Stem scene$ (all stems)

278 papers:

DAC-2015-CavigelliMB #embedded #network #realtime

Accelerating real-time embedded scene labeling with convolutional networks (LC, MM, LB), p. 6.

HIMI-IKC-2015-ZengCLSHC #framework #mobile #query

Scene Feature Recognition-Enabled Framework for Mobile Service Information Query System (YCZ, YHC, TYL, MJS, PYH, GLC), pp. 64–74.

ECIR-2015-SaracIGD #classification #concept #flexibility #framework #named

ConceptFusion: A Flexible Scene Classification Framework (MIS, AI, EG, PD), pp. 55–60.

CASE-2014-ChouW #image #locality

1-point affine RANSAC for scene image matching in appearance-based localization (CCC, CCW), pp. 1194–1199.

CHI-2014-CohenDMHT #named #visual notation

OneSpace: shared visual scenes for active freeplay (MC, KRD, HM, SEH, AT), pp. 2177–2180.

DUXU-TMT-2014-CoventryBJM #behaviour #named #security

SCENE: A Structured Means for Creating and Evaluating Behavioral Nudges in a Cyber Security Environment (LMC, PB, DJ, APAvM), pp. 229–239.

CIKM-2014-McParlaneMJ #social #social media #visual notation

“Picture the scene...”;: Visually Summarising Social Media Events (PJM, AJM, JMJ), pp. 1459–1468.

ICML-c1-2014-PinheiroC #network

Recurrent Convolutional Neural Networks for Scene Labeling (PHOP, RC), pp. 82–90.

ICML-c2-2014-LiG #classification #learning #representation #semantics

Latent Semantic Representation Learning for Scene Classification (XL, YG), pp. 532–540.

ICPR-2014-AfzalAFMO #3d #multi #re-engineering

RGB-D Multi-view System Calibration for Full 3D Scene Reconstruction (HA, DA, DF, BM, BEO), pp. 2459–2464.

ICPR-2014-AggarwalNJ #perspective

Estimating Floor Regions in Cluttered Indoor Scenes from First Person Camera View (SA, AMN, CVJ), pp. 4275–4280.

ICPR-2014-BartoliLKBB #adaptation #detection #multi #performance

Unsupervised Scene Adaptation for Faster Multi-scale Pedestrian Detection (FB, GL, SK, ADB, ADB), pp. 3534–3539.

ICPR-2014-ChangCC #image

Spatially-Varying Image Warps for Scene Alignment (CHC, CJC, YYC), pp. 64–69.

ICPR-2014-ChenCF #approach #classification #hybrid #semantics

A Hybrid Holistic/Semantic Approach for Scene Classification (ZC, ZC, HF), pp. 2299–2304.

ICPR-2014-Climent-PerezMR #detection #multi #using

Multi-view Event Detection in Crowded Scenes Using Tracklet Plots (PCP, DNM, PR), pp. 4370–4375.

ICPR-2014-ElmikatyS #detection #image #multi #using

Car Detection in High-Resolution Urban Scenes Using Multiple Image Descriptors (ME, TS), pp. 4299–4304.

ICPR-2014-FornoniC #learning #naive bayes #recognition

Scene Recognition with Naive Bayes Non-linear Learning (MF, BC), pp. 3404–3409.

ICPR-2014-FrinkenIIFU #recognition

Improving Point of View Scene Recognition by Considering Textual Data (VF, YI, RI, KF, SU), pp. 2966–2971.

ICPR-2014-GaoWXSZ #recognition #representation

Stroke Bank: A High-Level Representation for Scene Character Recognition (SG, CW, BX, CS, ZZ), pp. 2909–2913.

ICPR-2014-HiraiOHT

An HDR Spectral Imaging System for Time-Varying Omnidirectional Scene (KH, NO, TH, ST), pp. 2059–2064.

ICPR-2014-HtikeH #adaptation #detection #performance #video

Efficient Non-iterative Domain Adaptation of Pedestrian Detectors to Video Scenes (KKH, DCH), pp. 654–659.

ICPR-2014-HuML #composition #probability

Dynamic Task Decomposition for Probabilistic Tracking in Complex Scenes (TH, SM, OL), pp. 4134–4139.

ICPR-2014-KamberovBKK #detection #video

Unsupervised Detection of Video Sub-scenes (GK, MB, LK, OK), pp. 1934–1939.

ICPR-2014-KawarabukiO #detection

Snowfall Detection in a Foggy Scene (HK, KO), pp. 877–882.

ICPR-2014-KimBKC #multi #online #people

MAP-Based Online Data Association for Multiple People Tracking in Crowded Scenes (SWK, MB, KK, JYC), pp. 1212–1217.

ICPR-2014-LiuWF #modelling

Modeling the Relationship of Action, Object, and Scene (JL, XW, YF), pp. 2005–2010.

ICPR-2014-LiuZZL #detection #realtime

Real-Time Scene Text Detection Based on Stroke Model (YL, DZ, YZ, SL), pp. 3116–3120.

ICPR-2014-LuWMST #detection #modelling

Anomaly Detection through Spatio-temporal Context Modeling in Crowded Scenes (TL, LW, XM, PS, CLT), pp. 2203–2208.

ICPR-2014-LuWW #detection #summary

Audiotory Movie Summarization by Detecting Scene Changes and Sound Events (TL, YW, GW), pp. 756–760.

ICPR-2014-MuddamsettySTM #detection #using

Spatio-temporal Saliency Detection in Dynamic Scenes Using Local Binary Patterns (SMM, DS, AT, FM), pp. 2353–2358.

ICPR-2014-SuLTLT #recognition #using

Character Recognition in Natural Scenes Using Convolutional Co-occurrence HOG (BS, SL, ST, JHL, CLT), pp. 2926–2931.

ICPR-2014-SunHJC #detection #image #network #robust

Robust Text Detection in Natural Scene Images by Generalized Color-Enhanced Contrasting Extremal Region and Neural Networks (LS, QH, WJ, KC), pp. 2715–2720.

ICPR-2014-TianLST #multi #segmentation

Scene Text Segmentation with Multi-level Maximally Stable Extremal Regions (ST, SL, BS, CLT), pp. 2703–2708.

ICPR-2014-TuXN #analysis #detection #process

Computational Auditory Scene Analysis Based Voice Activity Detection (MT, XX, XN), pp. 797–802.

ICPR-2014-WangFH0KH #detection #image #performance

Fast and Accurate Text Detection in Natural Scene Images with User-Intention (LW, WF, YH, JS, YK, YH), pp. 2920–2925.

ICPR-2014-WanHA #image #learning #recognition

Indoor Scene Recognition from RGB-D Images by Learning Scene Bases (SW, CH, JKA), pp. 3416–3421.

ICPR-2014-XuSLPT #classification #video

Graphics and Scene Text Classification in Video (JX, PS, TL, TQP, CLT), pp. 4714–4719.

ICPR-2014-XuSLT #2d #3d #classification #video

2D and 3D Video Scene Text Classification (JX, PS, TL, CLT), pp. 2932–2937.

ICPR-2014-YooJKC #learning #optimisation

Transfer Learning of Motion Patterns in Traffic Scene via Convex Optimization (YJY, HJ, SWK, JYC), pp. 4158–4163.

ICPR-2014-ZhangQWL #classification #learning #online

Object Classification in Traffic Scene Surveillance Based on Online Semi-supervised Active Learning (ZZ, JQ, YW, ML), pp. 3086–3091.

ICPR-2014-ZouYCDJ #clustering #correlation #topic #video

A Belief Based Correlated Topic Model for Trajectory Clustering in Crowded Video Scenes (JZ, QY, YC, DSD, JJ), pp. 2543–2548.

DRR-2013-KumarPR #image #named #recognition #segmentation #word

NESP: Nonlinear enhancement and selection of plane for optimal segmentation and recognition of scene word images (DK, MNAP, AGR).

ICDAR-2013-BaiYL #correlation #locality #using

Scene Text Localization Using Gradient Local Correlation (BB, FY, CLL), pp. 1380–1384.

ICDAR-2013-FeildL #recognition

Improving Open-Vocabulary Scene Text Recognition (JLF, EGLM), pp. 604–608.

ICDAR-2013-FeildLS #probability #recognition #using

Using a Probabilistic Syllable Model to Improve Scene Text Recognition (JLF, EGLM, DAS), pp. 897–901.

ICDAR-2013-GaoWXSZLS #adaptation #detection

Adaptive Scene Text Detection Based on Transferring Adaboost (SG, CW, BX, CS, YZ, ZL, YS), pp. 388–392.

ICDAR-2013-GoelMAJ #word

Whole is Greater than Sum of Parts: Recognizing Scene Text Words (VG, AM, KA, CVJ), pp. 398–402.

ICDAR-2013-GomezK #multi

Multi-script Text Extraction from Natural Scenes (LGiB, DK), pp. 467–471.

ICDAR-2013-HuangSU #detection

Scene Character Detection by an Edge-Ray Filter (RH, PS, SU), pp. 462–466.

ICDAR-2013-IwamuraTK #automation #database

Automatic Labeling for Scene Text Database (MI, MT, KK), pp. 1365–1369.

ICDAR-2013-NarangRMH #image #recognition

Devanagari Character Recognition in Scene Images (VN, SR, OVRM, MH), pp. 902–906.

ICDAR-2013-NeumannM #multi #on the #recognition

On Combining Multiple Segmentations in Scene Text Recognition (LN, JM), pp. 523–527.

ICDAR-2013-SeokK #recognition

Scene Text Recognition with a Hough Forest Implicit Shape Model (JHS, JHK), pp. 599–603.

ICDAR-2013-SunH #approach #component #image

An Improved Component Tree Based Approach to User-Intention Guided Text Extraction from Natural Scene Images (LS, QH), pp. 383–387.

ICDAR-2013-TeradaHFU #detection #on the

On the Possibility of Structure Learning-Based Scene Character Detector (YT, RH, YF, SU), pp. 472–476.

ICDAR-2013-TianLST #recognition #using

Scene Text Recognition Using Co-occurrence of Histogram of Oriented Gradients (ST, SL, BS, CLT), pp. 912–916.

ICDAR-2013-TianSPT #re-engineering

Scene Character Reconstruction through Medial Axis (ST, PS, TQP, CLT), pp. 1360–1364.

ICDAR-2013-WangSZ #component #detection #multi #segmentation

Natural Scene Text Detection with Multi-channel Connected Component Segmentation (XW, YS, YZ), pp. 1375–1379.

ICDAR-2013-YiYT #case study #comparative #recognition

Feature Representations for Scene Text Character Recognition: A Comparative Study (CY, XY, YT), pp. 907–911.

ICDAR-2013-ZhouFLW #segmentation

Scene Text Segmentation via Inverse Rendering (YZ, JLF, EGLM, RW), pp. 457–461.

ICSM-2013-KwonT #energy #mobile

Reducing the Energy Consumption of Mobile Applications Behind the Scenes (YWK, ET), pp. 170–179.

OCSC-2013-YamauchiHN #analysis #source code #twitter

Searching Emotional Scenes in TV Programs Based on Twitter Emotion Analysis (TY, YH, YIN), pp. 432–441.

SIGIR-2013-YinYHH #detection #image #retrieval #robust

Accurate and robust text detection: a step-in for text retrieval in natural scene images (XCY, XY, KH, HWH), pp. 1091–1092.

CSCW-2012-PoelmanALJ

As if being there: mediated reality for crime scene investigation (RP, OA, SL, PJ), pp. 1267–1276.

ICML-2012-FarabetCNL #learning #multi #parsing

Scene parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers (CF, CC, LN, YL), p. 241.

ICML-2012-JiangLS #3d #learning #using

Learning Object Arrangements in 3D Scenes using Human Context (YJ, ML, AS), p. 119.

ICPR-2012-BergamascoATFZ #segmentation

Pairwise similarities for scene segmentation combining color and depth data (FB, AA, AT, MF, PZ), pp. 3565–3568.

ICPR-2012-ChenCZ #classification #clique #representation

Object clique representation for scene classification (JC, XC, BZ), pp. 2829–2832.

ICPR-2012-ChowdhuryBP #detection #using

Scene text detection using sparse stroke information and MLP (ARC, UB, SKP), pp. 294–297.

ICPR-2012-DingLHXW #recognition #video

Context-aware horror video scene recognition via cost-sensitive sparse coding (XD, BL, WH, WX, ZW), pp. 1904–1907.

ICPR-2012-FelhiBT #detection #image

A skeleton based descriptor for detecting text in real scene images (MF, NB, ST), pp. 282–285.

ICPR-2012-GaoM #analysis #canonical #correlation #detection #kernel #multi #using

Multi-modality movie scene detection using Kernel Canonical Correlation Analysis (GG, HM), pp. 3074–3077.

ICPR-2012-GonzalezBTB #image #recognition

A character recognition method in natural scene images (ÁG, LMB, JJYT, SB), pp. 621–624.

ICPR-2012-HuangOSU #detection #framework #multi #recognition

Scene character detection and recognition based on multiple hypotheses framework (RH, SO, PS, SU), pp. 717–720.

ICPR-2012-HuynhR #segmentation

Illuminant segmentation in non-uniformly lit scenes (CPH, ARK), pp. 3664–3667.

ICPR-2012-KumarCD #documentation #estimation #image

Sharpness estimation for document and scene images (JK, FC, DSD), pp. 3292–3295.

ICPR-2012-LiL #detection

Scene text detection via stroke width (YL, HL), pp. 681–684.

ICPR-2012-LiuHI #3d #image #re-engineering

Stage-based 3D scene reconstruction from single image (YL, PH, EI), pp. 1034–1037.

ICPR-2012-LiuLW #effectiveness #image #locality

Effectively localize text in natural scene images (XL, KL, WW), pp. 1197–1200.

ICPR-2012-NakazawaMMNHYY #multi #re-engineering #using

Dynamic scene reconstruction using asynchronous multiple Kinects (MN, IM, YM, HN, HH, HY, YY), pp. 469–472.

ICPR-2012-ParisHG #analysis #categorisation #image #towards

Sparse coding for histograms of local binary patterns applied for image categorization: Toward a Bag-of-Scenes analysis (SP, XH, HG), pp. 2817–2820.

ICPR-2012-PhanST #detection #symmetry #using

Text detection in natural scenes using Gradient Vector Flow-Guided symmetry (TQP, PS, CLT), pp. 3296–3299.

ICPR-2012-PotapovaZV #3d #segmentation

Attention-driven segmentation of cluttered 3D scenes (EP, MZ, MV), pp. 3610–3613.

ICPR-2012-RoyG #detection #framework #image #locality #probability

A probabilistic framework for logo detection and localization in natural scene images (AR, UG), pp. 2051–2054.

ICPR-2012-Sanchez-RieraCH #robust

Robust spatiotemporal stereo for dynamic scenes (JSR, JC, RH), pp. 360–363.

ICPR-2012-SankaranarayananD #locality #modelling #segmentation

Segmentation and scene modeling for MIL-based target localization (KS, JWD), pp. 3325–3328.

ICPR-2012-ShiT

Background subtraction via early recurrence in dynamic scenes (XS, JKT), pp. 3172–3175.

ICPR-2012-SomanathK #image #recognition #representation

Arrangement based image representation for scene recognition (GS, CK), pp. 2436–2439.

ICPR-2012-YinYHI #effectiveness #geometry #image #locality

Effective text localization in natural scene images with MSER, geometry-based grouping and AdaBoost (XY, XCY, HWH, KI), pp. 725–728.

ICPR-2012-ZenRSRS #categorisation #functional #semantics

Enhanced semantic descriptors for functional scene categorization (GZ, NR, JS, ER, NS), pp. 1985–1988.

ICPR-2012-ZhuSX #performance #segmentation

An efficient r-KDE model for the segmentation of dynamic scenes (QZ, ZS, YX), pp. 198–201.

DRR-2011-FanSNMH #feature model #recognition

Natural scene logo recognition by joint boosting feature selection in salient regions (WF, JS, SN, AM, YH), pp. 1–10.

ICDAR-2011-ChoSLK #multi

Scene Text Extraction by Superpixel CRFs Combining Multiple Character Features (MSC, JHS, SL, JHK), pp. 1034–1038.

ICDAR-2011-CoatesCCSSWWN #detection #image #learning #recognition

Text Detection and Character Recognition in Scene Images with Unsupervised Feature Learning (AC, BC, CC, SS, BS, TW, DJW, AYN), pp. 440–445.

ICDAR-2011-IwamuraKK #image #multi #recognition #using

Recognition of Multiple Characters in a Scene Image Using Arrangement of Local Features (MI, TK, KK), pp. 1409–1413.

ICDAR-2011-LeeLLYK #detection

AdaBoost for Text Detection in Natural Scene (JJL, PHL, SWL, ALY, CK), pp. 429–434.

ICDAR-2011-MishraAJ

An MRF Model for Binarization of Natural Scene Text (AM, KA, CVJ), pp. 11–16.

ICDAR-2011-PanZSN11a #adaptation #detection #segmentation #verification

Improving Scene Text Detection by Scale-Adaptive Segmentation and Weighted CRF Verification (YFP, YZ, JS, SN), pp. 759–763.

ICDAR-2011-ShahabSD11a #challenge #contest #image #robust

ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text in Scene Images (AS, FS, AD), pp. 1491–1496.

ICDAR-2011-WakaharaK #clustering #image #string #using

Binarization of Color Character Strings in Scene Images Using K-Means Clustering and Support Vector Machines (TW, KK), pp. 274–278.

ICDAR-2011-YamazoeEYT #approach #finite #recognition #transducer

Hypothesis Preservation Approach to Scene Text Recognition with Weighted Finite-State Transducer (TY, ME, TY, KT), pp. 359–363.

ICDAR-2011-YiT #detection #image #word

Text Detection in Natural Scene Images by Stroke Gabor Words (CY, YT), pp. 177–181.

ICDAR-2011-ZhangLYDW #random #recognition #using

An Improved Scene Text Extraction Method Using Conditional Random Field and Optical Character Recognition (HZ, CL, CY, XD, KW), pp. 708–712.

CHI-2011-LuffYKH

Hands on hitchcock: embodied reference to a moving scene (PL, NY, HK, CH), pp. 43–52.

HIMI-v2-2011-BagciMKKT #adaptation #recognition #using

Object and Scene Recognition Using Color Descriptors and Adaptive Color KLT (VHB, MGM, RK, RK, VT), pp. 355–363.

HIMI-v2-2011-Otsuka #analysis #behaviour #comprehension #multimodal #people

Multimodal Conversation Scene Analysis for Understanding People’s Communicative Behaviors in Face-to-Face Meetings (KO), pp. 171–179.

ICML-2011-SocherLNM #natural language #network #parsing #recursion

Parsing Natural Scenes and Natural Language with Recursive Neural Networks (RS, CCYL, AYN, CDM), pp. 129–136.

SIGIR-2011-LiWLKP #named #personalisation #recommendation #scalability

SCENE: a scalable two-stage personalized news recommendation system (LL, DW, TL, DK, BP), pp. 125–134.

ICPR-2010-AkbasA #classification #image #low level #segmentation

Low-Level Image Segmentation Based Scene Classification (EA, NA), pp. 3623–3626.

ICPR-2010-CandamoGKG #detection #using

Detecting Wires in Cluttered Urban Scenes Using a Gaussian Model (JC, DBG, RK, SG), pp. 432–435.

ICPR-2010-ErgulA #classification #topic #using

Scene Classification Using Spatial Pyramid of Latent Topics (EE, NA), pp. 3603–3606.

ICPR-2010-FengZH #detection #learning #online #self

Online Learning with Self-Organizing Maps for Anomaly Detection in Crowd Scenes (JF, CZ, PH), pp. 3599–3602.

ICPR-2010-HaberdarS #detection #framework #mobile #refinement #using #video

Disparity Map Refinement for Video Based Scene Change Detection Using a Mobile Stereo Camera Platform (HH, SKS), pp. 3890–3893.

ICPR-2010-HanCR10a #concept #interactive #learning #recognition #semantics

Semi-supervised and Interactive Semantic Concept Learning for Scene Recognition (XHH, YWC, XR), pp. 3045–3048.

ICPR-2010-HanL #biology #classification #multi

A Hierarchical GIST Model Embedding Multiple Biological Feasibilities for Scene Classification (YH, GL), pp. 3109–3112.

ICPR-2010-Hotta #classification #using #visual notation #word

Scene Classification Using Local Co-occurrence Feature in Subspace Obtained by KPCA of Local Blob Visual Words (KH), pp. 4230–4233.

ICPR-2010-HuangM #automation #detection #locality #video

Automatic Detection and Localization of Natural Scene Text in Video (XH, HM), pp. 3216–3219.

ICPR-2010-Jean #analysis

Local Optical Operators for Subpixel Scene Analysis (YDJ), pp. 3448–3451.

ICPR-2010-JhuoL #kernel #learning #multi #recognition

Boosted Multiple Kernel Learning for Scene Category Recognition (IHJ, DTL), pp. 3504–3507.

ICPR-2010-JiangWXD #classification #image

A New Biologically Inspired Feature for Scene Image Classification (AJ, CW, BX, RD), pp. 758–761.

ICPR-2010-JoshiP #adaptation #detection #incremental #learning

Scene-Adaptive Human Detection with Incremental Active Learning (AJJ, FP), pp. 2760–2763.

ICPR-2010-KitaW #clustering #image #using

Binarization of Color Characters in Scene Images Using k-means Clustering and Support Vector Machines (KK, TW), pp. 3183–3186.

ICPR-2010-LeeCJK #constraints

Scene Text Extraction with Edge Constraint and Text Collinearity (SL, MSC, KJ, JHK), pp. 3983–3986.

ICPR-2010-LiuA #learning #semantics #using

Learning Scene Semantics Using Fiedler Embedding (JL, SA), pp. 3627–3630.

ICPR-2010-OhH #learning #process #using #video

Unsupervised Learning of Activities in Video Using Scene Context (SO, AH), pp. 3579–3582.

ICPR-2010-OzturkYA #detection

Detecting Dominant Motion Flows in Unstructured/Structured Crowd Scenes (OO, TY, KA), pp. 3533–3536.

ICPR-2010-ShiGW #detection #realtime

Real-Time Abnormal Event Detection in Complicated Scenes (YS, YG, RW), pp. 3653–3656.

ICPR-2010-Weinman #recognition

Typographical Features for Scene Text Recognition (JJW), pp. 3987–3990.

ICPR-2010-WidhalmB #learning

Learning Major Pedestrian Flows in Crowded Scenes (PW, NB), pp. 4064–4067.

ICPR-2010-ZhangJ #geometry #multi

Visibility of Multiple Cameras in a Scene with Unknown Geometry (LZ, YJ), pp. 3619–3622.

SIGIR-2010-YiLWR #using #video

Contextual video advertising system using scene information inferred from video scripts (BJY, JTL, HWW, HCR), pp. 771–772.

SAC-2010-HuangT #detection #semantics #specification

Semantic scene detection system for baseball videos based on the MPEG-7 specification (YFH, LHT), pp. 941–947.

ICDAR-2009-BhattacharyaPM #image

Devanagari and Bangla Text Extraction from Natural Scene Images (UB, SKP, SM), pp. 171–175.

ICDAR-2009-HanifP #algorithm #detection #image #locality #using

Text Detection and Localization in Complex Scene Images using Constrained AdaBoost Algorithm (SMH, LP), pp. 1–5.

ICDAR-2009-KimLK #mobile #using

Scene Text Extraction Using Focus of Mobile Camera (EK, SL, JHK), pp. 166–170.

ICDAR-2009-MaruyamaY #classification #image

Extraction of Characters on Signboards in Natural Scene Images by Stump Classifiers (MM, TY), pp. 1365–1369.

ICDAR-2009-PanHL #image #locality #random

Text Localization in Natural Scene Images Based on Conditional Random Field (YFP, XH, CLL), pp. 6–10.

ICML-2009-ChoS #analysis #learning #modelling

Learning dictionaries of stable autoregressive models for audio scene analysis (YC, LKS), pp. 169–176.

KEOD-2009-ReinekingSH #classification #ontology #statistics

Evidential Combination of Ontological and Statistical Information for Active Scene Classification (TR, NS, JH), pp. 72–79.

SAC-2009-ShaLW #classification #using #visual notation

Foreground classification using active template in the scene context for visual surveillance (XS, XL, JW), pp. 943–944.

SAC-2009-Zheng #framework #mobile

Scene map on wireless mobile platform (JYZ), pp. 217–218.

CHI-2008-KarrerWLB #interface #named #navigation #video

DRAGON: a direct manipulation interface for frame-accurate in-scene video navigation (TK, MW, EL, JOB), pp. 247–250.

ICPR-2008-HanifPN #detection #image

A cascade detector for text detection in natural scene images (SMH, LP, PN), pp. 1–4.

ICPR-2008-HuangST08a #approximate

Approximation of salient contours in cluttered scenes (RH, NS, QT), pp. 1–4.

ICPR-2008-HuAS08a #learning #using

Learning motion patterns in crowded scenes using motion flow field (MH, SA, MS), pp. 1–5.

ICPR-2008-HuWGW #interactive #video

An interactive scene annotation tool for video surveillance (WH, JW, HG, YW), pp. 1–4.

ICPR-2008-LablackD #analysis #behaviour

Analysis of human behaviour in front of a target scene (AL, CD), pp. 1–4.

ICPR-2008-MakiKSS #automation #detection #interactive

Image-based automatic detection of indoor scene events and interactive inquiry (KM, NK, NS, YS), pp. 1–4.

ICPR-2008-MaWHJG #effectiveness

Effective scene matching with local feature representatives (SM, WW, QH, SJ, WG), pp. 1–4.

ICPR-2008-MorrisT #adaptation #analysis #process #video

An adaptive scene description for activity analysis in surveillance video (BM, MMT), pp. 1–4.

ICPR-2008-PanBS #detection #image #representation #using

Text detection from scene images using sparse representation (WP, TDB, CYS), pp. 1–5.

ICPR-2008-SimonB #detection #estimation #geometry #multi #realtime

Detection of the intersection lines in multiplanar environments: Application to real-time estimation of the camera-scene geometry (GS, MOB), pp. 1–4.

ICPR-2008-SongT #classification

C1 units for scene classification (DS, DT), pp. 1–4.

ICPR-2008-TeoLCS #3d #constraints #recognition #robust

3D ordinal constraint in spatial configuration for robust scene recognition (CLT, SL, LFC, JS), pp. 1–5.

ICPR-2008-UkitaKK #using

IBR-based free-viewpoint imaging of a complex scene using few cameras (NU, SK, MK), pp. 1–4.

ICPR-2008-XuKB #adaptation #mobile

Information-based gaze control adaptation to scene context for mobile robots (TX, KK, MB), pp. 1–4.

ICPR-2008-YenCWWC #using #video

A scene-based video watermarking technique using SVMs (SHY, HWC, CJW, PSPW, MCC), pp. 1–4.

ICPR-2008-ZhangLHT #automation #classification

Boosting local feature descriptors for automatic objects classification in traffic scene surveillance (ZZ, ML, KH, TT), pp. 1–4.

ICPR-2008-ZhiC #image

Depth-based image mosaicing for both static and dynamic scenes (QZ, JRC), pp. 1–4.

SAC-2008-HanaFOB #classification

Crime scene classification (ROAH, COdAF, LSO, FB), pp. 419–423.

DATE-2007-Botti #challenge #embedded #industrial

Flying embedded: the industrial scene and challenges for embedded systems in aeronautics and space (JB), p. 1246.

ICDAR-2007-BeaufortM #fault #finite #framework

A Weighted Finite-State Framework for Correcting Errors in Natural Scene OCR (RB, CMT), pp. 889–893.

ICDAR-2007-WeinmanLH #performance #recognition

Fast Lexicon-Based Scene Text Recognition with Sparse Belief Propagation (JJW, EGLM, ARH), pp. 979–983.

AGTIVE-2007-AschenbrennerG #graph #graph grammar #using

Transforming Scene Graphs Using Triple Graph Grammars — A Practice Report (NA, LG), pp. 32–43.

HCI-IPT-2007-LiGR #artificial reality

Resolving Occlusion Between Virtual and Real Scenes for Augmented Reality Applications (LL, TG, BR), pp. 634–642.

CASE-2006-HuSHL #modelling #probability #using

Vision-based Indoor Scene Cognition Using a Spatial Probabilistic Modeling Method (JSH, TMS, HCH, PCL), pp. 620–625.

ICEIS-AIDSS-2006-GolfinopoulosSMP #declarative #design #knowledge-based #modelling

A Knowledge-Based Reverse Design System for Declarative Scene Modeling (VG, VMS, GM, DP), pp. 82–90.

ICPR-v1-2006-AndradeBF #detection #modelling

Modelling Crowd Scenes for Event Detection (ELA, SB, RBF), pp. 175–178.

ICPR-v1-2006-BoschMOM #approach #classification #question #what

Object and Scene Classification: what does a Supervised Approach Provide us? (AB, XM, AO, RM), pp. 773–777.

ICPR-v1-2006-CayouetteC #realtime

Generic Real-Time Tracking Method on Semi-Dynamic Scenes (FC, JRC), pp. 711–714.

ICPR-v1-2006-Fisher #distributed

Scene recovery from many randomly distributed single pixel cameras (RBF), pp. 988–991.

ICPR-v1-2006-HarasseBD #detection #people

Human model for people detection in dynamic scenes (SH, LB, MD), pp. 335–354.

ICPR-v1-2006-KaufholdCHR #classification #recognition #segmentation #using

Recognition and Segmentation of Scene Content using Region-Based Classification (JPK, RC, AH, PR), pp. 755–760.

ICPR-v2-2006-KimK06b #estimation #graph #modelling #monte carlo #multi #online

Multi-modal Sequential Monte Carlo for On-Line Hierarchical Graph Structure Estimation in Model-based Scene Interpretation (SK, ISK), pp. 251–254.

ICPR-v2-2006-LeL #hybrid

A Hybrid License Plate Extraction Method for Complex Scenes (WL, SL), pp. 324–327.

ICPR-v2-2006-LimCG #identification #using

Scene Identification using Discriminative Patterns (JHL, JPC, SG), pp. 642–645.

ICPR-v3-2006-KawabataHS #detection #realtime

Real-Time Detection of Anomalous Objects in Dynamic Scene (SK, SH, KS), pp. 1171–1174.

ICPR-v3-2006-LienH #multi

Multi-view-based Cooperative Tracking of Multiple Human Objects in Cluttered Scenes (KCL, CLH), pp. 1123–1126.

ICPR-v3-2006-TsaiSH #multi

Multiple Human Objects Tracking in Crowded Scenes (YTT, HCS, CLH), pp. 51–54.

ICPR-v3-2006-ZhangHT #clustering #comparison #metric #similarity

Comparison of Similarity Measures for Trajectory Clustering in Outdoor Surveillance Scenes (ZZ, KH, TT), pp. 1135–1138.

ICPR-v4-2006-AlnasserF

Image-Based Rendering of Synthetic Diffuse Objects in Natural Scenes (MA, HF), pp. 787–790.

ICPR-v4-2006-AndersenJM #estimation

Estimation of Dynamic Light Changes in Outdoor Scenes Without the use of Calibration Objects (MSA, TJ, CBM), pp. 91–94.

ICPR-v4-2006-ChenLL #using #video

Video Scene Extraction Using Mosaic Technique (LHC, YCL, HYML), pp. 723–726.

ICPR-v4-2006-KanbaraUKY #3d #image #re-engineering

3D Scene Reconstruction from Reflection Images in a Spherical Mirror (MK, NU, MK, NY), pp. 874–879.

ICPR-v4-2006-PeursumVW #linear

Observation-Switching Linear Dynamic Systems for Tracking Humans Through Unexpected Partial Occlusions by Scene Objects (PP, SV, GAWW), pp. 929–934.

ICPR-v4-2006-ShenC #segmentation

Finding Text in Natural Scenes by Figure-Ground Segmentation (HS, JMC), pp. 113–118.

ICPR-v4-2006-YangLPZZ #detection #learning

Active Learning Based Pedestrian Detection in Real Scenes (TY, JL, QP, CZ, YZ), pp. 904–907.

ICDAR-2005-KimPK #image #using

Text Locating from Natural Scene Images Using Image Intensitie (JSK, SCP, SHK), pp. 655–659.

ICDAR-2005-SaoiGK #clustering #detection #image #multi

Text Detection in Color Scene Images based on Unsupervised Clustering of Multi-channel Wavelet Features (TS, HG, HK), pp. 690–694.

ICDAR-2005-YokobayashiW #correlation #image #recognition #segmentation #using

Segmentation and Recognition of Characters in Scene Images Using Selective Binarization in Color Space and GAT Correlation (MY, TW), pp. 167–171.

ICSE-2005-TilevichS #refactoring

Binary refactoring: improving code behind the scenes (ET, YS), pp. 264–273.

ICPR-v1-2004-KusachiSIA #detection #image #recognition #robust

Kanji Recognition in Scene Images without Detection of Text Fields — Robust Against Variation of Viewpoint, Contrast, and Background Texture (YK, AS, NI, KA), pp. 457–460.

ICPR-v1-2004-LevesqueD

Sparse Scene Structure Recovery from Atmospheric Degradation (DL, FD), pp. 84–87.

ICPR-v1-2004-OnishiF #comprehension #evaluation #image #using #video

Shooting the Lecture Scene Using Computer-controlled Cameras Based on Situation Understanding and Evaluation of Video Images (MO, KF), pp. 781–784.

ICPR-v1-2004-TodorovicN #detection #image #using

Detection of Artificial Structures in Natural-Scene Images Using Dynamic Trees (ST, MCN), pp. 35–39.

ICPR-v2-2004-EzakiBS #detection #image #towards #visual notation

Text Detection from Natural Scene Images: Towards a System for Visually Impaired Persons (NE, MB, LS), pp. 683–686.

ICPR-v2-2004-Hammoud #visual notation

Color Texture Signatures for Art-Paintings vs. Scene-Photographs Based on Human Visual System (RIH), pp. 525–528.

ICPR-v2-2004-KimBSCCKC #image #using #verification

Scene Text Extraction in Natural Scene Images using Hierarchical Feature Combining and Verification (KCK, HRB, YJS, YWC, SYC, KKK, YC), pp. 679–682.

ICPR-v2-2004-LiYMKG #detection #realtime

A Real-Time Vehicle Detection and Tracking System in Outdoor Traffic Scenes (XL, XY, YLM, RK, GG), pp. 761–764.

ICPR-v2-2004-SerratosaGS #2d #distance

Distance between 2D-Scenes based on Oriented Matroid Theory (FS, AG, AS), pp. 196–199.

ICPR-v2-2004-YamaguchiM #classification #image

Character Extraction from Natural Scene Images by Hierarchical Classifiers (TY, MM), pp. 687–690.

ICPR-v3-2004-DouretB #3d #monitoring #multi

A Multi-Cameras 3D Volumetric Method for Outdoor Scenes : A Road Traffic Monitoring Application (JD, RB), pp. 334–337.

ICPR-v3-2004-EhtiatiC #architecture #identification

A Strongly Coupled Architecture for Contextual Object and Scene Identification (TE, JJC), pp. 69–72.

ICPR-v3-2004-HiguchiAKF #recognition

Scene Recognition Based on Relationship between Human Actions and Objects (MH, SA, AK, KF), pp. 73–78.

ICPR-v3-2004-Li04a #representation

Sky-Ground Representation for Local Scene Description (SL), pp. 252–255.

ICPR-v4-2004-HagaSY #analysis #detection #using

Human Detection in Outdoor Scene using Spatio-Temporal Motion Analysis (TH, KS, YY), pp. 331–334.

ICPR-v4-2004-KimPL #bound #using

Object Boundary Edge Selection Using Normal Direction Derivatives of a Contour in a Complex Scene (TYK, JP, SWL), pp. 755–758.

ICPR-v4-2004-OrWCI #re-engineering #scalability

Large Scene Reconstruction with Local Details Recovery (SHO, KhW, MMYC, CYI), pp. 44–47.

ICPR-v4-2004-WangJ #detection #multi

Multi-View Face Detection under Complex Scene based on Combined SVMs (PW, QJ), pp. 179–182.

RE-2004-ZachosM #multi #named

ART-SCENE: Enhancing Scenario Walkthroughs With Multi-Media Scenarios (KZ, NAMM), pp. 360–361.

AGTIVE-2003-Klempien-HinrichsMT #3d

Collage Grammars for Collision-Free Growing of Objects in 3D Scenes (RKH, TM, CvT), pp. 383–397.

CHI-2003-FussellSK #collaboration #physics #video

Effects of head-mounted and scene-oriented video systems on remote collaboration on physical tasks (SRF, LDS, REK), pp. 513–520.

ICEIS-v2-2003-HattoriKY #multi #pattern matching #pattern recognition #recognition

Face Pattern Recognition and Extraction From Multiple Persons Scene (TH, HK, TY), pp. 92–99.

ICPR-v2-2002-HeydenH #constraints

Auto-Calibration via the Absolute Quadric and Scene Constraints (AH, DQH), pp. 631–634.

ICPR-v2-2002-InamotoS #generative #multi

Intermediate View Generation of Soccer Scene from Multiple Videos (NI, HS), pp. 713–716.

ICPR-v2-2002-TruongVD

Neighborhood Coherence and Edge Based Approaches to Film Scene Extraction (BTT, SV, CD), pp. 350–353.

ICPR-v3-2002-BurschkaH #classification

Scene Classification from Dense Disparity Maps in Indoor Environments (DB, GDH), pp. 708–712.

ICPR-v3-2002-ForsterLR #realtime #using

Real-Time Range Imaging for Dynamic Scenes Using Colour-Edge Based Structured Light (FF, MKL, BR), pp. 645–648.

ICPR-v3-2002-HsiehYC #detection

Morphology-Based License Plate Detection from Complex Scenes (JWH, SHY, YSC), pp. 176–179.

ICPR-v3-2002-PeiC #adaptation #fault #novel #predict

Novel Error Concealment Method with Adaptive Prediction to the Abrupt and Gradual Scene Changes (SCP, YZC), pp. 827–830.

ICPR-v3-2002-RavindranF #linear

A Simple Linear Method to Obtain Height Ordering of Scene Points (PR, NJF), pp. 719–722.

ICPR-v3-2002-SatoKYT #3d #image #modelling #multi #sequence #using

3-D Modeling of an Outdoor Scene by Multi-Baseline Stereo Using a Long Sequence of Images (TS, MK, NY, HT), pp. 581–584.

ICPR-v3-2002-SinKC #image #using

Locating Characters in Scene Images Using Frequency Features (BKS, SKK, BJC), pp. 489–492.

ICPR-v3-2002-SunPKA #3d #mobile #re-engineering #using

3D Reconstruction of Indoor and Outdoor Scenes Using a Mobile Range Scanner (YS, JKP, AK, MAA), pp. 653–656.

ICPR-v3-2002-VinsonC #3d #multi #re-engineering #segmentation

Multiple Rectangle Model for Vuildings Segmentation and 3D Scene Reconstruction (SV, LDC), pp. 623–626.

ICPR-v3-2002-WeiHK02a #design

The Design of a Stereo Panorama Camera for Scenes of Dynamic Range (SKW, FH, RK), pp. 635–638.

ICPR-v3-2002-ZhangHHYW #approach #embedded #recognition #robust

A Robust Approach for Recognition of Text Embedded in Natural Scenes (JZ, XC, AH, JY, AW), pp. 204–207.

ICPR-v4-2002-BaltzakisAT #visual notation

Fusion of Range and Visual Data for the Extraction of Scene Structure Information (HB, AAA, PET), pp. 7–11.

ICPR-v4-2002-FrancoisMW #geometry #symmetry #using

Reconstructing Mirror Symmetric Scenes From a Single View Using 2-View Stereo Geometry (ARJF, GGM, RW), pp. 12–16.

ICPR-v4-2002-Sakaino #estimation #robust

Nonlinear Robust Velocity Estimation of Vehicles from a Snowfall Traffic Scene (HS), pp. 60–63.

ICPR-v4-2002-SerranoSL #approach #classification #performance

A Computationally Efficient Approach to Indoor/Outdoor Scene Classification (NS, AES, JL), p. 146–?.

ICDAR-2001-LiDW #automation #image

Automatic Text Location in Natural Scene Images (CL, XD, YW), pp. 1069–1073.

ICDAR-2001-WangDL #image #recognition

Character Extraction and Recognition in Natural Scene Images (XW, XD, CL), pp. 1084–1088.

ICDAR-2001-WangK #image #verification

Character-Like Region Verification for Extracting Text in Scene Images (HW, JK), pp. 957–963.

CHI-2001-DuhPF #independence #visual notation

An “independent visual background” reduced balance disturbance envoked by visual scene motion: implication for alleviating simulator sickness (HBLD, DEP, TAF), pp. 85–89.

ICPR-v1-2000-ChengDHT #detection #performance

Efficient Detection and Extraction of Color Objects from Complex Scenes (JC, SD, GH, JT), pp. 1668–1671.

ICPR-v1-2000-GandhiKA #segmentation

Application of Planar Motion Segmentation for Scene Text Extraction (TG, RK, SA), pp. 1445–1449.

ICPR-v1-2000-HeikkilaSS #estimation #segmentation #using

Camera Motion Estimation from Non-Stationary Scenes Using EM-Based Motion Segmentation (JH, PS, OS), pp. 1370–1374.

ICPR-v1-2000-KnightR #self

Self-Calibration of a Stereo Rig in a Planar Scene by Data Combination (JK, IDR), pp. 1411–1414.

ICPR-v1-2000-LourakisTAO #3d #constraints #geometry #using

Using Geometric Constraints for Matching Disparate Stereo Views of 3D Scenes Containing Planes (MIAL, SVT, AAA, SCO), pp. 1419–1422.

ICPR-v1-2000-MikicCKT #detection

Moving Shadow and Object Detection in Traffic Scenes (IM, PCC, GTK, MMT), pp. 1321–1324.

ICPR-v1-2000-NgoPCZ #detection #representation #video

Motion-Based Video Representation for Scene Change Detection (CWN, TCP, RTC, HZ), pp. 1827–1830.

ICPR-v1-2000-OuerhaniH #visual notation

Computing Visual Attention from Scene Depth (NO, HH), pp. 1375–1378.

ICPR-v1-2000-StevensB #comparison #image #refinement

Image Comparison Techniques in the Context of Scene Refinement (MRS, JRB), pp. 1685–1688.

ICPR-v1-2000-StevensB00a

Searching for Objects in a Scene (MRS, JRB), pp. 1730–1733.

ICPR-v2-2000-MugurelVW #incremental #learning #multi #on the #recognition

On the Incremental Learning and Recognition of the Pattern of Movement of Multiple Labeled Objects in Dynamic Scenes (ML, SV, GAWW), pp. 2652–2655.

ICPR-v3-2000-KimCL #detection #feature model #performance #using

Fast Scene Change Detection Using Direct Feature Extraction from MPEG Compressed Videos (YMK, SWC, SWL), pp. 3178–3181.

ICPR-v3-2000-ObertiR #adaptation #multi

Adaptive Tracking of Multiple Non Rigid Objects in Cluttered Scenes (FO, CSR), pp. 7108–7111.

ICPR-v4-2000-HaritaogluHD #maintenance #modelling #performance

A Fast Background Scene Modeling and Maintenance for Outdoor Surveillance (IH, DH, LSD), pp. 4179–4183.

ICPR-v4-2000-LinZ #automation #video

Automatic Video Scene Extraction by Shot Grouping (TL, HZ), pp. 4039–4042.

ICPR-v4-2000-PujolLVV #people

Locating People in Indoor Scenes for Real Applications (AP, FL, XV, JJV), pp. 4632–4635.

ICPR-v4-2000-SawakiMH #automation #image #recognition

Automatic Acquisition of Context-based Image Templates for Degraded Character Recognition in Scene Images (MS, HM, NH), pp. 4015–4018.

ICPR-v4-2000-ShimamuraTYY #image #modelling #using

Construction and Presentation of a Virtual Environment Using Panoramic Stereo Images of a Real Scene and Computer Graphics Models (JS, HT, NY, KY), pp. 4463–4467.

ICPR-v4-2000-TrivediBG #architecture #database

Database Architecture for Autonomous Transportation Agents for On-Scene Networked Incident Management (ATON) (MMT, SKB, AG), pp. 4664–4667.

CHI-1998-PlanteTI #interactive #using

Evaluating the Location of Hot Spots in Interactive Scenes Using the 3R Toolbox (AP, ST, SI), pp. 117–123.

ICML-1998-MaronR #classification #learning #multi

Multiple-Instance Learning for Natural Scene Classification (OM, ALR), pp. 341–349.

ICPR-1998-BaillardDM #segmentation

Segmentation of urban scenes from aerial stereo imagery (CB, OD, HM), pp. 1405–1407.

ICPR-1998-FanYG #comprehension #knowledge-based #named

KRUS: a knowledge-based road scene understanding system (CF, XY, WG), pp. 731–733.

ICPR-1998-GiacconeGJ #estimation #using

Creating virtual scenes using active contours and global motion estimation (PRG, DG, GAJ), pp. 1505–1507.

ICPR-1998-GuKTH #image #robust #using

Robust extraction of characters from color scene image using mathematical morphology (LG, TK, NT, RMH), pp. 1002–1004.

ICPR-1998-TerrillonDA #detection #image #invariant

Detection of human faces in complex scene images by use of a skin color model and of invariant Fourier-Mellin moments (JCT, MD, SA), pp. 1350–1355.

ICPR-1998-YoungKM #evolution #modelling #using

Hypothesis selection for scene interpretation using grammatical models of scene evolution (RCDY, JK, JM), pp. 1718–1720.

REFSQ-1998-HaumerPW #abstraction #concept #modelling

Abstraction Guides: Interrelating Conceptual Models with Real World Scenes (PH, KP, KW), pp. 23–32.

HCI-SEC-1997-BaconS #3d #representation

Hybridization of Classical Documentary Techniques and Techniques of Three Dimensional Representation in Space: Dynamical Constitution of Virtual Scenes (JB, XS), pp. 925–928.

ICPR-1996-AzencottDP #identification #multi #scalability

Multiscale identification of buildings in compressed large aerial scenes (RA, FD, JP), pp. 974–978.

ICPR-1996-BenosmanMD #multi #re-engineering

Multidirectional stereovision sensor, calibration and scenes reconstruction (RB, TM, JD), pp. 161–165.

ICPR-1996-HennebertRB #2d #approach #segmentation

A hierarchical approach for scene segmentation based on 2D motion (CH, VR, PB), pp. 218–222.

ICPR-1996-IraniA #2d #3d #approach #detection

A unified approach to moving object detection in 2D and 3D scenes (MI, PA), pp. 712–717.

ICPR-1996-KashinoH #analysis #integration #music

A music scene analysis system with the MRF-based information integration scheme (KK, NH), pp. 725–729.

ICPR-1996-Lemaire #nondeterminism #recognition

Use of a priori descriptions in a high-level language and management of the uncertainty in a scene recognition system (JL), pp. 560–564.

ICPR-1996-Maver #representation

Necessary views for a coarse representation of a scene (JM), pp. 936–940.

ICPR-1996-SeitzD #representation #towards #using

Toward image-based scene representation using view morphing (SMS, CRD), pp. 84–89.

ICPR-1996-SequeiraGR #3d #performance #re-engineering

Active view selection for efficient 3D scene reconstruction (VS, JGMG, MIR), pp. 815–819.

ICPR-1996-SilvaCS #3d #segmentation

3-D data acquisition and scene segmentation system (JAS, AJCC, JCMdS), pp. 563–567.

ICPR-1996-Sparr #image #re-engineering #sequence

Simultaneous reconstruction of scene structure and camera locations from uncalibrated image sequences (GS), pp. 328–333.

ICPR-1996-YangT #geometry #locality #mobile #modelling

Mobile robot localization by geometric hashing and model-based scene matching (YBY, HTT), pp. 181–185.

ICSE-1996-KoskimiesM #diagrams #named #object-oriented #source code #using

Scene: Using Scenario Diagrams and Active Text for Illustrating Object-Oriented Programs (KK, HM), pp. 366–375.

SEKE-1995-NourO #approach #information management #representation

An Approach Based on “Frames” for Knowledge Representation and Scenes Interpretation in a Robot-Vision System (MN, KO), pp. 275–282.