #image #network: Two-Stage Convolutional Network for Image Super-Resolution (ZH, XW, XG), pp. 2670–2675.
ICPR-2018-WuWDW: Ensemble Reversible Data Hiding (HW, WW0, JD0, HW0), pp. 2676–2681.
ICPR-2018-DengLLZL #composition #detection #rank: Low-Rank and Sparse Decomposition on Contrast Map for Small Infrared Target Detection (XD, WL0, LL, WZ, XL), pp. 2682–2687.
ICPR-2018-KasemHJ #image #network #towards: Revised Spatial Transformer Network towards Improved Image Super-resolutions (HMK, KWH, JJ), pp. 2688–2692.
ICPR-2018-ChengSZW0 #higher-order #image #retrieval: Deep High-order Supervised Hashing for Image Retrieval (JC, QS, JZ, XW, QZ0), pp. 2693–2698.
ICPR-2018-DingLXKS #generative #network #recognition #robust #speech #towards: Mutual-optimization Towards Generative Adversarial Networks For Robust Speech Recognition (KD, NL, YX, DK, KS), pp. 2699–2704.
ICPR-2018-LiWK18a #framework #image #learning #using: Infrared and Visible Image Fusion using a Deep Learning Framework (HL0, XJW, JK), pp. 2705–2710.
ICPR-2018-ZhangL #video: Non-uniform Illumination Video Enhancement Based on Zone System and Fusion (YZ, SL), pp. 2711–2716.
ICPR-2018-ZhuMT #graph #kernel #multi #retrieval: Multi-Kernel Supervised Hashing with Graph Regularization for Cross-Modal Retrieval (MZ, HM, JT), pp. 2717–2722.
ICPR-2018-FayerMGDC: Radiometric confidence criterion for patch-based inpainting (JF, GM, SG, MD, BC), pp. 2723–2728.
ICPR-2018-NguyenTL #data-driven #learning #using: Are French Really That Different? Recognizing Europeans from Faces Using Data-Driven Learning (VDN, MT, JL), pp. 2729–2734.
ICPR-2018-YamadaIYK #network #segmentation #using: Texture Segmentation using Siamese Network and Hierarchical Region Merging (RY, HI, NY, TK), pp. 2735–2740.
ICPR-2018-XuZZ #image #network #recognition #using: Screen-rendered text images recognition using a deep residual network based segmentation-free method (XX0, JZ, HZ), pp. 2741–2746.
ICPR-2018-GaoCMXL #probability #visual notation: Deep Pixel Probabilistic Model for Super Resolution Based on Human Visual Saliency Mechanism (HG, ZC, GM, WX, ZL), pp. 2747–2752.
ICPR-2018-ChenDCWL #generative: Joint Denoising and Super-Resolution via Generative Adversarial Training (LC, WD, LC, CW0, JL), pp. 2753–2758.
ICPR-2018-JiangWYSLGFZ #network #recursion: Recursive Inception Network for Super-Resolution (TJ, XW, ZY, WS, GL, SG, HF, QZ), pp. 2759–2764.
ICPR-2018-ShengCWL #detection #image #multi #ranking: Weakly Supervised Vehicle Detection in Satellite Images via Multiple Instance Ranking (YS, LC, CW0, JL), pp. 2765–2770.
ICPR-2018-ShibataIHM #image #set #using: Restoration of Sea Surface Temperature Satellite Images Using a Partially Occluded Training Set (SS, MI, AH, MM), pp. 2771–2776.
ICPR-2018-LiuWL0ZHL #approach #image: An Attention-Based Approach for Single Image Super Resolution (YL, YW, NL, XC0, YZ, YH, GL), pp. 2777–2784.
ICPR-2018-LiZXGX: Compression of Acoustic Model via Knowledge Distillation and Pruning (CL, LZ, SX, PG, BX0), pp. 2785–2790.
ICPR-2018-TagawaZ: Super-Resolution Ultrasound Imaging Based on the Phase of the Carrier Wave Without Deterioration by Grating Lobes (NT, JZ), pp. 2791–2796.
ICPR-2018-SimberovaS #data analysis: Solar Atmosphere Data Analysis (SS, TS), pp. 2797–2802.
ICPR-2018-WangCYX #network #self: Self-Attention Based Network for Punctuation Restoration (FW0, WC0, ZY0, BX0), pp. 2803–2808.
ICPR-2018-LiuL #collaboration #image #representation: Face Image Super-Resolution via K-NN Regularized Collaborative Representation with Importance Reweighting (LL, SL), pp. 2809–2814.
ICPR-2018-ZhangDKQL #detection #multi #network: Global Contrast Enhancement Detection via Deep Multi-Path Network (CZ, DD, LK, HQ, SL), pp. 2815–2820.
ICPR-2018-ShenYCFM #image: Deep joint rain and haze removal from a single image (LS, ZY, QC, FF, JM), pp. 2821–2826.
ICPR-2018-LuYY #classification #image: Getting Rid of Night: Thermal Image Classification Based on Feature Fusion (GL, HY, CY), pp. 2827–2832.
ICPR-2018-XuDMB #recognition #using: Video-based Emotion Recognition using Aggregated Features and Spatio-temporal Information (JX, YD, LM, HB), pp. 2833–2838.
ICPR-2018-YangYZT #challenge #named #self: Self-Talk: Responses to Users' Opinions and Challenges in Human Computer Dialog (MY, NSRY, KZ, JT), pp. 2839–2844.
ICPR-2018-LuYP #assessment #image: Deep Conditional Color Harmony Model for Image Aesthetic Assessment (PL, JY, XP), pp. 2845–2850.
ICPR-2018-LiaoCQ #image #using #visualisation: Visualization of Hyperspectral Images Using Moving Least Squares (DL, SC, YQ), pp. 2851–2856.
ICPR-2018-ZhangLWCZ #automation #framework #image #multimodal #set: An Automated Point Set Registration Framework for Multimodal Retinal Image (HZ, XL, GW, YC, WZ), pp. 2857–2862.
ICPR-2018-YangZWQ #analysis #classification #detection #image #quality #recognition: Quality Classified Image Analysis with Application to Face Detection and Recognition (FY, QZ0, MW, GQ), pp. 2863–2868.
ICPR-2018-ShiXZLG: Vessel Enhancement Based on Length-constrained Hessian Information (ZS, HX, JZ, JL, LG), pp. 2869–2874.
ICPR-2018-YangZT #using: Reducing Tongue Shape Dimensionality from Hundreds of Available Resources Using Autoencoder (MY, DZ, JT), pp. 2875–2880.
ICPR-2018-ShahinJA #approach #verification: One-Class SVMs Based Pronunciation Verification Approach (MAS, JXJ, BA), pp. 2881–2886.
ICPR-2018-SahuC #video: Shot Level Egocentric Video Co-summarization (AS, ASC), pp. 2887–2892.
ICPR-2018-ChengWLY #locality #people #visual notation: Visual Localization of Key Positions for Visually Impaired People (RC, KW, LL, KY), pp. 2893–2898.
ICPR-2018-ShiL #analysis #segmentation #video: A New Foreground Segmentation Method for Video Analysis in Different Color Spaces (HS, CL), pp. 2899–2904.
ICPR-2018-CuiLZLXGJZ #classification #network: Classification Guided Deep Convolutional Network for Compressed Sensing (WC, SL, SZ, YL0, HX, XG, FJ0, DZ), pp. 2905–2910.
ICPR-2018-DewanAS #recognition: Spatio-Temporal Laban Features for Dance Style Recognition (SD, SA0, NS), pp. 2911–2916.
ICPR-2018-Yang0CF #analysis #canonical #correlation #detection #image #using: Heterogeneous image change detection using Deep Canonical Correlation Analysis (JY, YZ0, YC, LF), pp. 2917–2922.
ICPR-2018-GuTG #image: Integrating Local and Non-local Denoiser Priors for Image Restoration (SG, RT, LVG), pp. 2923–2928.
ICPR-2018-Gong0LL #semantics #synthesis: Dynamic Facial Expression Synthesis Driven by Deformable Semantic Parts (NG, YY0, YL, DL), pp. 2929–2934.
ICPR-2018-ZhaoLJGW #documentation #image: Skip-Connected Deep Convolutional Autoencoder for Restoration of Document Images (GZ, JL, JJ, HG, JRW), pp. 2935–2940.
ICPR-2018-WangXS #music #random #semantics: Semantic Music Annotation by Label-Specific Conditional Random Fields (QW, YX, FS), pp. 2941–2946.
ICPR-2018-FasogbonF18a #automation #feature model: Automatic Feature Extraction for Wide-angle and Fish-eye Camera Calibration (PF, LF), pp. 2947–2952.
ICPR-2018-YangXDZ: Delving into the Synthesizability of Dynamic Texture Samples (FY, GSX, DD, LZ), pp. 2953–2958.
ICPR-2018-ZhouYCK #detection #image: Blurred Image Region Detection based on Stacked Auto-Encoder (YZ0, JY, YC, SYK), pp. 2959–2964.
ICPR-2018-YanXAK #3d #detection #fault #feature model: Accumulated Aggregation Shifting Based on Feature Enhancement for Defect Detection on 3D Textured Low-Contrast Surfaces (YY, SX, HA, SK), pp. 2965–2970.
ICPR-2018-WangYCHYZ #video: Unsupervised Video Highlight Extraction via Query-related Deep Transfer (HW, HY, PC, RH, CY, LZ), pp. 2971–2976.
ICPR-2018-0006HCK: Super-resolution Imaging Based on Global Interpolation and Structural Similarities (YZ0, SH, YC, SYK), pp. 2977–2982.
ICPR-2018-AnnadaniJ #adaptation #approach #detection #image: Augment and Adapt: A Simple Approach to Image Tampering Detection (YA, CVJ), pp. 2983–2988.
ICPR-2018-El-GamalEAGBHKE #framework #using: Significant Region-Based Framework for Early Diagnosis of Alzheimer's Disease Using 11C PiB-PET Scans (FEZAEG, MME, AA, MG, GNB, HH, RK, ASEB), pp. 2989–2994.
ICPR-2018-WuLCW #learning #multi #semantics: Learning a Hierarchical Latent Semantic Model for Multimedia Data (SHW, YSL, SHC, JCW), pp. 2995–3000.
ICPR-2018-ChenC: A New Dynamic Minimal Path Model for Tubular Structure Centerline Delineation (DC0, LDC), pp. 3001–3006.
ICPR-2018-GalteriBSB #algorithm #detection #video: Video Compression for Object Detection Algorithms (LG, MB, LS, ADB), pp. 3007–3012.
ICPR-2018-VoulodimosDDR #3d #sequence #summary: Kinematics-based Extraction of Salient 3D Human Motion Data for Summarization of Choreographic Sequences (AV, ND, ADD, IR), pp. 3013–3018.
ICPR-2018-0004CW: Weakly Supervised Domain-Specific Color Naming Based on Attention (LY0, YC, JvdW), pp. 3019–3024.
ICPR-2018-GabdulkhakovaK #distance: Confocal Ellipse-based Distance and Confocal Elliptical Field for polygonal shapes (AG, WGK), pp. 3025–3030.
ICPR-2018-HansenL #multi: Multiphase Local Mean Geodesic Active Regions (JDKH, FL), pp. 3031–3036.
ICPR-2018-GaoXLY #performance: A fast Cascade Shape Regression Method based on CNN-based Initialization (PG, JX, KL, YY), pp. 3037–3042.
ICPR-2018-DuanMKY #classification #image #using: A New Single Image Super-resolution Method Using SIMK-based Classification and ISRM Technique (PD, AM, XK, CY), pp. 3043–3048.
ICPR-2018-ChenYXT #video: Video Stitching with Extended-MeshFlow (KC0, JY, BX, JT), pp. 3049–3054.
ICPR-2018-FaulaBE #analysis #image #performance: A Fast Local Analysis by Thresholding applied to image matching (YF, SB, VE), pp. 3055–3060.
ICPR-2018-SwamiD #image #named #network: CANDY: Conditional Adversarial Networks based End-to-End System for Single Image Haze Removal (KS, SKD), pp. 3061–3067.
ICPR-2018-MustaniemiKSMH #detection #metric #performance #using: Fast Motion Deblurring for Feature Detection and Matching Using Inertial Measurements (JM, JK, SS, JM, JH), pp. 3068–3073.
ICPR-2018-DahlDTG #detection: Layered Surface Detection for Virtual Unrolling (VAD, ABD, CHT, CG), pp. 3074–3080.
ICPR-2018-LiuRYXCY #graph #image #network: Fully convolutional network and graph-based method for co-segmentation of retinal layer on macular OCT images (YL, GR, GY, XX, XC, YY), pp. 3081–3085.
ICPR-2018-WuW #gesture #recognition #using: Applying hand gesture recognition and joint tracking to a TV controller using CNN and Convolutional Pose Machine (YW, CMW), pp. 3086–3091.
ICPR-2018-0001D #network #recognition: Deep Emotion Transfer Network for Cross-database Facial Expression Recognition (SL0, WD), pp. 3092–3099.
ICPR-2018-ChenSSZ #evaluation #modelling #named: WiTT: Modeling and the evaluation of table tennis actions based on WIFI signals (CC, YS, KIS, HZ0), pp. 3100–3107.
ICPR-2018-KimT #authentication: One-factor Cancellable Biometrics based on Indexing-First-Order Hashing for Fingerprint Authentication (JK, ABJT), pp. 3108–3113.
ICPR-2018-LiuZWWZ #identification #mining #multi: Identification of Hypertension by Mining Class Association Rules from Multi-dimensional Features (FL0, XZ, ZW, TW, YZ), pp. 3114–3119.
ICPR-2018-AbateNBM #question #smarttech #what: What are you doing while answering your smartphone? (AFA, MN, SB, MDM), pp. 3120–3125.
ICPR-2018-LiangLTZ0 #on the #recognition: On Mugshot-based Arbitrary View Face Recognition (JL, FL0, HT, QZ, AKJ0), pp. 3126–3131.
ICPR-2018-LuoHD #constraints #recognition #subclass: Local Subclass Constraint for Facial Expression Recognition in the Wild (ZL, JH, WD), pp. 3132–3137.
ICPR-2018-CzovnyBSC #3d #using: Minutia Matching using 3D Pore Clouds (RKC, ORPB, LS, HSGC), pp. 3138–3143.
ICPR-2018-0051RF #3d: Dual-modality Talking-metrics: 3D Visual-Audio Integrated Behaviometric Cues from Speakers (JZ0, KR, RBF), pp. 3144–3149.
ICPR-2018-LakraTKV0 #named #segmentation: SegDenseNet: Iris Segmentation for Pre-and-Post Cataract Surgery (AL, PT, RK, MV, RS0), pp. 3150–3155.
ICPR-2018-SiddiquiV0 #approach #learning #recognition: Face Recognition for Newborns, Toddlers, and Pre-School Children: A Deep Learning Approach (SS, MV, RS0), pp. 3156–3161.
ICPR-2018-LatJ: Enhancing OCR Accuracy with Super Resolution (AL, CVJ), pp. 3162–3167.
ICPR-2018-KurzendorferBSB #analysis #classification #random #segmentation #using: Myocardial Scar Segmentation in LGE-MRI using Fractal Analysis and Random Forest Classification (TK, KB, SS, AB, CF, AKM), pp. 3168–3173.
ICPR-2018-BiswasMGBP #architecture #documentation #hybrid #recognition #robust: A Hybrid Deep Architecture for Robust Recognition of Text Lines of Degraded Printed Documents (CB, PSM, KG, UB, SKP), pp. 3174–3179.
ICPR-2018-DasRBP #classification #documentation #image #learning #network: Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks (AD, SR, UB, SKP), pp. 3180–3185.
ICPR-2018-YeZ0HBHH #re-engineering: A Unified Neighbor Reconstruction Method for Embeddings (ZY, ZZ, LB0, GH, ZJB, YH, ERH), pp. 3186–3191.
ICPR-2018-ZhuDR #classification #feature model #flexibility #image: Flexible and Discriminative Non-linear Embedding with Feature Selection for Image Classification (RZ, FD, YR), pp. 3192–3197.
ICPR-2018-BaiHA #analysis #correlation #kernel #recognition: Kernel Discriminant Correlation Analysis: Feature Level Fusion for Nonlinear Biometric Recognition (YB, MH, MAM), pp. 3198–3203.
ICPR-2018-YangCTWZ #behaviour #recognition: Recognition of Infants' Gaze Behaviors and Emotions (BY, JC, YT, LW, HZ), pp. 3204–3209.
ICPR-2018-KhalidY #multi #network #recognition: Multi-Modal Three-Stream Network for Action Recognition (MUK, JY), pp. 3210–3215.
ICPR-2018-ZhangCZ #architecture #network #recognition: Temporal Inception Architecture for Action Recognition with Convolutional Neural Networks (WZ, JC, HZ), pp. 3216–3221.
ICPR-2018-LiZXGX18a #network #recognition #speech: Recurrent Neural Network Based Small-footprint Wake-up-word Speech Recognition System with a Score Calibration Method (CL, LZ, SX, PG, BX0), pp. 3222–3227.
ICPR-2018-SaitohK #database #named #recognition #smarttech #speech #visual notation: SSSD: Speech Scene database by Smart Device for Visual Speech Recognition (TS, MK), pp. 3228–3232.
ICPR-2018-Shen0 #algorithm #composition: A New Singular Value Decomposition Algorithm for Octonion Signal (MS, RW0), pp. 3233–3237.
ICPR-2018-AbdolshahSRGV #constraints: Expected Hypervolume Improvement with Constraints (MA, AS, SR, SG0, SV), pp. 3238–3243.
ICPR-2018-Yang0K #generative #multi #network: Multi-scale Generative Adversarial Networks for Crowd Counting (JY, YZ0, SYK), pp. 3244–3249.
ICPR-2018-SinhaNGG #analysis #hybrid #navigation #network #performance: Hybrid Path Planner for Efficient Navigation in Urban Road Networks through Analysis of Trajectory Traces (SS, MKN, SG, SKG), pp. 3250–3255.
ICPR-2018-ZhangZDW #classification #image #network: Image Exploration Procedure Classification with Spike-timing Neural Network for the Blind (TZ, TZ, BSD, JPW), pp. 3256–3261.
ICPR-2018-Savchenko #performance #recognition #statistics #using: Efficient Statistical Face Recognition Using Trigonometric Series and CNN Features (AVS), pp. 3262–3267.
ICPR-2018-LeiZH0HL #classification #learning #multi #rank: Multi-classification of Parkinson's Disease via Sparse Low-Rank Learning (HL, YZ, ZH, FZ0, LH, BL), pp. 3268–3272.
ICPR-2018-ChanLK #mobile #realtime #recognition: Real-Time Texture-less Object Recognition on Mobile Devices (JC, JAL, QK), pp. 3273–3278.
ICPR-2018-TianZZLW #feature model #fine-grained #multi #recognition: Selective Multi-Convolutional Region Feature Extraction based Iterative Discrimination CNN for Fine-Grained Vehicle Model Recognition (YT, WZ, QZ, GL, XW), pp. 3279–3284.
ICPR-2018-ZhuZLLZC #identification #network: A Shortly and Densely Connected Convolutional Neural Network for Vehicle Re-identification (JZ, HZ, ZL, SL, LZ, CC), pp. 3285–3290.
ICPR-2018-LiW18a #detection #semantics #using #visual notation: Visual Relationship Detection Using Joint Visual-Semantic Embedding (BL, YW0), pp. 3291–3296.
ICPR-2018-WangGH #image: Time-Dependent Pre-attention Model for Image Captioning (FW, XG, LH), pp. 3297–3302.
ICPR-2018-ChengHW #problem #towards #visual notation: Towards Unconstrained Pointing Problem of Visual Question Answering: A Retrieval-based Method (WC, YH0, LW0), pp. 3303–3308.
ICPR-2018-YangLYL #image #recognition #visual notation: Action Recognition with Visual Attention on Skeleton Images (ZY, YL, JY, JL), pp. 3309–3314.
ICPR-2018-DehzangiBI #detection #multi #process #using: Activity Detection using Fusion of Multi-Pressure Sensors in Insoles (OD, BAB, OI), pp. 3315–3321.
ICPR-2018-UekiHKK #fine-grained #query #retrieval #using #video: Fine-grained Video Retrieval using Query Phrases - Waseda_Meisei TRECVID 2017 AVS System - (KU, KH, KK, TK), pp. 3322–3327.
ICPR-2018-SunYW0 #performance #retrieval: Discriminate Cross-modal Quantization for Efficient Retrieval (PS, CY, SW, XB0), pp. 3328–3334.
ICPR-2018-HaoDWT #fine-grained #learning #named #representation #retrieval: DeepFirearm: Learning Discriminative Feature Representation for Fine-grained Firearm Retrieval (JH, JD0, WW0, TT), pp. 3335–3340.
ICPR-2018-ZhangSOS #identification #network #using: Person Re-identification Using Two-Stage Convolutional Neural Network (YZ, JS, DO, HTS), pp. 3341–3346.
ICPR-2018-LePB #recognition: Human Gait Recognition with Micro-Doppler Radar and Deep Autoencoder (HTL0, SLP, AB), pp. 3347–3352.
ICPR-2018-ZhongD #analysis #difference #recognition: Deep Difference Analysis in Similar-looking Face recognition (YZ, WD), pp. 3353–3358.
ICPR-2018-ChoiCT #authentication #mobile #network #probability #random: One-class Random Maxout Probabilistic Network for Mobile Touchstroke Authentication (SC, IC, ABJT), pp. 3359–3364.
ICPR-2018-LiCGJH #gesture #multimodal #recognition #using: Multimodal Gesture Recognition Using Densely Connected Convolution and BLSTM (DL, YC, MkG, SJ, CH), pp. 3365–3370.
ICPR-2018-RaghavendraVRGB #detection #multi #recognition: Detecting Disguise Attacks on Multi-spectral Face Recognition Through Spectral Signatures (RR, NV, KBR, RSG, CB), pp. 3371–3377.
ICPR-2018-ChenLZ #gesture #performance #recognition #taxonomy: Temporal Hierarchical Dictionary with HMM for Fast Gesture Recognition (HC, XL0, GZ), pp. 3378–3383.
ICPR-2018-LiWX #multi #recognition: Facial Expression Recognition by Multi-Scale CNN with Regularized Center Loss (ZL, SW, GX), pp. 3384–3389.
ICPR-2018-LeeLC #using: Cancelable Biometrics Using Noise Embedding (DHL, SHL, NIC), pp. 3390–3395.
ICPR-2018-WangF #detection #using: Saliency Detection using Iterative Dynamic Guided Filtering (CW, YF), pp. 3396–3401.
ICPR-2018-LuoKWCS #anti #multi: Face Anti-Spoofing with Multi-Scale Information (SL, MK, SW, XC, SS), pp. 3402–3407.
ICPR-2018-FerrariBB #dataset #identification: Extended YouTube Faces: a Dataset for Heterogeneous Open-Set Face Identification (CF, SB, ADB), pp. 3408–3413.
ICPR-2018-LengK #network: Confidence-Driven Network for Point-to-Set Matching (ML, IAK), pp. 3414–3420.
ICPR-2018-ZuninoMCAPBVBM #analysis #detection #gesture #video: Video Gesture Analysis for Autism Spectrum Disorder Detection (AZ, PM, AC, CA, JP, FB, EV, CB, VM), pp. 3421–3426.
ICPR-2018-RhifWF #3d #network #recognition #sequence #using: Action Recognition from 3D Skeleton Sequences using Deep Networks on Lie Group Features (MR, HW, IRF), pp. 3427–3432.
ICPR-2018-DongZL #network #recognition: Dynamic Facial Expression Recognition Based on Convolutional Neural Networks with Dense Connections (JD, HZ, LL), pp. 3433–3438.
ICPR-2018-Gonzalez-SosaVH #distance #recognition: Person Recognition at a Distance: Improving Face Recognition Through Body Static Information (EGS, RVR, JHO, JF), pp. 3439–3444.
ICPR-2018-DamerWHCB0K #recognition #robust: Deep Learning-based Face Recognition and the Robustness to Perspective Distortion (ND, YW, OH, CC, BB, AB0, AK), pp. 3445–3450.
ICPR-2018-LaiY #gesture #recognition: CNN+RNN Depth and Skeleton based Dynamic Hand Gesture Recognition (KL, SNY), pp. 3451–3456.
ICPR-2018-GuoNC #distance #recognition: A Joint Density Based Rank-Score Fusion for Soft Biometric Recognition at a Distance (BHG, MSN, JNC), pp. 3457–3462.
ICPR-2018-HanselmannN #invariant #optimisation #recognition: Optimizing Energies for Pose-Invariant Face Recognition (HH, HN), pp. 3463–3468.
ICPR-2018-SoleymaniDKDN #abstraction #identification #multimodal #network: Multi-Level Feature Abstraction from Convolutional Neural Networks for Multimodal Biometric Identification (SS, AD, HK, JMD, NMN), pp. 3469–3476.
ICPR-2018-XiangLHH #identification: Person Re-identification Based on Feature Fusion and Triplet Loss Function (JX, RL, JH, WH), pp. 3477–3482.
ICPR-2018-AiZYH #algorithm #identification #named: iCushion: A Pressure Map Algorithm for High Accuracy Human Identification (HA, LZ, ZY, HH), pp. 3483–3488.
ICPR-2018-HuKLFLZD #learning #named #representation: FV-Net: learning a finger-vein feature representation based on a CNN (HH, WK, YL, YF, HL, JZ, FD), pp. 3489–3494.
ICPR-2018-YangHPFZ #estimation #low level: Incorporating high-level and low-level cues for pain intensity estimation (RY, XH, JP, XF, GZ), pp. 3495–3500.
ICPR-2018-ChengK #3d #encoding #recognition: Advancing Surface Feature Encoding and Matching for More Accurate 3D Biometric Recognition (KHMC, AK), pp. 3501–3506.
ICPR-2018-MingCLVB #detection #interactive #liveness #named #network #verification: FaceLiveNet: End-to-End Networks Combining Face Verification with Interactive Facial Expression-Based Liveness Detection (ZM, JC, MML, MV, JCB), pp. 3507–3512.
ICPR-2018-MutasimBTIA #classification #video: Effect of Artefact Removal Techniques on EEG Signals for Video Category Classification (AKM, MRB, RST, MKI, MAA), pp. 3513–3518.
ICPR-2018-ZengWCYHLZ #3d #constraints: High-Quality Facial Keypoints Matching with Motion Smoothness Constraint and 3D Model Constraint (XZ, XW0, KC, PY, XH, DL, YZ0), pp. 3519–3524.
ICPR-2018-BeheraDDR #recognition #using: Air Signature Recognition Using Deep Convolutional Neural Network-Based Sequential Model (SKB, AKD, DPD, PPR0), pp. 3525–3530.
ICPR-2018-LiaoZWN #detection #named #network #recognition: Uniface: A Unified Network for Face Detection and Recognition (ZL, PZ, QW, BN), pp. 3531–3536.
ICPR-2018-WenWSY #adaptation #learning #recognition #representation: Adaptive convolution local and global learning for class-level joint representation of face recognition with single sample per person (WW, XW0, LS, MY0), pp. 3537–3542.
ICPR-2018-NguyenNSADF #learning #recognition: Meta Transfer Learning for Facial Emotion Recognition (DNT, KN0, SS, IA, DD, CF), pp. 3543–3548.
ICPR-2018-HibrajVSP #clustering #set #using: Speaker Clustering Using Dominant Sets (FH, SV, TS, MP), pp. 3549–3554.
ICPR-2018-DantchevaBB: Show me your face and I will tell you your height, weight and body mass index (AD, FB, PTB), pp. 3555–3560.
ICPR-2018-ZouZLLH #generative #image #lens: Generation Textured Contact Lenses Iris Images Based on 4DCycle-GAN (HZ, HZ, XL, JL, ZH), pp. 3561–3566.
ICPR-2018-ChowdhuryAT0R #dataset #recognition: MSU-AVIS dataset: Fusing Face and Voice Modalities for Biometric Recognition in Indoor Surveillance Videos (AC, YA, LT, XL0, AR), pp. 3567–3573.
ICPR-2018-MadapanaW #gesture #learning #recognition: Hard Zero Shot Learning for Gesture Recognition (NM, JPW), pp. 3574–3579.
ICPR-2018-NiuHSC #learning #named: SynRhythm: Learning a Deep Heart Rate Estimator from General to Specific (XN, HH, SS, XC), pp. 3580–3585.
ICPR-2018-PanHSC #estimation #robust: Revised Contrastive Loss for Robust Age Estimation from Face (HP, HH, SS, XC), pp. 3586–3591.
ICPR-2018-GaolLH0W #automation #learning #multi #predict: Automatic Facial Attractiveness Prediction by Deep Multi-Task Learning (LG, WL, ZH, DH0, YW), pp. 3592–3597.
ICPR-2018-DehzangiM #behaviour #predict #using: Unobtrusive Driver Drowsiness Prediction Using Driving Behavior from Vehicular Sensors (OD, SM), pp. 3598–3603.
ICPR-2018-DaiHGX0GQ #detection #multi #network #segmentation: Fused Text Segmentation Networks for Multi-oriented Scene Text Detection (YD, ZH, YG, YX, KC0, JG, WQ), pp. 3604–3609.
ICPR-2018-JiangZWYLWFL #detection: R2 CNN: Rotational Region CNN for Arbitrarily-Oriented Scene Text Detection (YJ, XZ, XW, SY, WL, HW, PF, ZL), pp. 3610–3615.
ICPR-2018-WeiZG #constraints #documentation #image #keyword #representation #visual notation #word: Word Image Representation Based on Visual Embeddings and Spatial Constraints for Keyword Spotting on Historical Documents (HW, HZ0, GG), pp. 3616–3621.
ICPR-2018-LiZQ #assessment #documentation #image #named #quality: CG-DIQA: No-Reference Document Image Quality Assessment Based on Character Gradient (HL, FZ, JQ), pp. 3622–3626.
ICPR-2018-LiYL #clustering #detection #documentation #image #predict: Page Object Detection from PDF Document Images by Deep Structured Prediction and Supervised Clustering (XL, FY, CLL), pp. 3627–3632.
ICPR-2018-EskenaziGO #component #image #using: Watercolor, Segmenting Images Using Connected Color Components (SE, PGK, JMO), pp. 3633–3638.
ICPR-2018-BhuniaBBKB0P #network #using: Handwriting Trajectory Recovery using End-to-End Deep Encoder-Decoder Network (AKB, AB, AKB, AK, PB, PPR0, UP0), pp. 3639–3644.
ICPR-2018-BhuniaBBKB0P18a #generative #image #network #using #word: Word Level Font-to-Font Image Translation using Convolutional Recurrent Generative Adversarial Networks (AKB, AKB, PB, AK, AB, PPR0, UP0), pp. 3645–3650.
ICPR-2018-KhareSNSGPL #segmentation: Weighted-Gradient Features for Handwritten Line Segmentation (VK, PS, BJN, GCS, DSG, UP0, TL), pp. 3651–3656.
ICPR-2018-NavyaSSRGPL #gender #identification #multi: Multi-Gradient Directional Features for Gender Identification (BJN, GCS, PS, SR, DSG, UP0, TL), pp. 3657–3662.
ICPR-2018-KilKC #using: Scene text rectification using glyph and character alignment properties (THK, HIK, NIC), pp. 3663–3668.
ICPR-2018-YuanCLYL #detection: Detecting Phishing Websites and Targets Based on URLs and Webpage Links (HY, XC0, YL, ZY, WL), pp. 3669–3674.
ICPR-2018-HanAMYU #identification: Script Identification of Central Asia Based on Fused Texture Features (XkH, AA, HM, NY, KU), pp. 3675–3680.
ICPR-2018-ZhangZDD #analysis #network #online #recognition: Trajectory-based Radical Analysis Network for Online Handwritten Chinese Character Recognition (JZ, YZ, JD, LD), pp. 3681–3686.
ICPR-2018-YuLLW #detection: A Fusion Strategy for the Single Shot Text Detector (ZY, SL, YL, PSPW), pp. 3687–3691.
ICPR-2018-DangCLOT #approach #random: A randomized hierarchical trees indexing approach for camera-based information spotting (QBD, MC, MML, JMO, CDT), pp. 3692–3697.
ICPR-2018-CaoFM #multi #network #recognition: An End-to-End Neural Network for Multi-line License Plate Recognition (YC, HF, HM), pp. 3698–3703.
ICPR-2018-TuggenerESPS #classification #dataset #detection #segmentation: DeepScores-A Dataset for Segmentation, Detection and Classification of Tiny Objects (LT, IE, JS, MP, TS), pp. 3704–3709.
ICPR-2018-ZhaoPL0DWQ #learning #locality #semantics #topic #using: Learning Topics Using Semantic Locality (ZZ, KP, SL, ZL0, CD, YW, QQ), pp. 3710–3715.
ICPR-2018-XiongJXXLW #documentation #energy #estimation #image #using: Historical document image binarization using background estimation and energy minimization (WX0, XJ, JX, ZX, ML, JW), pp. 3716–3721.
ICPR-2018-0004BWS #distance #word: Improve Word Mover's Distance with Part-of-Speech Tagging (XC0, LB, DW, JS), pp. 3722–3728.
ICPR-2018-ZhanLL #network #recognition #string #using: Handwritten Digit String Recognition using Convolutional Neural Network (HZ, SL, YL), pp. 3729–3734.
ICPR-2018-ZhuD #detection #robust: Sliding Line Point Regression for Shape Robust Scene Text Detection (YZ, JD), pp. 3735–3740.
ICPR-2018-MohantyDG18a #detection #network #robust: Robust Scene Text Detection with Deep Feature Pyramid Network and CNN based NMS Model (SM, TD, HPG), pp. 3741–3746.
ICPR-2018-SongCHSC #detection #refinement #semantics: Scene Text Detection via Deep Semantic Feature Fusion and Attention-based Refinement (YS, YC, HH, SS, XC), pp. 3747–3752.
ICPR-2018-MandalCPS #online #recognition: Exploring Discriminative HMM States for Improved Recognition of Online Handwriting (SM, HC, SRMP, SS), pp. 3753–3758.
ICPR-2018-WangHJ #learning #using: Focus on Scene Text Using Deep Reinforcement Learning (HW, SH, LJ), pp. 3759–3765.
ICPR-2018-HeYLXLHS #estimation #physics #using: Variational Mode Decomposition-Based Heart Rate Estimation Using Wrist-Type Photoplethysmography During Physical Exercise (WH, YY, YL, HX, LL0, WH, MS), pp. 3766–3771.
ICPR-2018-AlshawaqfehKS #detection #robust: Robust Fussed Lasso Model for Recurrent Copy Number Variation Detection (MA, AAK, ES), pp. 3772–3777.
ICPR-2018-CaoLL0JJC #detection #image #learning: Deep Learning Based Bioresorbable Vascular Scaffolds Detection in IVOCT Images (YC, YL, JL, RZ0, QJ, JJ, YC), pp. 3778–3783.
ICPR-2018-BicegoLDGA #mining #modelling #topic #using: Mining NMR Spectroscopy Using Topic Models (MB, PL, MD, FG, MA), pp. 3784–3789.
ICPR-2018-YangLPKWSLDCTZ #3d #automation #image #network #segmentation: Automatic Segmentation of Kidney and Renal Tumor in CT Images Based on 3D Fully Convolutional Neural Network with Pyramid Pooling Module (GY, GL, TP, YK, JW, HS, LL, JLD, JLC, LT, XZ), pp. 3790–3795.
ICPR-2018-LiDHCH #multi #process #semantics: Multi-label Semantic Decoding from Human Brain Activity (DL, CD, LH, ZC, HH), pp. 3796–3801.
ICPR-2018-0003TCSS: Despeckling CNN with Ensembles of Classical Outputs (DM0, ST, SC, MS, ASS), pp. 3802–3807.
ICPR-2018-TlustyAB #clustering #detection #estimation: Unsupervised clustering of mammograms for outlier detection and breast density estimation (TT, GA, RBA), pp. 3808–3813.
ICPR-2018-WangZGW #detection #image #multi #network #parametricity #using: Fully convolutional neural networks for prostate cancer detection using multi-parametric magnetic resonance images: an initial investigation (YW, BZ, DG, JW), pp. 3814–3819.
ICPR-2018-JiQYKZ #automation #image #network #segmentation #using: Automatic Prostate Segmentation on MR Images Using Enhanced Holistically-Nested Networks (DJ, JQ, JY, TK, SZ), pp. 3820–3825.
ICPR-2018-TheagarajanGB #automation #classification #generative #named: DeephESC: An Automated System for Generating and Classification of Human Embryonic Stem Cells (RT, BXG, BB), pp. 3826–3831.
ICPR-2018-Dou0 #2d #3d #network #predict: 2D and 3D Convolutional Neural Network Fusion for Predicting the Histological Grade of Hepatocellular Carcinoma (TD, WZ0), pp. 3832–3837.
ICPR-2018-YuanTLDZ #automation #learning #multi #segmentation #using: Fully Automatic Segmentation of the Left Ventricle Using Multi-Scale Fusion Learning (TY, QT, XL, XD, JZ), pp. 3838–3843.
ICPR-2018-AbreuFVBDNW #2d #graph #image #modelling #segmentation: Model-based graph segmentation in 2-D fluorescence microsecopy images (AA, FXF, SV, PB, PD, BN, CW), pp. 3844–3849.
ICPR-2018-LiCZC #detection #network: Mammographic mass detection based on convolution neural network (YL, HC, LZ, LC), pp. 3850–3855.
ICPR-2018-SuCWLJT #image: Encoded Texture Features to Characterize Bone Radiograph Images (RS, WC, LW, XL, QJ, WT), pp. 3856–3861.
ICPR-2018-ElNakiebNSDMSEK #personalisation #towards: Towards Personalized Autism Diagnosis: Promising Results (YE, MN, AS0, OD, AMM, AS, AE, RK, MG, AK, GB, AEB), pp. 3862–3867.
ICPR-2018-LicandroSRDDSLK #identification: WGAN Latent Space Embeddings for Blast Identification in Childhood Acute Myeloid Leukaemia (RL, TS, MR, MD, MD, AS, GL, MK), pp. 3868–3873.
ICPR-2018-XieCL #image #rank #re-engineering: Nonlocal Low-Rank and Total Variation Constrained PET Image Reconstruction (NX, YC, HL), pp. 3874–3879.
ICPR-2018-ZhaoLZTNM #analysis #automation #component #image #multi #robust #segmentation #using: Automatic Multi-Atlas Segmentation for Abdominal Images Using Template Construction and Robust Principal Component Analysis (YZ0, HL0, RZ, GT, MN, BHM), pp. 3880–3885.
ICPR-2018-EladawiEFPGARKS #analysis #image: Early Diagnosis of Diabetic Retinopathy in OCTA Images Based on Local Analysis of Retinal Blood Vessels and Foveal Avascular Zone (NE, ME, LF, FP, MG, AA, AEMR, RK, SS, AEB), pp. 3886–3891.
ICPR-2018-MaSLGX #detection #image #novel: A Novel Two-Stage Deep Method for Mitosis Detection in Breast Cancer Histology Images (MM, YS, WL, YG0, JX), pp. 3892–3897.
ICPR-2018-AbdeltawabSSMEG #3d #detection: A New 3D CNN-based CAD System for Early Detection of Acute Renal Transplant Rejection (HA, MS, AS0, SM, MEB, MG, YA, MAEG, ACD, MTEM, AEB), pp. 3898–3903.
ICPR-2018-Bhugra0ACLC #automation #quantifier: Automatic Quantification of Stomata for High-Throughput Plant Phenotyping (SB, DM0, AA, SC, BL, AC), pp. 3904–3910.
ICPR-2018-ZhangLZXSL #classification #network: Spatial Pyramid Dilated Network for Pulmonary Nodule Malignancy Classification (GZ, YL, DZ, YX, YS, JL), pp. 3911–3916.
ICPR-2018-PiantadosiSS #network #segmentation: Breast Segmentation in MRI via U-Net Deep Convolutional Neural Networks (GP, MS, CS), pp. 3917–3922.
ICPR-2018-RedaGSEEAEEKE #classification #novel #precise: A Novel ADCs-Based CNN Classification System for Precise Diagnosis of Prostate Cancer (IR, MG, AS0, ME, AAEF, BOA, MAEG, AE, RK, AEB), pp. 3923–3928.
ICPR-2018-MoTWW #approach #detection #performance: An Efficient Approach for Polyps Detection in Endoscopic Videos Based on Faster R-CNN (XM, KT, QW, GW), pp. 3929–3934.
ICPR-2018-XuXZHCZDNW #estimation #framework #hybrid: A Hybrid Framework for Tumor Saliency Estimation (FX, MX, YZ, KH, HDC, BZ, JD, CN, YW), pp. 3935–3940.
ICPR-2018-WangK #image #segmentation: Nuclei Segmentation of Cervical Cell Images Based on Intermediate Segment Qualifier (RW, SiK), pp. 3941–3946.
ICPR-2018-ZhangJZZSLH #multi #named #segmentation: SequentialSegNet: Combination with Sequential Feature for Multi-Organ Segmentation (YZ, XJ, CZ, YZ, ZS, ZL, ZH), pp. 3947–3952.

Proceedings of the 24th International Conference on Pattern RecognitionICPR, 2018.

Contents (653 items)

Proceedings of the 24th International Conference on Pattern Recognition
ICPR, 2018.