1. Home
  2. Proceedings
  3. WACV
  4. WACV 2014
Default Cover Image

2014 IEEE Winter Conference on Applications of Computer Vision (WACV)

March 24 2014 to March 26 2014

Steamboat Springs, CO, USA

Table of Contents

A discriminative parts based model approach for fiducial points free and shape constrained head pose normalisation in the wildFull-text access may be available. Sign in or learn about subscription options.pp. 1-2
by Abhinav Dhall, Karan Sikka, Gwen Littlewort, Roland Goecke, Marian Bartlett
Data-driven road detectionFull-text access may be available. Sign in or learn about subscription options.pp. 1134-1141
by Jose M. Alvarez, Mathieu Salzmann, Nick Barnes
Segmentation and tracking of partial planar templatesFull-text access may be available. Sign in or learn about subscription options.pp. 1128-1133
by Abdelsalam Masoud, William Hoff
Robust tracking and mapping with a handheld RGB-D cameraFull-text access may be available. Sign in or learn about subscription options.pp. 1120-1127
by Kyoung-Rok Lee, Truong Nguyen
Plant classification system for crop /weed discrimination without segmentationFull-text access may be available. Sign in or learn about subscription options.pp. 1142-1149
by Sebastian Haug, Andreas Michaels, Peter Biber, Jorn Ostermann
Scale-Space SIFT flowFull-text access may be available. Sign in or learn about subscription options.pp. 1112-1119
by Weichao Qiu, Xinggang Wang, Xiang Bai, Alan Yuille, Zhuowen Tu
A lp-norm MTMKL framework for simultaneous detection of multiple facial action unitsFull-text access may be available. Sign in or learn about subscription options.pp. 1104-1111
by Xiao Zhang, Mohammad H. Mahoor, S. Mohammad Mavadati, Jeffrey F. Cohn
Fully automatic 3D facial expression recognition using local depth featuresFull-text access may be available. Sign in or learn about subscription options.pp. 1096-1103
by Mingliang Xue, Ajmal Mian, Wanquan Liu, Ling Li
Relative facial action unit detectionFull-text access may be available. Sign in or learn about subscription options.pp. 1090-1095
by Mahmoud Khademi, Louis-Philippe Morency
A novel method for post-surgery face recognition using sum of facial parts recognitionFull-text access may be available. Sign in or learn about subscription options.pp. 1082-1089
by Ranran Feng, Balakrishnan Prabhakaran
Matching image sets via adaptive multi convex hullFull-text access may be available. Sign in or learn about subscription options.pp. 1074-1081
by Shaokang Chen, Arnold Wiliem, Conrad Sanderson, Brian C. Lovell
Simultaneous recognition of facial expression and identity via sparse representationFull-text access may be available. Sign in or learn about subscription options.pp. 1066-1073
by Mohammad Reza Mohammadi, Emad Fatemizadeh, Mohammad H. Mahoor
Predicting movie ratings from audience behaviorsFull-text access may be available. Sign in or learn about subscription options.pp. 1058-1065
by Rajitha Navarathna, Patrick Lucey, Peter Carr, Elizabeth Carter, Sridha Sridharan, Iain Matthews
AutoCaption: Automatic caption generation for personal photosFull-text access may be available. Sign in or learn about subscription options.pp. 1050-1057
by Krishnan Ramnath, Simon Baker, Lucy Vanderwende, Motaz El-Saban, Sudipta N. Sinha, Anitha Kannan, Noran Hassan, Michel Galley, Yi Yang, Deva Ramanan, Alessandro Bergamo, Lorenzo Torresani
Exploring the geo-dependence of human face appearanceFull-text access may be available. Sign in or learn about subscription options.pp. 1042-1049
by Mohammad T. Islam, Scott Workman, Hui Wu, Nathan Jacobs, Richard Souvenir
Improving multiview face detection with multi-task deep convolutional neural networksFull-text access may be available. Sign in or learn about subscription options.pp. 1036-1041
by Cha Zhang, Zhengyou Zhang
A discriminative parts based model approach for fiducial points free and shape constrained head pose normalisation in the wildFull-text access may be available. Sign in or learn about subscription options.pp. 1028-1035
by Abhinav Dhall, Karan Sikka, Gwen Littlewort, Roland Goecke, Marian Bartlett
The effectiveness of face detection algorithms in unconstrained crowd scenesFull-text access may be available. Sign in or learn about subscription options.pp. 1020-1027
by Jeremiah R. Barr, Kevin W. Bowyer, Patrick J. Flynn
Extending explicit shape regression with mixed feature channels and pose priorsFull-text access may be available. Sign in or learn about subscription options.pp. 1013-1019
by Matthias Richter, Hua Gao, Hazim Kemal Ekenel
Comparison of face detection and image classification for detecting front seat passengers in vehiclesFull-text access may be available. Sign in or learn about subscription options.pp. 1006-1012
by Yusuf Artan, Peter Paul, Florent Perronin, Aaron Burry
Writer identification and verification using GMM supervectorsFull-text access may be available. Sign in or learn about subscription options.pp. 998-1005
by Vincent Christlein, David Bernecker, Florian Honig, Elli Angelopoulou
Finger-knuckle-print verification based on vector consistency of corresponding interest pointsFull-text access may be available. Sign in or learn about subscription options.pp. 992-997
by Min-Ki Kim, Patrick J. Flynn
Adaptive representations for video-based face recognition across poseFull-text access may be available. Sign in or learn about subscription options.pp. 984-991
by Yi-Chen Chen, Vishal M. Patel, Rama Chellappa, P. Jonathon Phillips
Iris crypts: Multi-scale detection and shape-based matchingFull-text access may be available. Sign in or learn about subscription options.pp. 977-983
by Feng Shen, Patrick J. Flynn
Active Clustering with Ensembles for Social structure extractionFull-text access may be available. Sign in or learn about subscription options.pp. 969-976
by Jeremiah R. Barr, Leonardo A. Cament, Kevin W. Bowyer, Patrick J. Flynn
Estimating cloudmaps from outdoor image sequencesFull-text access may be available. Sign in or learn about subscription options.pp. 961-968
by Nathan Jacobs, Joshua King, Daniel Bowers, Richard Souvenir
Repeated constrained sparse coding with partial dictionaries for hyperspectral unmixingFull-text access may be available. Sign in or learn about subscription options.pp. 953-960
by Naveed Akhtar, Faisal Sahfait, Ajmal Mian
Ant tracking with occlusion tunnelsFull-text access may be available. Sign in or learn about subscription options.pp. 947-952
by Thomas Fasciano, Anna Dornhaus, Min C. Shin
Data association based ant tracking with interactive error correctionFull-text access may be available. Sign in or learn about subscription options.pp. 941-946
by Hoan Nguyen, Thomas Fasciano, Daniel Charbonneau, Anna Dornhaus, Min C. Shin
Materials discovery: Fine-grained classification of X-ray scattering imagesFull-text access may be available. Sign in or learn about subscription options.pp. 933-940
by M. Hadi Kiapour, Kevin Yager, Alexander C. Berg, Tamara L. Berg
Spatial inference for coherent geophysical fluids by appearance and geometryFull-text access may be available. Sign in or learn about subscription options.pp. 925-932
by Sai Ravela
Rotation estimation from cloud trackingFull-text access may be available. Sign in or learn about subscription options.pp. 917-924
by Sangwoo Cho, Enrique Dunn, Jan-Michael Frahm
Determining underwater vehicle movement from sonar data in relatively featureless seafloor tracking missionsFull-text access may be available. Sign in or learn about subscription options.pp. 909-916
by Anthony Spears, Ayanna M. Howard, Michael West, Thomas Collins
Object tracking via non-Euclidean geometry: A Grassmann approachFull-text access may be available. Sign in or learn about subscription options.pp. 901-908
by Sareh Shirazi, Mehrtash T. Harandi, Brian C. Lovell, Conrad Sanderson
Information theoretic sensor management for multi-target tracking with a single pan-tilt-zoom cameraFull-text access may be available. Sign in or learn about subscription options.pp. 893-900
by Pietro Salvagnini, Federico Pernici, Marco Cristani, Giuseppe Lisanti, Iacopo Masi, Alberto Del Bimbo, Vittorio Murino
Urban Tracker: Multiple object tracking in urban mixed trafficFull-text access may be available. Sign in or learn about subscription options.pp. 885-892
by Jean-Philippe Jodoin, Guillaume-Alexandre Bilodeau, Nicolas Saunier
Structure-aware keypoint tracking for partial occlusion handlingFull-text access may be available. Sign in or learn about subscription options.pp. 877-884
by Wassim Bouachir, Guillaume-Alexandre Bilodeau
Automatic tracker selection w.r.t object detection performanceFull-text access may be available. Sign in or learn about subscription options.pp. 870-876
by Duc Phu Chau, Francois Bremond, Monique Thonnat
Consensus-based matching and tracking of keypoints for object trackingFull-text access may be available. Sign in or learn about subscription options.pp. 862-869
by Georg Nebehay, Roman Pflugfelder
Online discriminative dictionary learning for visual trackingFull-text access may be available. Sign in or learn about subscription options.pp. 854-861
by Fan Yang, Zhuolin Jiang, Larry S. Davis
Robust tracking of articulated human movements through Component-Based Multiple Instance Learning with particle filteringFull-text access may be available. Sign in or learn about subscription options.pp. 847-853
by Kyuseo Han, Johnny Park, Avinash C. Kak
Real-time multi-target tracking at 210 megapixels/second in Wide Area Motion ImageryFull-text access may be available. Sign in or learn about subscription options.pp. 839-846
by Arslan Basharat, Matt Turek, Yiliang Xu, Chuck Atkins, David Stoup, Keith Fieldhouse, Paul Tunison, Anthony Hoogs
Video segmentation with joint object and trajectory labelingFull-text access may be available. Sign in or learn about subscription options.pp. 831-838
by Michael Ying Yang, Bodo Rosenhahn
A fully implicit alternating direction method of multipliers for the minimization of convex problems with an application to motion segmentationFull-text access may be available. Sign in or learn about subscription options.pp. 823-830
by Karin Tichmann, Oliver Junge
Linear regression motion analysis for unsupervised temporal segmentation of human actionsFull-text access may be available. Sign in or learn about subscription options.pp. 816-822
by Simon Jones, Ling Shao
Video alignment to a common referenceFull-text access may be available. Sign in or learn about subscription options.pp. 808-815
by Rahul Dutta, Bruce Draper, J. Ross Beveridge
Combining semantic scene priors and haze removal for single image depth estimationFull-text access may be available. Sign in or learn about subscription options.pp. 800-807
by Ke Wang, Enrique Dunn, Joseph Tighe, Jan-Michael Frahm
Robust optical flow estimation for continuous blurred scenes using RGB-motion imaging and directional filteringFull-text access may be available. Sign in or learn about subscription options.pp. 792-799
by Wenbin Li, Yang Chen, JeeHang Lee, Gang Ren, Darren Cosker
Interactive video segmentation using occlusion boundaries and temporally coherent superpixelsFull-text access may be available. Sign in or learn about subscription options.pp. 784-791
by Radu Dondera, Vlad Morariu, Yulu Wang, Larry Davis
Video text detection and recognition: Dataset and benchmarkFull-text access may be available. Sign in or learn about subscription options.pp. 776-783
by Phuc Xuan Nguyen, Kai Wang, Serge Belongie
Summarisation of short-term and long-term videos using texture and colourFull-text access may be available. Sign in or learn about subscription options.pp. 769-775
by Johanna Carvajal, Chris McCool, Conrad Sanderson
Exploring context information for inter-camera multiple target trackingFull-text access may be available. Sign in or learn about subscription options.pp. 761-768
by Yinghao Cai, Gerard Medioni
Smart surveillance framework: A versatile tool for video analysisFull-text access may be available. Sign in or learn about subscription options.pp. 753-760
by Antonio C. Nazare, Cassio E. dos Santos, Renato Ferreira, William Robson Schwartz
Multi class boosted random ferns for adapting a generic object detector to a specific videoFull-text access may be available. Sign in or learn about subscription options.pp. 745-752
by Pramod Sharma, Ramakant Nevatia
Joint semantic and geometric segmentation of videos with a stage modelFull-text access may be available. Sign in or learn about subscription options.pp. 737-744
by Buyu Liu, Xuming He, Stephen Gould
Image parsing with graph grammars and Markov Random Fields applied to facade analysisFull-text access may be available. Sign in or learn about subscription options.pp. 729-736
by Mateusz Kozinski, Renaud Marlet
Object co-labeling in multiple imagesFull-text access may be available. Sign in or learn about subscription options.pp. 721-728
by Xi Chen, Arpit Jain, Larry S. Davis
Introspective semantic segmentationFull-text access may be available. Sign in or learn about subscription options.pp. 714-720
by Gautam Singh, Jana Kosecka
Scene recognition by jointly modeling latent topicsFull-text access may be available. Sign in or learn about subscription options.pp. 706-713
by Shaohua Wan, J.K. Aggarwal
Unsupervised Non-parametric Geospatial Modeling from Ground ImageryFull-text access may be available. Sign in or learn about subscription options.pp. 698-705
by Nathan Frey, Antonio Torralba, Christopher Stauffer
Understanding the 3D layout of a cluttered room from multiple imagesFull-text access may be available. Sign in or learn about subscription options.pp. 690-697
by Sid Yingze Bao, Axel Furlan, Li Fei-Fei, Silvio Savarese
Task-based control of articulated human pose detection for OpenVLFull-text access may be available. Sign in or learn about subscription options.pp. 682-689
by Georgii Oleinikov, Gregor Miller, James J. Little, Sidney Fels
Understanding and analyzing a large collection of archived swimming videosFull-text access may be available. Sign in or learn about subscription options.pp. 674-681
by Long Sha, Patrick Lucey, Sridha Sridharan, Stuart Morgan, Dave Pease
Pedestrian detection in low resolution videosFull-text access may be available. Sign in or learn about subscription options.pp. 668-673
by Hisham Sager, William Hoff
Real-time 3-D face tracking and modeling framework for mid-res camFull-text access may be available. Sign in or learn about subscription options.pp. 660-667
by Jongmoo Choi, Anh Tran, Yann Dumortier, Gerard Medioni
Play type recognition in real-world football videoFull-text access may be available. Sign in or learn about subscription options.pp. 652-659
by Sheng Chen, Zhongyuan Feng, Qingkai Lu, Behrooz Mahasseni, Trevor Fiez, Alan Fern, Sinisa Todorovic
“Important stuff, everywhere!” Activity recognition with salient proto-objects as contextFull-text access may be available. Sign in or learn about subscription options.pp. 646-651
by Lukas Rybok, Boris Schauerte, Ziad Al-Halah, Rainer Stiefelhagen
A combination of generative and discriminative models for fast unsupervised activity recognition from traffic scene videosFull-text access may be available. Sign in or learn about subscription options.pp. 640-645
by Mahesh Venkata Krishna, Joachim Denzler
Mining discriminative 3D Poselet for cross-view action recognitionFull-text access may be available. Sign in or learn about subscription options.pp. 634-639
by Jiang Wang, Xiaohan Nie, Yin Xia, Ying Wu
Real time action recognition using histograms of depth gradients and random decision forestsFull-text access may be available. Sign in or learn about subscription options.pp. 626-633
by Hossein Rahmani, Arif Mahmood, Du Q. Huynh, Ajmal Mian
Coupling video segmentation and action recognitionFull-text access may be available. Sign in or learn about subscription options.pp. 618-625
by Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars
Action in chains: A chains model for action localization and classificationFull-text access may be available. Sign in or learn about subscription options.pp. 610-617
by Gilad Sharir, Tinne Tuytelaars
Multi-view action recognition one camera at a timeFull-text access may be available. Sign in or learn about subscription options.pp. 604-609
by Scott Spurlock, Richard Souvenir
A joint perspective towards image super-resolution: Unifying external- and self-examplesFull-text access may be available. Sign in or learn about subscription options.pp. 596-603
by Zhangyang Wang, Zhaowen Wang, Shiyu Chang, Jianchao Yang, Thomas Huang
Bayesian Optimization with an Empirical Hardness Model for approximate Nearest Neighbour SearchFull-text access may be available. Sign in or learn about subscription options.pp. 588-595
by Julieta Martinez, James J. Little, Nando de Freitas
Max residual classifierFull-text access may be available. Sign in or learn about subscription options.pp. 580-587
by Hien V. Nguyen, Vishal M. Patel
Unsupervised iterative manifold alignment via local feature histogramsFull-text access may be available. Sign in or learn about subscription options.pp. 572-579
by Ke Fan, Ajmal Mian, Wanquan Liu, Lin Li
Composite Discriminant Factor analysisFull-text access may be available. Sign in or learn about subscription options.pp. 564-571
by Vlad I. Morariu, Ejaz Ahmed, Venkataraman Santhanam, David Harwood, Larry S. Davis
Multimodal fusion using dynamic hybrid modelsFull-text access may be available. Sign in or learn about subscription options.pp. 556-563
by Mohamed R. Amer, Behjat Siddiquie, Saad Khan, Ajay Divakaran, Harpreet Sawhney
Unsupervised dictionary learning with double-layer sparse representationFull-text access may be available. Sign in or learn about subscription options.pp. 548-555
by Mai Xu, Zulin Wang
Is my new tracker really better than yours?Full-text access may be available. Sign in or learn about subscription options.pp. 540-547
by Luka Cehovin, Matej Kristan, Ales Leonardis
Benchmarking large-scale Fine-Grained CategorizationFull-text access may be available. Sign in or learn about subscription options.pp. 532-539
by Anelia Angelova, Philip M. Long
Small Hand-held Object Recognition Test (SHORT)Full-text access may be available. Sign in or learn about subscription options.pp. 524-531
by Jose Rivera-Rubio, Saad Idrees, Ioannis Alexiou, Lucas Hadjilucas, Anil A. Bharath
Image segmentation of mesenchymal stem cells in diverse culturing conditionsFull-text access may be available. Sign in or learn about subscription options.pp. 516-523
by Muhammad Jamal Afridi, Chun Liu, Christina Chan, Seungik Baek, Xiaoming Liu
Improving background subtraction using Local Binary Similarity PatternsFull-text access may be available. Sign in or learn about subscription options.pp. 509-515
by Pierre-Luc St-Charles, Guillaume-Alexandre Bilodeau
Large-scale semantic co-labeling of image setsFull-text access may be available. Sign in or learn about subscription options.pp. 501-508
by Jose M. Alvarez, Mathieu Salzmann, Nick Barnes
Scale-invariant line descriptors for wide baseline matchingFull-text access may be available. Sign in or learn about subscription options.pp. 493-500
by Bart Verhagen, Radu Timofte, Luc Van Gool
Multiple foreground recognition and cosegmentation: An object-oriented CRF model with robust higher-order potentialsFull-text access may be available. Sign in or learn about subscription options.pp. 485-492
by Hongyuan Zhu, Jiangbo Lu, Jianfei Cai, Jianming Zheng, Nadia M. Thalmann
Improving streaming video segmentation with early and mid-level visual processingFull-text access may be available. Sign in or learn about subscription options.pp. 477-484
by Subarna Tripathi, Youngbae Hwang, Serge Belongie, Truong Nguyen
Hierarchical representation of videos with spatio-temporal fibersFull-text access may be available. Sign in or learn about subscription options.pp. 469-476
by Ratnesh Kumar, Guillaume Charpiat, Monique Thonnat
Efficient dense subspace clusteringFull-text access may be available. Sign in or learn about subscription options.pp. 461-468
by Pan Ji, Mathieu Salzmann, Hongdong Li
Viewpoint-independent book spine segmentationFull-text access may be available. Sign in or learn about subscription options.pp. 453-460
by Lior Talker, Yael Moses
Multi-leaf alignment from fluorescence plant imagesFull-text access may be available. Sign in or learn about subscription options.pp. 437-444
by Xi Yin, Xiaoming Liu, Jin Chen, David M. Kramer
Age group classification via structured fusion of uncertainty-driven shape features and selected surface featuresFull-text access may be available. Sign in or learn about subscription options.pp. 445-452
by Kuan-Hsien Liu, Shuicheng Yan, C.-C. Jay Kuo
Integrating visual words as bunch of n-grams for effective biomedical image classificationFull-text access may be available. Sign in or learn about subscription options.pp. 431-436
by Glauco V. Pedrosa, Md Mahmudur Rahman, Sameer K. Antani, Dina Demner-Fushman, L. Rodney Long, Agma J. M. Traina
A CRF approach to fitting a generalized hand skeleton modelFull-text access may be available. Sign in or learn about subscription options.pp. 409-416
by Radu Paul Mihail, Gustav Blomquist, Nathan Jacobs
Discovering discriminative cell attributes for HEp-2 specimen image classificationFull-text access may be available. Sign in or learn about subscription options.pp. 423-430
by Arnold Wiliem, Peter Hobson, Brian C. Lovell
Automatic 3D change detection for glaucoma diagnosisFull-text access may be available. Sign in or learn about subscription options.pp. 401-408
by Lu Wang, Vinutha Kallem, Mayank Bansal, Jayan Eledath, Harpreet Sawhney, Denise J. Pearson, Richard A. Stone
Linear Local Distance coding for classification of HEp-2 staining patternsFull-text access may be available. Sign in or learn about subscription options.pp. 393-400
by Xiang Xu, Feng Lin, Carol Ng, Khai Pang Leong
Video segmentation and feature co-occurrences for activity classificationFull-text access may be available. Sign in or learn about subscription options.pp. 385-392
by Remi Trichet, Ramakant Nevatia
Showing 100 out of 153
Load More
Load All