Available Papers from the USC Computer Vision Group 1970-Present

The papers are grouped by year, within each of the yearly groups papers are arranged with journal papers first then conference papers. The easiest way to search for an author or word in the title is using your browser search. Our you can select the year or scroll through the entire listing. The sublisting under the research topics may not be as complete or up to date.

Available Papers for 2013

Journal Papers
Multiple Target Tracking by Learning-Based Hierarchical Association of Detection Responses Chang Huang, Yuan Li, Ram Nevatia PAMI, Vol. 35, No. 4, April 2013, pp. 898-910. Publisher Link
Hierarchy of nonlocal means for preferred automatic sharpness enhancement and tone mapping Anustup Choudhury and Gérard Medioni, JOSA-A, Vol. 30, No. 3, March 2013, pp. 353-366. Publisher Link

Conference Papers
Large-scale Web Video Event Classification by use of Fisher Vectors Chen Sun and Ram Nevatia WACV 2013, pp. 15-22 Publisher Link
Towards a Practical PTZ Face Detection and Tracking System Yinghao Cai, Gérard Medioni, and Thang Ba Dinh WACV 2013, pp. 31-38 Publisher Link

Available Papers for 2012

Journal Papers
A framework for robust online video contrast enhancement using modularity optimization Anustup Choudhury Gérard Medioni, IEEE Cir. Sys, Video Tech, September 2012, ppl 1266-1279 IEEE Reference
A Closed-Form Solution to Tensor Voting: Theory and Applications Tai-Pang Wu, Sai-Kit Yeung, Jia-Ya Jia, Chi-Keung Tang, Gérard Medioni, PAMI Volume 34, No. 8, August 2012, pp. 1482-1495. PAMI Reference

Reports
Activity Recognition in Wide Aerial Video Surveillance Using Entity Relationship Models Jongmoo Choi, Yann Dumortier, Jan Prokaj, and Gérard Medioni, USC Technical Report, February 2012

Conference Papers
Robust Object Tracking Using Constellation Model with Superpixel Weijun Wang and Ram Nevatia ACCV 2012
Pairwise Threshold for Gaussian Mixture Classification and Its Application on Human Tracking Enhancement Daegeon Kim and Sung Chun Lee, AVSS12, pp. 368-372
Accurate Full Body Scanning from a Single Fixed 3D Camera Ruizhe Wang, Jong-Moo Choi, Gérard Medioni, 3DIMPVT 2012, pp. 432-439. IEEE Source
Efficient Incremental Learning of Boosted Classifiers for Object Detection Pramod Sharma, Chang Huang Ram Nevatia ICPR 2012
Real-time staircase detection from a wearable stereo system Young Hoon Lee, Tung-Sing Leung, and Gérard Medioni, ICPR 2012
Pose based Activity Recognition using Multiple Kernel Learning Prithviraj Banerjee, Ram Nevatia ICPR 2012
Online Learned Discriminative Part-Based Appearance Models for Multi-Human Tracking Bo Yang Ram Nevatia ECCV 2012, pp. Vol I, 315484-498. Springer Source
Tracking Using Motion Patterns for Very Crowded Scenes Xuemei Zhao, Dian Gong, Gérard Medioni, ECCV 2012, pp. Vol II, 315-328. Springer Source
Kernelized Temporal Cut for Online Temporal Segmentation and Recognition Dian Gong Gérard Medioni, Sikai Zhu, Xuemei Zhao ECCV 2012, pp. Vol III, 229-243. Springer Source
Laser Scan Quality 3-D Face Modeling Using a Low-Cost Depth Camera M. Hernandez, J. Choi and Gérard Medioni, EUSIPCO 2012, pp. 1995-1999. August 27-31, 2012,
Activity Recognition in Wide Aerial Video Surveillance Using Entity Relationship Models Jongmoo Choi, Yann Dumortier, Jan Prokaj and Gérard Medioni, ICMR 2012
Accurate Full Body Scanning from a Single Fixed 3D Camera Ruizhe Wang, Jongmoo Choi and Gérard Medioni, 3DimPVT 2012
Multi-Target Tracking by Online Learning of Non-linear Motion Patterns and Robust Appearance Models Bo Yang, and Ram Nevatia CVPR 2012
An Online Learned CRF Model for Multi-Target Tracking Bo Yang, and Ram Nevatia CVPR 2012
Unsupervised Incremental Learning for Improved Object Detection in a Video Pramod Sharma, Chang Huang, and Ram Nevatia CVPR 2012
Probabilistic tensor voting for robust perceptual grouping Dian Gong, and Gérard Medioni, POCV 2012, IEEE Reference
Tracking many vehicles in wide area aerial surveillance Jan Prokaj, Xuemei Zhao, and Gérard Medioni, CNWASA 2012, pp. 37-43. IEEE Reference
Robust Multiple Manifold Structure Learning Dian Gong, Xuemei Zhao and Gérard Medioni, 29th International Conference on Machine Learning (ICML 2012), Edinburgh, Scotland
Accurate Efficient Mosaicking for Wide Area Aerial Surveillance Jan Prokaj, and Gérard Medioni, WACV 2012, pp. 273-280.
Real-time 3-D face tracking and modeling from a webcam Jong-Moo Choi, Yann Dumortier, Sang-Il Choi, Muhammad Bilal Ahmad Gérard Medioni, WACV 2012, pp. 33-40. IEEE Reference
Simultaneous inference of activity, pose and object Furqan M. Khan, Vivek Kumar Singh, Ram Nevatia WACV 2012, pp. 281-288. IEEE Reference

Available Papers for 2011

Journal Papers
Simultaneous tracking and action recognition for single actor human actions Vivek Kumar Singh Ram Nevatia VisualComputer, Vol. 27, No. 12, December 2011, pp. 1115-1123.
Segmentation of Objects in a Detection Window by Nonparametric Inhomogeneous CRFs. Bo Yang, Chang Huang, Ram Nevatia CVIU, Vol. 115, No. 11, pp. 1473-1482, Nov. 2011.
Urban Scene Understanding from aerial and ground LIDAR data Eunyoung Kim, Gérard Medioni, MVA Vol. 22, No. 4, July 2011, pp. 691-703.
User interactive multiple aerial view analysis for reconstructing a large number of 3D architectural models Sung Chun Lee, Ram Nevatia ISPRS Photogrammetry and Remote Sensing, Vol. 66, No. 4, July 2011, pp. 446-462.
Efficient detection and tracking of moving objects in geo-coordinates Yuping Lin, Qian Yu, Gérard Medioni MVA, Vol. 22, No. 3, May 2011, pp. 505-520.

Conference Papers
Action Recognition in Cluttered Dynamic Scenes using Pose-Specific Part Models Vivek Kumar Singh Ram Nevatia ICCV 2011,
Dynamic Manifold Warping for View Invariant Action Recognition Dian Gong Gérard Medioni ICCV 2011, pp. 571-578.
Robust Unsupervised Motion Pattern Inference from Video and Applications Xuemei Zhao Gérard Medioni ICCV 2011, pp. 715-722.
Aerial 3D Reconstruction with Line-Constrained Dynamic Programming Huei-Hung Liao, Yuping Lin, Gérard Medioni ICCV 2011, pp. 1855-1862.
Perceptually Motivated Automatic Sharpness Enhancement Using Hierarchy of Non-Local Means Anustup Choudhury Gérard Medioni CPCV 2011, pp. 730-737. (ICCV Workshop)
Learning neighborhood cooccurrence statistics of sparse features for human activity recognition Prithviraj Banerjee, Ram Nevatia AVSS 2011, pp. 212-217.
A systems level approach to perimeter protection Peter Tu, Ting Yu, Dashan Gao, Ram Nevatia Sung Chun Lee, Hale Kim, Phill Kyu Rhee, Joong-Hwan Baek, AVSS 2011, pp. 517-518. Demo Session.
Learning Affinities and Dependencies for Multi-Target Tracking using a CRF Model Bo Yang, Chang Huang, Ram Nevatia CVPR, 2011, pp. 1233-1240
Using 3D Scene Structure to Improve Tracking Jan Prokaj and Gérard Medioni CVPR, 2011, pp. 1337-1344.
How does Person Identity Recognition Help Multi-Person Tracking? Cheng-Hao Kuo, Ram Nevatia CVPR 2011, pp. 1217-1224.
Context Tracker: Exploring Supporters and Distracters in Unconstrained Environments T. B. Dinh, N. Vo, and Gérard Medioni CVPR 2011, pp. 1177-1184
Inferring Tracklets for Multi-Object Tracking Jan Prokaj, Mark Duchaineau, Gérard Medioni WAVP, pp. 37-44, 2011. (CVPR Workshop)
Robust camera calibration tool for video surveillance camera in urban environment Sung Chun Lee, Ram Nevatia Camera Networks, 2011, pp. 26-27. (CVPR Workshop)
A RGB-D camera Based Navigation for the Visually Impaired Young Hoon Lee, Gérard Medioni, Advanced Reasoning with Depth Camera Workshop. (CVPR Workshop)
High Resolution Face Sequences from a PTZ Network Camera Thang Ba Dinh, Nam Vo Gérard Medioni Face and Gesture, 2011, pp. 531-538.
3D Object Recognition in Depth Images using Visibility Context Eunyoung Kim and Gérard Medioni, IROS2011
Scalable Object Classification in Range Images Eunyoung Kim and Gérard Medioni, 3DIMPVT 2011
Vehicle detection from low quality aerial LIDAR data Bo Yang, Pramod Sharma, Ram Nevatia WACV, 2011, pp. 541-548
Co-training framework of generative and discriminative trackers with partial occlusion handling Thang Ba Dinh, Gérard Medioni WMVC, 2011, pp. 642-649

Available Papers for 2010

Journal Papers
Perceptually Motivated Automatic Color Contrast Enhancement Based on Color Constancy Estimation Anustup Choudhury, Gérard Medioni JIVP, 2010, No. 2010, pp. xx-yy.
Robust, Real-Time 3D Face Tracking from a Monocular View Wei-Kai Liao, Douglas Fidaleo, Gérard Medioni JIVP, 2010, No. 2010, pp. xx-yy.
Registration of 2D Points Using Geometric Algebra and Tensor Voting Leo Reyes-Lozano, Gérard Medioni, Eduardo Bayro-Carrochano JMIV, Vol. 37, No. 3, July 2010, pp. 249-266.

Conference Papers
Dynamics Based Trajectory Segmentation for UAV videos Prithviraj Banerjee, Ram Nevatia AVSS 2010, pp. 345-352
Inter-camera Association of Multi-target Tracks by On-Line Learned Appearance Affinity Models Cheng-Hao Kuo, Chang Huang, Ram Nevatia ECCV 2010, Vol I: pp. 383-396
Efficient Inference with Multiple Heterogeneous Part Detectors for Human Pose Estimation Vivek Kumar Singh, Ram Nevatia and Chang Huang ECCV 2010, Vol II: pp. 314-327
Dense Structure Inference for Object Classification in Aerial LIDAR Dataset Eunyoung Kim, Gérard Medioni, ICPR 2010, pp. 3049-3052
Color Constancy Using Standard Deviation of Color Channels Anustup Choudhury, Gérard Medioni ICPR 2010, pp. 1722-1726
3D Face Reconstruction Using a Single or Multiple Views Jong-Moo Choi, Gérard Medioni, Yu-Ping Lin, Luciano Silva, Olga Regina, Mauricio Pamplona, Timothy C. Faltemier, ICPR 2010, pp. 3959-3962
High performance object detection by collaborative learning of Joint Ranking of Granules features Chang Huang, Ram Nevatia CVPR 2010, pp. 41-48
Human Action Recognition Using a Dynamic Bayesian Action Network with 2D Part Models Vivek Kumar Singh, Ram Nevatia ICCVGIP 2010, pp. 17-24.
Accurate person tracking through changing poses for multi-view action recognition Pradeep Natarajan, Prithviraj Banerjee, Ram Nevatia ICCVGIP 2010, pp. 155-161.
Learning 3D action models from a few 2D videos for view invariant action recognition Pradeep Natarajan, Vivek Kumar Singh, Ram Nevatia CVPR 2010, pp. 2006-2013.
Multi-target tracking by on-line learned discriminative appearance models Cheng-Hao Kuo, Chang Huang, Ram Nevatia CVPR 2010, pp. 685-692.
Accurate 3D face reconstruction from weakly calibrated wide baseline images with profile contours Yu-Ping Lin, Gérard Medioni, Jong-Moo Choi, CVPR 2010, pp. 1490-1497
Multiple pose context trees for estimating human pose in object context Vivek Kumar Singh, Furqan Muhammad Khan, Ram Nevatia SMiCV 2010, pp. 17-24
Locally Linear Denoising on Image Manifolds Dian Gong, Fei Sha, Gérard Medioni AISTATS 2010, Chia Laguna Resort, Sardinia, Italy, May 2010.
Human pose estimation from a single view point, real-time range sensor Matheen Siddiqui, Gérard Medioni CVCG 2010, pp. 1-8
Robot vision for the visually impaired Vivek Pradeep, Gérard Medioni, James Weiland CVAVI 2010, pp. 15-22
Color contrast enhancement for visually impaired people Anustup Choudhury, Gérard Medioni CVAVI 2010, pp. 33-40

Available Papers for 2009

Journal Papers
Detection and Segmentation of Multiple, Partially Occluded Objects by Grouping, Merging, Assigning Part Detection Responses, Bo Wu; Ram Nevatia IJCV, Vol. 82, No. 2, April 2009.
Human Pose Tracking in Monocular Sequence Using Multilevel Structured Models Mun Wai Lee; Ram Nevatia PAMI Vol. 31, No. 1, January 2009, pp. 27-38.
Identifying Noncooperative Subjects at a Distance Using Face Images and Inferred Three-Dimensional Face Models Gérard Medioni, Jongmoo Choi, Cheng-Hao Kuo, and Douglas Fidaleo SMC-A Vol. 39, No. 1, January 2009, pp. 12-24.
Multiple-Target Tracking by Spatiotemporal Monte Carlo Markov Chain Data Association Qian Yu, Gérard Medioni PAMI Vol. 31, No. 12, December 2009, pp. 2196-2210.

Conference Papers
3-D model based vehicle recognition Jan Prokaj, Gérard Medioni, WACV 2009,
Color constancy using denoising methods and cepstral analysis Anustup Choudhury, Gérard Medioni ICIP 2009, pp. 1637-1640.
Extensive articulated human detection by voting Cluster Boosted Tree Bo Yang, Chang Huang, Ram Nevatia, WACV 2009,
Graphical framework for action recognition using temporally dense STIPs, Pradeep Natarajan, Prithviraj Banerjee, Furqan M. Khan, Ram Nevatia, Motion and Video Computing 2009
Learning to Associate: HybridBoosted Multi-Target Tracker for Crowded Scene Yuan Li, Chang Huang and Ram Nevatia CVPR 2009, pp. 2953-2960
Monocular human pose tracking using multi frame part dynamics, Vivek Kumar Singh, Ram Nevatia, Motion and Video Computing 2009
Motion Pattern Interpretation and Detection for Tracking Moving Vehicles in Airborne Video Qian Yu and Gérard Medioni, CVPR 2009, pp. 2671-2678
Perceptually motivated automatic color contrast enhancement Anustup Choudhury, Gérard Medioni, IEEE Color and Reflectance in Imaging and Computer Vision Workshop, CRICV pp. 1893-1900.
Real time tracking using an active pan-tilt-zoom network camera Thang Ba Dinh, Qian Yu, Gérard Medioni, IROS 2009, pp. 3786-3793.
Robust multi-view car detection using unsupervised sub-categorization Cheng-Hao Kuo, Ram Nevatia, WACV 2009,
StaRSaC: Stable Random Sample Consensus for Parameter Estimation Jongmoo Choi and Gérard Medioni, CVPR 2009, pp. 675-682.
Vision based Short Range Interaction between a Personal Service Robot and a User M. Siddiqui, W.K. Liao, Gérard Medioni Intl Symposium on Rotics 2009
Visual Loop Closing using multi-resolution SIFT Grids in Metric-Topological SLAM Vivek Pradeep, Gérard Medioni, James Weiland CVPR 2009, pp. 1438-1445.

Available Papers for 2008

Journal Papers
2-D Registration and 3-D Shape Reconstruction of the Retinal Fundus from Fluorescein Images Tae Eun Choe, Gérard Medioni, Isaac Cohen, Alexander Walsh, SriniVas Sadda Journal of Medical Image Analysis, pp.174-190 Apr. 2008
Inferring Segmented Dense Motion Layers Using 5D Tensor Voting Changki Min, Gérard Medioni, PAMI Vol. 30, No. 9, September 2008, pp. 1589-1602.
Segmentation and Tracking of Multiple Humans in Crowded Environments Tao Zhao, Ram Nevatia, Bo Wu PAMI Vol. 30, No. 7, July 2008, pp. 1198-1211.

Conference Papers 2008
3D face tracking and expression inference from a 2D sequence using manifold learning Wei-Kai Liao and Gérard Medioni, CVPR 2008
Distributed Visual Processing for a Home Visual Sensor Network Kwangsu Kim, Gérard Medioni, WACV 2008
Efficient scan-window based object detection using GPGPU Li Zhang, Ram Nevatia CVGPU 2008
Global data association for multi-object tracking using network flows Li Zhang, Yuan Li, Ram Nevatia CVPR 2008
A GPU-based implementation of motion detection from a moving platform Qian Yu and Gérard Medioni, CVGPU 2008
Human detection by searching in 3d space using camera and scene knowledge Yuan Li, Bo Wu, Ram Nevatia ICPR 2008,
Integrated Detection and Tracking for Multiple Moving Objects using Data-Driven MCMC Data Association Qian Yu, Gérard Medioni, IEEE Motion and Video Computing 2008
Key Object Driven Multi-category Object Recognition, Localization and Tracking Using Spatio-temporal Context Yuan Li, Ram Nevatia ECCV 2008, Volume IV: 409-422
Mutual Information Computation and Maximization Using GPU Yuping Lin and Gérard Medioni, CVGPU 2008
Online, Real-time Tracking and Recognition of Human Actions Pradeep Natarajan, Ram Nevatia IEEE Motion and Video Computing 2008
Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers Qian Yu, Thang Ba Dinh, Gérard Medioni, ECCV 2008, Volume II: 678-691
Optimizing discrimination-efficiency tradeoff in integrating heterogeneous local features for object detection Bo Wu, Ram Nevatia CVPR 2008
Pedestrian Tracking by Associating Tracklets using Detection Residuals Vivek Kumar Singh, Bo Wu, Ram Nevatia IEEE Motion and Video Computing 2008
Piecewise Planar Modeling for Step Detection using Stereo Vision Vivek Pradeep, Gérard Medioni and James Weiland CVAVI 2008, Workshop on Computer Vision Applications for the Visually Impaired
Real-Time 3D Body Pose Tracking from Multiple 2D Images Chi-Wei Chu, Ram Nevatia AMDO 2008, pp. 42-52
Retinal Image Registration from 2D to 3D Yuping Lin and Gérard Medioni, CVPR 2008
Robust Object Tracking based on Detection with Soft Decision Li Zhang, Bo Wu, Vivek Kumar Singh, Ram Nevatia IEEE Motion and Video Computing 2008
Robust Object Tracking by Hierarchical Association of Detection Responses Chang Huang, Bo Wu, Ram Nevatia ECCV 2008, Volume II: 788-801
Segmentation of multiple, partially occluded objects by grouping, merging, assigning part detection responses Bo Wu, Ram Nevatia, Yuan Li, CVPR 2008
Two-Frames Accurate Motion Segmentation Using Tensor Voting and Graph-Cuts Thang Dinh, Gérard Medioni, IEEE Motion and Video Computing 2008
View and scale invariant action recognition using multiview shape-flow models Pradeep Natarajan, Ram Nevatia CVPR 2008

Available Papers for 2007

Journal Papers
Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors Bo Wu and Ram Nevatia IJCV, Vol. 75, No. 2, November 2007, pp. 247-266.
Detecting Motion Regions in the Presence of a Strong Parallax from a Moving Camera by Multiview Geometric Constraints Chang Yuan, Gérard Medioni, Jinman Kang, Isaac Cohen, PAMI, Vol. 29, No. 9, September 2007, pp. 1627-1641.
Registration of 3D Points Using Geometric Algebra and Tensor Voting Leo Reyes, Gérard Medioni, Eduardo Bayro-Corrochano, IJCV, Vol. 75, No. 2, November 2007, pp. 351-369.
Robust Real-Time Vision for a Personal Service Robot Gérard Medioni, Alexandre R.J. Francois, Matheen Siddiqui, Kwangsu Kim and Hosub Yoon CVIU, Vol. 108, Issues 1-2, pp. 196-203 (October-November 2007)

Conference Papers 2007
3-D Metric Reconstruction and Registration of Images of Near-planar Surfaces Tae Eun Choe, Gérard Medioni ICCV 2007 October 2007, Rio de Janario, Brazil
Body Part Detection for Human Pose Estimation and Tracking Mun Wai Lee; Ram Nevatia Workshop on Motion and Video Computing February 2007
Cluster Boosted Tree Classifier for Multi-View, Multi-Pose Object Detection Bo Wu, Ram Nevatia ICCV October 2007, Rio de Janario, Brazil
Coupled Hidden Semi Markov Models for Activity Recognition P. Natarajan, Ram Nevatia Workshop on Motion and Video Computing February 2007
Detection and Tracking of Multiple Humans with Extensive Pose Articulation Li Zhang, Ram Nevatia, Bo Wu ICCV October 2007, Rio de Janario, Brazil
Efficient Upper Body Pose Estimation from a Single Image or a Sequence Matheen Siddiqui, Gérard Medioni Human Motion pp. 74-87. October 2007, Rio de Janario, Brazil
Hierarchical Multi-channel Hidden Semi Markov Models P. Natarajan, Ram Nevatia IJCAI
Improving Part based Object Detection by Unsupervised, Online Boosting Bo Wu and Ram Nevatia, CVPR June 2007
Inferring 3D Volumetric Shape of Both Moving Objects and Static Background Observed by a Moving Camera Chang Yuan and Gérard Medioni, CVPR June 2007
Integrating Multiple Visual Cues for Robust Real-Time 3D Face Tracking Wei-Kai Liao, Douglas Fidaleo, Gérard Medioni AMFG pp. 109-123. October 2007, Rio de Janario, Brazil
Map-Enhanced Detection and Tracking from a Moving Platform with Local and Global Data Association Qian Yu, Gérard Medioni, Workshop on Motion and Video Computing February 2007
Map-Enhanced UAV image sequence Registration and Synchronization of Multiple Image Sequences Yuping Lin, Gérard Medioni Workshop on Image Registration & Fusion Workshop (CVPR 2007) June 2007
Map-Enhanced UAV Image Sequence Registration Yuping Lin, Qian Yu, Gérard Medioni WACV, February 2007
Model-Assisted 3D Face Reconstruction from Video Douglas Fidaleo, Gérard Medioni AMFG pp. 124-138 October 2007, Rio de Janario, Brazil
Moving Object Detection on a Runway Prior to Landing Using an Onboard Infrared Camera Cheng-Hua Pai, Gérard Medioni, Yu-Ping Lin and Ray Rida Hamza OTCBVS Workshop, CVPR June 2007
Multiple Target Tracking Using Spatio-Temporal Markov Chain Monte Carlo Data Association Qian Yu, Gérard Medioni, and Isaac Cohen CVPR June 2007
Non-Cooperative Persons Identification at a Distance with 3D Face Modeling Gérard Medioni, Jongmoo Choi, Cheng-Hao Kuo, Anustup Choudhury, Li Zhang, Douglas Fidaleo IEEE Conference on Biometrics
Pedestrian Detection in Infrared Images based on Local Shape Features Li Zhang, Ram Nevatiaand Bo Wu OTCBVS Workshop, CVPR June 2007
Real Time Body Pose Tracking in an Immersive Training Environment Chi-Wei Chu, Ram Nevatia CV HCI pp. 146-156. October 2007, Rio de Janario, Brazil
Simultaneous Object Detection and Segmentation by Boosting Local Shape Feature based Classifier Bo Wu and Ram Nevatia, CVPR June 2007
Single View Human Action Recognition using Key Pose Matching and Viterbi Path Searching Fengjun Lv, Ram Nevatia CVPR June 2007
Planar Patch based 3D Environment Modeling with Stereo Camera Eunyoung Kim, Gérard Medioni, Sukhan Lee RO-MAN (Robot and Human Interactive Communication) 2007

Available Papers for 2006

Journal Papers
Camera Calibration from Video of a Walking Human F. Lv, Tao Zhao, Ram Nevatia. PAMI, Vol. 28, No. 9, September 2006, pp. 1513-1518.
A Model-Based Approach for Estimating Human 3D Poses in Static Images Mun Wai Lee, Isaac Cohen PAMI, Vol. 28, No. 6, June 2006 pp. 905-916.
Stereo Using Monocular Cues within the Tensor Voting Framework Mordohai, P.; Gérard Medioni; PAMI, Vol. 28, No. 6, June 2006 pp. 968-982.

Conference Papers
3D Reconstruction of Background and Objects Moving on Ground Plane Viewed from a Moving Camera Chang Yuan, Gérard Medioni CVPR 2006, Volume II, pp. 2261-2268
3-D Shape Reconstruction of Retinal Fundus Tae Eun Choe, Isaac Cohen, Gérard Medioni CVPR 2006, Volume II, pp. 2277-2284
Belief Propagation Driven Method for Facial Gestures Recognition in Presence of Occlusions Wei-Kai Liao and Isaac Cohen Vision for Human-Computer Interaction V4HCI. (At CVPR 2006)
Boosted Markov Chain Monte Carlo Data Association for Multiple Target Detection and Tracking Qian Yu, Isaac Cohen, Gérard Medioni, Bo Wu, ICPR 2006, Volume II: pp. 675-678
Boosted Markov Chain Monte Carlo Data Association for Multiple Target Detection and Tracking Yun-Qian Ma, Qian Yu, Isaac Cohen ISVC 2006, Volume I: pp. 783-792
Evaluation of USC Human Tracking System for Surveillance Videos Bo Wu, Xuefeng Song, Vivek Kumar Singh, and Ram Nevatia In CLEAR'06 Evaluation Campaign and Workshop, in conjunction with FG'06, 2006.
Human Pose Tracking Using Multi-Level Structured Models M.W. Lee and Ram Nevatia ECCV 2006, Volume III, pp. 368-381.
Left-Luggage Detection using Bayesian Inference Fengjun Lv, Xuefeng Song, Bo Wu, Vivek Kumar Singh, Ram Nevatia 9th Intl. Workshop on Performance Evaluation of Tracking and Surveillance (PETS-CVPR'06)
Motion Segmentation by Spatiotemporal Smoothness Using 5D Tensor Voting Changki Min and Gérard Medioni 5th Workshop on Perceptual Organization in Computer Vision. (At CVPR 2006)
Multi-layer Mosaics in the Presence of Motion and Depth Effects Changki Min, Qian Yu, Gérard Medioni, ICPR 2006, Volume I: pp. 992-995
Optimal Global Mosaic Generation from Retinal Images Tae Eun Choe, Isaac Cohen, Munwai Lee, Gérard Medioni, ICPR 2006, Volume III: pp. 681-684
Real Time Limb Tracking with Adaptive Model Selection Matheen Siddiqui, Gérard Medioni, ICPR 2006, Volume IV: pp. 770-773
Recognition and Segmentation of 3-D Human Action Using HMM and Multi-Calss AdaBoost F. Lv and Ram Nevatia ECCV 2006, Volume IV, pp. 359-372.
Robust real-time upper body limb detection and tracking Matheen Siddiqui, Gérard Medioni, International Workshop on Visual Surveillance and Sensory Networks 2006, pp. 53-60.
Speaker Tracking in Seminars by Human Body Detection Bo Wu, Vivek Kumar Singh, Ram Nevatia, and Chi-Wei Chu In CLEAR'06 Evaluation Campaign and Workshop, in conjunction with FG'06, 2006.
Tensor Voting Accelerated by Graphics Processing Units (GPU) Changki Min, Gérard Medioni, ICPR 2006, Volume III, pp. 1103-1106
Tracking of Multiple, Partially Occluded Humans based on Static Body Part Detection B. Wu and Ram Nevatia CVPR 2006, Volume I, pp. 951-958.
Tracking Multiple Humans in Meetings B. Wu and Ram Nevatia Vision for Human-Computer Interaction V4HCI. (At CVPR 2006)

Available Papers for 2005

Journal Papers
Parametric reconstruction of generalized cylinders from limb edges Chunhong Pan, Hongping Yan, Gérard Medioni, Songde Ma IP, Vol. 14, No. 8, August 2005, pp. 1202-1214.
VERL: An Ontology Framework for Representing and Annotating Video Events Alexandre R.J. Francois, Ram Nevatia, Jerry Hobbs, Robert C. Bolles IEEE Multimedia Magazine, October-December 2005, pp. 76-86.
A Voting-Based Computational Framework for Visual Motion Analysis and Interpretation Nicolescu, M., Gérard Medioni, PAMI Vol. 27, No. 5, May 2005, pp. 739-752.

Conference Papers 2005
3D Human Action Recoginition Using Spatio-Temporal Motion Templates Fengjun Lv, Ram Nevatia, M.W. Lee, Vision for Human-Computer Interaction, June 2005
Classifying Facial Gestures in Presence of Head Motion Wei-Kai Liao and Isaac Cohen Vision for Human-Computer Interaction, June 2005
Detection and Tracking of Moving Objects from a Moving Platform in Presence of Strong Parallax J. Kang, I. Cohen, Gérard Medioni, C. Yuan ICCV, Volume I, pp. 10-17. October 2005.
Detection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors Bo Wu, Ram Nevatia ICCV, Volume I, pp. 90-97. October 2005.
Dynamic Human Pose Estimation using Markov chain Monte Carlo Approach Mun Wai Lee, Ram Nevatia IEEE Workshop on Motion and Video Computing. Breckenridge, Colorado. Jan 4-5, 2005.
EDF: A Framework for Semantic Annotation of Video Pradeep Natarajan, Ram Nevatia. Workshop on Semantic Knowledge in Computer Vision, October 2005
Integrating Component Cues for Human Pose Tracking Mun Wai Lee, Ram Nevatia. Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, at ICCV, Beijing, October 2005
An Investigation of Model Bias in 3D Face Tracking D. Fidaleo and Gérard Medioni IEEE International Workshop on Analysis and Modeling of Faces and Gestures, Beijing, Oct. 16, 2005.
A Model-Based Vehicle Segmentation Method for Tracking Xuefeng Song, Ram Nevatia. ICCV, Volume II, pp. 1124-1131. October 2005.
Persistent Objects Tracking Across Multiple Non Overlapping Cameras J. Kang, I. Cohen and Gérard Medioni IEEE Workshop on Motion and Video Computing. Breckenridge, Colorado. Jan 4-5, 2005.
Posture and Gesture Recognition using 3D Body Shapes Decomposition Chi-Wei Chu, Isaac Cohen Vision for Human-Computer Interaction, June 2005
Registration of Multimodal Fluorescein Images Sequence of the Retina T.E. Choe, I. Cohen ICCV, Volume I, pp. 106-113. October 2005.
Smart Room: Participant and Speaker Localization and Identification C. Busso, S. Hernanz, C-W. Chu, S. Kwon, S. Lee, P.G. Georgiou, I. Cohen, S. Narayanan IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP. March 18-23. 2005.
Unsupervised Dimensionality Estimation and Manifold Learning in high-dimensional Spaces by Tensor Voting P. Mordohai and Gérard Medioni 19th IJCAI, pp. 798-803, Edinburgh, Scotland, July 2005

Available Papers for 2004

Journal Papers
Automatic description of complex buildings from multiple images ZuWhan Kim, Ram Nevatia CVIU, Vol. 96, No. 1, October 2004, pp. 60-95.
First order augmentation to tensor voting for boundary inference and multiscale analysis in 3d Wai-Shun Tong, Chi-Keung Tang, Mordohai, P., Gérard Medioni PAMI, Vol. 26, No. 5, May 2004, pp. 594-611.
Simultaneous Two-View Epipolar Geometry Estimation and Motion Segmentation by 4D Tensor Voting Wai-Shun Tong, Chi-Keung Tang, Gérard Medioni PAMI, Vol. 26, No. 9, September 2004, pp. 1167-1184.
Tracking Multiple Humans in Complex Situations Tao Zhao, Ram Nevatia PAMI, Vol. 26, No. 9, September 2004, pp. 1208-1221.
Video-based event recognition: activity representation and probabilistic recognition methods Somboon Hongeng, Ram Nevatia, Francois Bremond CVIU, Vol. 96, No. 2, November 2004, pp. 129-162.

Conference Papers
3D hand reconstruction from a monocular view Sung Uk Lee, I. Cohen ICPR, 2004, Vol. III: 310-313
3D modeling from turntable sequences using dense stereo carving and multi-view consistency J. Arnabat, S. Casanovas, Gérard Medioni ICPR, 2004, Vol. IV: 36-39.
Automatic Tracking and Labeling of Human Activities in a Video Sequence Fengjun Lv, Jinman Kang, Ram Nevatia, Isaac Cohen, Gérard Medioni Workshop on Performance Evaluation of Tracking and Surveillance (PETS), 2004
CAMSHIFT Tracker Design Experiments with Intel OpenCV and SAI, Alexandre R.J. François IMSC TR 04-423, July 2004
Combined face-body tracking in indoor environment Xuefeng Song, Ram Nevatia ICPR, 2004, Vol. IV: 159-162
Dense Multiple View Stereo with General Camera Placement using Tensor Voting P. Mordohai and Gérard Medioni Second International Symposium on 3-D Data Processing, Visualization and Transmission, Thessaloniki, Greece, September 2004
Extraction and integration of window in a 3D building model from ground view images Sung Chun Lee, Ram Nevatia CVPR, 2004, Vol. II: 113-120
Human Upper Body Pose Estimation in Static Images M.W. Lee, I. Cohen ECCV, 2004, Vol II: 126-138
Junction Inference and Classification for Figure Completion using Tensor Voting P. Mordohai and Gérard Medioni Fourth Workshop on Perceptual Organization in Computer Vision, Washington DC, USA, June 2004
Non-iterative approach to multiple 2D motion estimation Eun-Young Kang, I. Cohen, Gérard Medioni ICPR, 2004, Vol. IV: 791-794
Object reacquisition using invariant appearance model Jinman Kang, I. Cohen, Gérard Medioni ICPR, 2004, Vol. IV: 759-762
An Ontology for Video Event Representation Ram Nevatia, J. Hobbs, B. Bolles IEEE Workshop on Event Detection and Recognition, June 2004
Parametric 2D layer inference from uncalibrated cameras E. Kang, I. Cohen and Gérard Medioni, ACCV, 2004
Proposal maps driven MCMC for estimating human body pose in static images Mun Wai Lee, I. Cohen CVPR, 2004, Vol. II: 334-341
Real-Time Multi-Resolution Blob Tracking Alexandre R.J. François IRIS TR 04-422, April 2004
A Robust and Non-Iterative Estimation Method of Multiple 2D Motions Eun-Young Kang, I. Cohen, Gérard Medioni, International Conference on Image Processing, 2004, Vol. V: 3367-3370.
Stereo using Monocular Cues within the Tensor Voting Framework P. Mordohai and Gérard Medioni, 8th ECCV, pp 588-601, Prague, Czech Republic, May 2004
Tracking multiple humans in crowded environment Tao Zhao, Ram Nevatia CVPR, 2004, Vol. II: 406-413
Tracking Objects from Multiple Stationary and Moving Cameras Jinman Kang, I. Cohen, Gérard Medioni, IDSS, 2004
Tracking people in crowded scenes across multiple cameras J. Kang, I. Cohen and Gérard Medioni, ACCV, 2004
Tracking soccer players using the graph representation P. Figueroa, N. Leite, R.M.L. Barros, I. Cohen, Gérard Medioni, ICPR, 2004, Vol. IV: 7870790

Available Papers for 2003

Journal Papers
Car Detection in Low Resolution Aerial Images, Tao Zhao, Ram Nevatia IVC(21), No. 8, August 2003, pp. 693-703
Expandable bayesian networks for 3D object description from multiple views and multiple mode inputs, ZuWhan Kim, Ram Nevatia PAMI, Vol. 25, No. 6, June 2003, pp. 769-774.
Layered 4D representation and voting for grouping from motion, Mircea Nicolescu, Gérard Medioni, PAMI(25), No. 4, April 2003, pp. 492-501.
Mirror symmetry ==> 2-view stereo geometry Alexandre R. J. François, Gérard Medioni, Roman Waupotitsch IVC(21), No. 2, February 2003, pp. 137-143.

Conference Papers
Bayesian Human Segmentation in Crowded Situations Tao Zhao, Ram Nevatia CVPR03 II: 459-466
Continuous Tracking Within and across Camera Streams Jinman Kang, Isaac Cohen and Gérard Medioni CVPR'2003, Vol I, 267-272
Face modeling and recognition in 3-D Gérard Medioni, Waupotitsch, R., International Workshop on Analysis and Modeling of Faces and Gestures, pp. 232-233
Fast and Robust 2D Parametric Image Registration Eun-Young Elaine Kang, Isaac Cohen and Gérard Medioni IRIS-03-421
A Handheld Mirror Simulation Alexandre François, Elaine Kang Proceedings of the IEEE International Conference on Multimedia and Expo, vol. II, pp. 745-748, Baltimore, MD, July 2003.
Hierarchical Language-based Representation of Events in Video Streams, Ram Nevatia, Tao Zhao, Somboon Hongeng, IEEE Workshop on Event Mining
Human Body Tracking with Auxiliary Measurements Mun Wai Lee, Isaac Cohen Analysis and Modeling of Faces and Gestures, 112-119
Inference of Human Postures by Classification of 3D Human Body Shape Isaac Cohen, Hongxia Li International Workshop on Analysis and Modeling of Faces and Gestures, pp. 74-81
Interactive 3D Building Modeling Using a Hierarchical Representation Sung Chun Lee and Ram Nevatia IEEE Workshop on Higher-Level Knowledge in 3D Modeling and Motion (HLK) ICCV 2003. Nice, October 17 2003
Large-scale event detection using semi-hidden markov models Somboon Hongeng, Ram Nevatia ICCV03, pp. 1455-1462.
Motion Segmentation with Accurate Boundaries - A Tensor Voting Approach Mircea Nicolescu, Gérard Medioni CVPR03
Multi-Views Tracking Within and Across Uncalibrated Camera Streams J. Kang, I. Cohen and Gérard Medioni, ACM SIGMM Workshop on Video Surveillance, 2003
MuSA.RT - Music on the Spiral Array . Real-Time, Elaine Chew, Alexandre R.J. François Proceedings of the ACM Multimedia 2003
Soccer Player Tracking across Uncalibrated Camera Streams J. Kang, I. Cohen and Gérard Medioni, Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, with ICCV'03
Software Architecture for Computer Vision: Beyond Pipes and Filters, Alexandre R.J. François IRIS TR 03-240, July 2003
Software Architecture for Immersipresence, Alexandre R.J. François IMSC TR 03-001, December 2003

Available Papers for 2002

Journal Papers
Curvature-Augmented Tensor Voting for Shape Inference from Noisy 3D Data, Tang, C.K., Gérard Medioni, PAMI, Vol. 24, No. 6, pp. 858-864, June 2002
Inference of Segmented Overlapping Surfaces from Binocular Stereo M.S. Lee, Gérard Medioni, and P. Mordohai PAMI, Vol. 24, No. 6, pp. 824-837, June 2002

Conference Papers
3D Body Reconstruction for Immersive Interaction Isaac Cohen and Mun Wai Lee. Second International Workshop on Articulated Motion and Deformable Objects Palma de Mallorca, Spain, 21-23 November, 2002.
3D tracking of human locomotion: a tracking as recognition approach Tao Zhao, Ram Nevatia ICPR, Quebec City, Canada, August 2002. pp. I: 546-551.
4-D Voting for Matching, Densification and Segmentation into Motion Layers Mircea Nicolescu, Gérard Medioni ICPR, Quebec City, Canada, August 2002.
Automatic and Interactive Modeling of Buildings in Urban Environments from Aerial Images . Ram Nevatia and Keith Price IEEE ICIP 2002, Rochester, NY, September 2002, Volume III, pp. 525-528.
Automatic Integration of Facade Textures into 3D Building Models with a Projective Geometry Based Line Clustering Sung Chun Lee, Soon Ki Jung, and Ram Nevatia Computer Graphics Forum (Euro Graphics), Vol. 21, No. 3, pp. 511-519, 2002.
Automatic Pose Estimation of Complex 3D Building Models Sung Chun Lee, Soon Ki Jung, and Ram Nevatia WACV 2002. December 2002.
Components for Immersion Alexandre R.J. François Proceedings of the IEEE International Conference on Multimedia and Expo, Lausanne, Switzerland, August 2002.
Continuous multi-views tracking using tensor voting Jinman Kang, I. Cohen, Gérard Medioni, WMVC, December 2002. 181-186
Generation of a 3-D face model from one camera Gérard Medioni, Pesenti, B., ICPR, Quebec City, Canada, August 2002, pp. III: 667-671.
A Handheld Virtual Mirror Alexandre François, Elaine Kang and Umberto Malesci SIGGRAPH Conference Abstracts and Applications, p.140, San Antonio, TX, July 2002.
Human Body Posture Inference for Immersive Interaction, ACM, Isaac Cohen, Hongxia Li and Mun Wai Lee International Workshop on Immersive Telepresence, ACM Multimedia 2002, Juan Les Pins, France. 6 December, 2002.
Integrating Ground and Aerial Views for Urban Site Modeling Sung Chun Lee, Soon Ki Jung, and Ram Nevatia ICPR, Quebec City, Canada, August 2002. pp. IV: 107-112.
Learning highly structured motion model for 3D human tracking Tao Zhao, Tianshu Wang, Harry Shum ACCV2002, January 2002
Motion Segmentation with Accurate Boundaries - A Tensor Voting Approach Mircea Nicolescu, Gérard Medioni IRIS-02-418 Tech Report
Particle filter with analytical inference for human body tracking, Mun Wai Lee, I. Cohen, Soon Ki Jung WMVC, December 2002. 159-165.
Perceptual Grouping for Multiple View Stereo using Tensor Voting P. Mordohai and Gérard Medioni, ICPR, Quebec City, Canada, August 2002, pp. III: 639-644.
Perceptual Grouping from Motion Cues Using Tensor Voting in 4-D Mircea Nicolescu, Gérard Medioni ECCV, vol. III, pp. 423-437, Copenhagen, Denmark, May 2002.
Reconstructing Mirror Symmetric Scenes From a Single View Using 2-View Stereo Geometry Alexandre R.J. François and Gérard Medioni, ICPR, Quebec City, Canada, August 2002
Robust Affine Motion Estimation in Joint Image Space using Tensor Voting Kang, E.Y., Cohen, I., Gérard Medioni, ICPR, Quebec City, Canada, August 2002, pp. IV: 256-259.
Self-calibration of a camera from video of a walking human Fengjun Lv, Tao Zhao, Ram Nevatia ICPR, Quebec City, Canada, August 2002. pp. I: 562-567.
Stochastic Human Segmentation from a Static Camera Tao Zhao, Ram Nevatia WMVC, December 2002

Available Papers for 2001

Journal Papers
Crater detection for autonomous landing on asteroids B. Leroy, Gérard Medioni, E. Johnson, L. Matthies, IVC, Vol. 19, No. 11, September 2001, pp. 787-792.
Detection and Modeling of Buildings from Multiple Aerial Images. S. Noronha and Ram Nevatia, PAMI, No. 5, May 2001, pp. 501-518
Event Detection and Analysis from Video Streams, Gérard Medioni, Isaac Cohen, François Brémond, Somboon Hongeng, Ram Nevatia, PAMI, Vol. 23, No. 8, August 2001, pp. 873-889.
Interactive 3-D Model Extraction From a Single Image Alexandre R.J. François and Gérard Medioni, Image and Vision Computing, vol. 19, no. 6, April 2001, pp. 317-328.
N-Dimensional Tensor Voting and Application to Epipolar Geometry Estimation, Chi-Keung Tang, Gérard Medioni, Mi-Suen Lee, PAMI, Vol. 23, No. 8, August 2001, pp. 829-844.

Conference Papers
2-D Shape Decomposition into Overlapping Parts A. Massad, Gérard Medioni, 4th International Workshop on Visual Form, Capri, Italy, pp. 398-409
Automatic Description of Buildings with Complex Rooftops from Multiple Images. ZuWhan Kim, Andres Huertas, and Ram Nevatia, CVPR December 2001.
Car Detection in Low Resolution Aerial Image. Tao Zhao, Ram Nevatia IEEE ICCV, July 2001.
Efficient Dense Depth Estimation from Dense Multiperspective Panoramas, Li, Y., Tang, C.K., Shum, H.Y., IEEE ICCV, July 2001, pp. I: 119-126.
Epipolar Geometry Estimation for Non-Static Scenes by 4D Tensor Voting, W. S. Tong, C. K. Tang, Gérard Medioni, CVPR December 2001. pp. I:926-933
First Order Tensor Voting and Application to 3-D Scale Analysis, W. S. Tong, C. K. Tang, Gérard Medioni, CVPR, December 2001, pp. I:175-182
Inference of 3D human body posture from multiple cameras for vision-based user interfaces Isaac Cohen, Gérard Medioni, Haisong Gu 5th World Multi-Conference on Systemics, Cybernetics and Informatics, 2001, Orlando Florida
Inference of Segmented Overlapping Surfaces from Binocular and Multiple-View Stereo P. Mordohai, Gérard Medioni, and M.S. Lee Third Workshop on Perceptual Organization in Computer Vision, ICCV, Vancouver, Canada, July 2001
A Model-Based Approach for Multi-View Complex Building Description. Z. Kim, A. Huertas, and Ram Nevatia, Proc. ASCONA, 2001.
A Modular Software Architecture for Real-Time Video Processing Alexandre R.J. François and Gérard Medioni Proceedings of the International Workshop on Computer Vision Systems, July 2001, pp. 35-49.
Multi-Agent Event Recognition,. Somboon Hongeng, Ram Nevatia IEEE ICCV, July 2001. pp. II: 84-91
Segmentation and tracking of multiple humans in complex situations Tao Zhao, Ram Nevatia, Fengjun Lv CVPR December 2001

Available Papers for 2000

Journal Papers
Detecting Changes in Aerial Views of Man-Made Structures Andres Huertas and Ramakant Nevatia. IVC, Vol. 18, No. 8, 15 May 2000, pp. 583-596.

Conference Papers
3-D Structures for Generic Object Recognition Gérard Medioni and Alexandre R.J. François, ICPR 2000, Vol. 1, pp. 30-37. September 2000
Automatic Description of Complex Buildings with Multiple Images ZuWhan Kim, Andres Huertas and Ramakant Nevatia WACV 2000, Palm Springs, pp. 155-162.
Bayesian Framework for Video Surveillance Application, Somboon Hongeng, Francois Bremond, Ramakant Nevatia ICPR 2000, pp. Vol I: 164-170. September 2000
Electronic Pan-Tilt-Zoom: A Solution for Intelligent Room Systems Mircea Nicolescu, Gérard Medioni International Conference on Multimedia and Expo, pp. 1581-1584, New York, NY, July 2000.
Geodesic distance evolution of surfaces: a new method for matching surfaces H. M. Yahia, E. G. Huot, I. L. Herlin, I. Cohen CVPR 2000
GlobeAll: Panoramic Video for an Intelligent Room Mircea Nicolescu, Gérard Medioni ICPR 2000, Vol. I, pp. 823-826, September 2000.
A Graph-based Global Registration for 2D Mosaics Eun-Young Kang, Isaac Cohen and Gérard Medioni ICPR 2000, September 2000
Learning Bayesian Networks for Diverse and Varying Numbers of Evidence Set ZuWhan Kim and Ramakant Nevatia International Conference on Machine Learning, 2000, pp. 479-486.
Learning in Building Extraction Zu Whan, A. Huertas Results for Building Extraction; Aerial Images
Modeling 3-D Complex Buildings with User Assistance Sung Chun Lee, A. Huertas and Ram Nevatia WACV 2000, Palm Springs, pp. 170-177.
A Modular Middleware Flow Scheduling Framework Alexandre R.J. François and Gérard Medioni Proceedings of ACM Multimedia 2000, Los Angeles, CA, November 2000, pp. 371-374.
Multisensor Integration for Building Modeling A. Huertas, Z. Kim and Ram Nevatia. CVPR 2000, II: 203-210
Representation and Optimal Recognition of Human Activities Somboon Hongeng, Francois Bremond, Ramakant Nevatia CVPR, 2000
Research in Knowledge-Based Automatic Feature Extraction. Ram Nevatia, A. Huertas Project final report. April 2000. IRIS-00-383.
Segmentation, Tracking and Interpretation Using Panoramic Video Mircea Nicolescu, Gérard Medioni, Mi-Suen Lee Proceedings of the IEEE Workshop on Omnidirectional Vision, pp. 169-174, Hilton Head Island, SC, June 2000.
Street Grids in Urban Environments Keith Price Results for Street Grids; Aerial Images
Surface Matching with Large Deformations and Arbitrary Topology: A Geodesic Distance Evolution Scheme on a 3-Manifold, E. Huot, H. Yahia, I. Cohen, I. Herlin, Proc. ECCV 2000.
Urban Street Grid Description and Verification Keith Price WACV 2000, Palm Springs, pp. 148-154.

Available Papers for 1999

Journal Papers
Grouping ., -, -->, 0, into Regions, Curves, and Junctions Mi-Suen Lee and Gérard Medioni CVIU, Vol. 76, No. 1, October 1999, pp. 54-69
Part-Based 3D Descriptions of Complex Objects from a Single Image M. Zerroug, Ram Nevatia PAMI, Vol. 21, No. 9, September 1999, pp. 835-848
Simultaneous Surface Approximation and Segmentation of Complex Objects Chia-Wei Liao and Gérard Medioni CVIU, Vol. 73, No. 1, January 1999, pp. 43-63.
Uncertain Reasoning and Learning for Feature Grouping ZuWhan Kim and Ramakant Nevatia CVIU, Vol 76, No. 3, December 1999, pp. 278-288.

Conference Papers
Adaptive Color Background Modeling for Real-time Segmentation of Video Streams Alexandre R.J. François and Gérard Medioni International Conference on Imaging Science, Systems, and Technology, Las Vegas, NA, June 1999, pp. 227-232.
Detecting and Tracking Moving Objects in Video Surveillance, Isaac Cohen, Gérard Medioni, CVPR 1999. II:319-325
Efficient Iterative Solutions to M-View Projective Reconstruction Problem Qian Chen, Gérard Medioni, CVPR 1999. II: 55-61
Epipolar Geometry Estimation by Tensor Voting in 8D, Chi-Keung Tang, and Gérard Medioni, ICCV 1999, pp. 502-509.
A Human-Assisted System to Build 3-D Models From a Single Image Alexandre R.J. François and Gérard Medioni IEEE International Conference on Multimedia Computing and Systems, vol. 1, Florence, Italy, June 1999, pp. 282-288.
The MURI Project for Rapid Feature Extraction in Urban Areas. Ram Nevatia, A. Huertas, Z. Kim ISPRS: Automatic Extraction of GIS Objects from Digital Imagery, September 1999.
Road Grid Extraction and Verification Keith Price ISPRS: Automatic Extraction of GIS Objects from Digital Imagery, September 8-10, 1999, pp. 101-106.
Robust Estimation of Curvature Information from Noisy 3D Data for Shape Description,, Chi-Keung Tang, and Gérard Medioni, ICCV 1999, pp. 426-433.
Semi-Automatic System to Infer Complex 3D Shapes from Photographs Qian Chen, Gérard Medioni, IEEE Multimedia Systems 1999. II: 798-805
Use of Hyperspectral Data with Intensity Images for Automatic Building Modeling A. Huertas, Ram Nevatia and D. Landgrebe, 2nd International Conference On Information Fusion, Sunnyvale, CA, July 1999.
User Assisted Modeling of Buildings from Aerial Iamges J. Li, Ram Nevatia and S. Noronha. CVPR 1999. II:274-279
A Volumetric Stereo Matching Method: Application to Image-Based Modeling Qian Chen, Gérard Medioni, CVPR 1999. I: 29-34

Available Papers for 1998

Journal Papers
Building Detection and Description from a Single Intensity Image Chungan Lin and Ram Nevatia, CVIU(72), No. 2, November 1998, pp. 101-121.
Event Detection and Analysis from Video Streams, Gérard Medioni Ram Nevatia, Isaac Cohen, IUW 1998. pp. 63-72.
Inference of Integrated Surface, Curve, and Junction Descriptions from Sparse 3D Data Tang, C.K., and Gérard Medioni PAMI(20), No. 11, November 1998, pp. 1206-1223.

Conference Papers
Building Detection and Description from multiple Views Sanjay Noronha and Ram Nevatia. Outline and Results of Building Extraction; Aerial Images
Curves Matching Using Geodesic Paths Isaac Cohen, Isabelle Herlin. CVPR 1998, pp. 741-746.
Detecting Changes in Aerial Views of Man-Made Structures Andres Huertas and Ramakant Nevatia. ICCV 98, pp. 73-79.
Detection and Tracking of Objects in Airborne Video Imagery I. Cohen, Gérard Medioni CVPR'98 Workshop on Interpretation of Visual Motion.
Detecting and Tracking Moving Objects in Video from an Airborne Observer I. Cohen, Gérard Medioni DARPA IUW 98, pp. 217-222
Inferring Segmented Surface Description from Stereo Data Mi-Suen Lee and Gérard Medioni CVPR, 1998, pp. 346-352.
Integrated Surface, Curve and Junction Inference from Sparse 3-D Data Sets, Chi-Keung Tang, and Gérard Medioni, ICCV 1998, pp. 818-823.
Knowledge-Based Building Detection and Description: 1997-1998 Ram Nevatia and A. Huertas. DARPA IUW 1998.
Real-Time Billboard Substitution in a Video Stream Gérard Medioni, Gideon Guy, Hillel Rom and Alexandre R.J. François Proceedings of the 10th Tyrrhenian International Workshop on Digital Communications, "Multimedia Communications", Ischia, Italy, 1998, pp. 71-84.
Recent Advances in Detection and Description of Buildings from Multiple Images
Sanjay Noronha, Ram Nevatia, ACCV98, II: 259-266.
Rendering from Uncalibrated Stereo Images Q. Chen and Gérard Medioni USC IRIS-98-365
Research in Knowledge-Based Automatic Feature Extraction. Ram Nevatia, A. Huertas IRIS-98-361.
Scenario Recognition in Airborne Video Imagery Bremond, Gérard Medioni CVPR'98 Workshop on Interpretation of Visual Motion.
Tracking Meteorological Structures through Curves Matching Using Geodesic Paths Isaac Cohen, Isabelle Herlin. ICCV 1998
Use of Cues from Range Data for Automatic Building Modeling A. Huertas, Z. Kim and Ram Nevatia. IUW 1998.
User Assisted Modeling of Buildings J. Li, Ram Nevatia and S.Nornoha. IUW 1998. 571-576.

Available Papers for 1997

Journal Papers
Inference of Surfaces, 3D Curves, and Junctions from Sparse, Noisy, 3D Data G. Guy and Gérard Medioni PAMI(19), No. 11, November 1997, pp. 1265-1277.

Conference Papers
3DSketch: Modeling by Digitizing with a Smart 3D Pen S. Han and Gérard Medioni ACM Multimedia'97
Buildings Detection and Description System. Chung An Lin Outline and results of Building Extraction; Aerial Images
Detection and Description of Buildings from Multiple Aerial Images Sanjay Noronha and Ram Nevatia. DARPA IUW 1997, 989-998
Detection and Description of Buildings from Multiple Aerial Images Sanjay Noronha and Ram Nevatia. CVPR97, pp. 588-594
Image Synthesis from a Sparse Set of Views Qian Chen, Gérard Medioni, Visualization 1997. 260-275
Non-uniform Skew Estimation by Tensor Voting S. Han, M.S. Lee, and Gérard Medioni IEEE Document Image Analysis, Puerto Rico, June 20, 97
Older Building detection results Chung An Lin Results for Building Extraction; Aerial Images
Overview paper. for the APGD project. DARPA IUW 97.
RADIUS Overview Andres Huertas and Ramakant Nevatia DARPA IUW 1997.
Surveillance and Monitoring Using Video Images from a UAV. Gérard Medioni, Ram Nevatia VSAM Overview paper, From IUW 97.
A System for Building Detection from Aerial Images Ram Nevatia, Chungan Lin and Andres Huertas. Ascona Workshop, 1997.

Available Papers for 1996

Journal Papers
Inferring Global Perceptual Contours from Local Features, G. Guy and Gérard Medioni IJCV Vol. 20, No. 1/2, 1996, pp. 113-133. (Earlier CVPR, 1993, pp. 787-787.)
Perceptual Grouping for Generic Recognition Parag Havaldar and Gérard Medioni IJCV, Vol. 20, No. 1/2, 1996, pp. 59-80
Recovering LSHGCs and SHGCs from Stereo, Ronald Chung and Ramakant Nevatia IJCV(20), No. 1/2, 1996, pp. 43-58
Three-Dimensional Descriptions Based on the Analysis of the Invariant and Quasi-Invariant Properties of Some Curved-Axis Generalized Cylinders, M. Zerroug and Ram Nevatia PAMI, Vo. 18, No. 3, March 1996, pp. 237-253.
Volumetric Descriptions from a Single Intensity Image, Part 1, Part 2 Part 3 M. Zerroug and Ram Nevatia IJCV, Vol. 20, No. 1/2, 1996, pp. 11-42.

Conference Papers
3-D Matcher System David Cherel 1996 report.
Buildings Detection and Description from Monocular Aerial Images Chungan Lin and Ram Nevatia, ARPA Image Understanding Workshop 1996.
Detection and Description of Buildings from Multiple Aerial Images Sanjay Noronha and Ram Nevatia. ARPA IUW 1996, pp. 469-478
Detection and Description of Buildings from Multiple Aerial Images Sanjay Noronha and Ram Nevatia. Internal Report
Generic Shape Learning and Recognition, A. Francois, Gérard Medioni Proceedings of the International Workshop on Object Representation in Computer Vision. Cambridge, England, April 1996.
Inference of Segmented, Volumetric Shape from Intensity Images, Parag Havaldar and Gérard Medioni CVPR, June 1996. pp. 278-284
Inference of Segmented, Volumetric Shape from Intensity Images. P. Havaldar and Gérard Medioni, DARPA IUW 96
Object Description and Recognition in Complex Environments Ram Nevatia IRIS-96-349
Research in Model-Based Change Detection and Model Updating Ram Nevatia and A. Huertas IRIS-96-351
Triangular NURBS Surface Modeling of Scattered Data, S. Han and Gérard Medioni IEEE Visualization, San Francisco, California, USA, Oct. 1996.
USC IMAGE UNDERSTANDING RESEARCH: 1994-1995 Ram Nevatia, Keith Price and Gérard Medioni DARPA IUW 96
The 1996 final report in 4 parts: Part 1. Part 2. Part 3. Part 4.
View Synthesis From Unregistered Images Parag Havaldar and Misuen Lee Graphics Interface, Toronto, Canada, 1996

Available Papers for 1995

Journal Papers
Description of Complex Objects from Multiple Range Images Using an Inflating Baloon Model, Y. Chen and Gérard Medioni CVIU Vol. 61, No. 3, May 1995, pp. 325-334.
Finding Waldo, or Focus of Attention Using Local Color Information, Ennesser, F., and Gérard Medioni PAMI(17), No. 8, August 1995, pp. 805-809.
Shape From Contour: Straight Homogeneous Generalized Cylinders and Constant Cross-Section Generalized Cylinders Ulupinar, F., and Ram Nevatia, PAMI(17), No. 2, February 1995, pp. 120-135.
Surface Approximation of a Cloud of 3D Points, C. Liao and Gérard Medioni GMIP, Vol. 57, No. 1, January 1995. pp. 67-74.
Use of Monocular Groupings and Occlusion Analysis in a Hierarchical Stereo System, , Chung, R.C.K., and Ram Nevatia, CVIU(62), No. 3, November 1995, pp. 245-268

Conference Papers
3-D Descriptions of Buildings from an Oblique View Aerial Image Chungan Lin and Ram Nevatia IEEE International Symposium on Computer Vision, 1995, pp. 377-382.
Structure and Motion from a Sparse Set of Views M.S. Lee, Gérard Medioni Proceedings of the IEEE International Symposium on Computer Vision, Coral Gable, Florida (Nov. 1995) And IUW 96
Including Interaction in an Automated Modelling System S. Heuel. Symposium on Computer Vision, 1995 383-388
Including Interaction in an Automated Modelling System. S. Heuel. Building Extraction; Aerial Images
Detection of Buildings from Monocular Images Chungan Lin, Andres Huertas and Ram Nevatia Ascona Workshop, 1995.
Research in Model-Based Change Detection and Model Updating A. Huertas IRIS-96-340
Segmented Shape Descriptions from 3-View Stereo Parag Havaldar and Gérard Medioni - ICCV 1995.
Inference of Surfaces, 3D Curves and Junctions from Sparse 3D Data , G. Guy and Gérard Medioni SCV 1995, 599-604. And ARPA IUW 1996 pp. 1041-1050.
Recovering Surfaces, 3-D Intersections, and 3-D Junctions Using Perceptual Constraints, G. Guy and Gérard Medioni Technical Report
Pose Estimation of Mulit-Part Curved Objects, M. Zerroug and Ram Nevatia SCV95, 431-436. And IUW 96

Available Papers for 1994

Journal Papers
Recovery of 3-D Objects with Multiple Curved Surfaces from 2-D Contours Fatih Ulupinar, Ramakant Nevatia AI(67), No. 1, May 1994, pp. 1-28.

Conference Papers
Representaion and Computation of Spatial Environments for Indoor Navigation, D. Kim and Ram Nevatia CVPR 1994, 475-482
Detection of Buildings Using Perceptual Grouping and Shadows or Abstract C. Lin, A. Huertas and Ram Nevatia CVPR 1994, pp. 62-69.
A Method for Recognition and Localization of Generic Objects for Indoor Navigation, D. Kim and Ram Nevatia IUW 1994
From an Intensity Image to 3-D Segmented Descriptions, M. Zerroug and Ram Nevatia ICPR 1994, A:108-113.
Extraction of Groups for Recognition Parag Havaldar and Gérard Medioni ECCV, volume I, pp. 251-261, Stolkholm, 1994
Surface Approximation of Complex 3D Objects, C. Liao and Gérard Medioni IUW 1994
Surface Description of Complex Objects from Multiple Range Images, Y. Chen and Gérard Medioni CVPR 1994.
Surface Description of Objects from Multiple Range Images, Y. Chen and Gérard Medioni IUW 1994.
USC IMAGE UNDERSTANDING RESEARCH: 1993-1994 Ram Nevatia, Keith Price, and Gérard Medioni, IUW 1994
Model Validation for Change Detection M. Bejanin, A. Huertas, Gérard Medioni and Ram Nevatia IUW 1994
Inference of Surfaces from Sparse 3-D Data G. Guy and Gérard Medioni, IUW 1994, II:1487-1494
A Method for Recognition and Localization of Generic Objects for Indoor Navigation D. Kim and Ram Nevatia IUW 1994
Learning, Recognition and Navigation from a Sequence of Infrared Images N. Milhaud and Gérard Medioni, IUW 1994
Image Feature Extraction on Connection Machine CM-5 V. Prasanna and C.-L. Wang, IUW 1994
Knowledge Representation for Computer Vision: The Veil Project Keith Price, T. Russ and R. MacGregor, IUW 1994
Knowledge Representation for Computer Vision: The Veil Project Part 2 Part 3 Keith Price, T. Russ and R. MacGregor, Final Report (in 3 parts)
Volumetric Part Segmentation from Range Images H. Rom and Gérard Medioni, IUW 1994
Three-Dimensional Part-Based Descriptions from a Real Intensity Image M. Zerroug and Ram Nevatia IUW 1994

Available Papers for 1993

Journal Papers
Describing and Segmenting Scenes from Imperfect and Incomplete Data K.G. Rao, and Ram Nevatia CVGIP(57), No. 1, January 1993, pp. 1-23.
Perception of 3-D Surfaces from 2-D Contours, Ulupinar, F., and Ram Nevatia PAMI(15), No. 1, January 1993, pp. 3-18.

Conference Papers
Detection of Buildings from Monocular Views of Aerial Scenes using Perceptual Grouping and Shadows A. Huertas, C. Lin and Ram Nevatia ARPA Image Understanding Workshop 1993, pp. 253-260.
Segmentation and 3D Recovery of Curved Axis Generalized Cylinders in Real Intensity Images, M. Zerroug and Ram Nevatia 1993
Part Decomposition and Description of 3D Shapes, H. Rom and Gérard Medioni Report, appears in ICPR 1994, A:629-632.
IUW 93 Overview (no figures)
A Feature-Based Monocular Motion Analysis System Guided by Feedback Information Kim, Y.C., and Keith Price, CVPR 1993, pp. 744-745

Available Papers for 1992

Journal Papers
3-D Surface Description from Binocular Stereo S. D. Cochran and Gérard Medioni PAMI, Vol. 14, No. 10, October 1992, pp. 981-994
Perceptual Organization for Scene Segmentation and Description, R. Mohan, and Ram Nevatia PAMI(14), No. 6, June 1992, pp. 616-635

Conference Papers
Map-Based Localization using the Panoramic Horizon Fridtjof Stein and Gérard Medioni Report
Recovering Building Structures from Stereo Chung, C.K.R., Ram Nevatia IEEE WACV, 1992, pp. 64-73
Perceptual Grouping Using Global Saliency-Enhancing Operators G. Guy, Gérard Medioni ICPR, volume I, pp. 99-103.
The Registar Machine: From Conception to Installation Gérard Medioni, A. Huertas, M.R. Wilson WACV 1992, pp. 224-231.
Refinement of Noisy Correspondence Using Feedback from 3-D Motion Kim, Y.C., and Keith Price, CVPR 1992, pp. 836-838

Available Papers for 1991

Journal Papers
A Versatile PC-Based Range Finding System, Saint-Marc, P., Jezouin, J.L., Gérard Medioni RA(7), No. 2, April 1991, pp. 250-256.
Constraints for Interpretation of Line Drawings under Perspective Projection Fatih Ulupinar, Ramakant Nevatia CVGIP(53), No. 1, January 1991, pp. 88-96.

Available Papers for 1990

Journal Papers
Motion Estimation With More Than Two Frames, Shariat, H., and Keith Price, PAMI(12), No. 5, May 1990, pp. 417-434.
Detecting Runways in Complex Airport Scenes, A. Huertas, W. Cole, and Ram Nevatia CVGIP(51), No. 2, August, 1990, pp. 107-145.

Conference Papers

Available Papers for 1989

Journal Papers
Stereo Error Detection, Correction, and Evaluation, Mohan, R., Gérard Medioni, and Ram Nevatia PAMI(11), No. 2, February 1989, pp. 113-120.
Using Perceptual Organization to Extract 3-D Structures, R. Mohan, and R. Ram Nevatia PAMI(11), No. 11, November 1989, pp. 1121-1139
Adaptive Multiscale Feature Extraction from Range Data Parvin, B., Gérard Medioni CVGIP(45), No. 3, March 1989, pp. 346-356.
Recognizing 3-D objects using surface descriptions Fan, T.-J.; Gérard Medioni Ram Nevatia PAMI(11), No. 11, November 1989, pp. 1140-1157

Conference Papers

Available Papers for 1988

Journal Papers
Detecting Buildings in Aerial Images, A. Huertas, Ram Nevatia CVGIP(41), No. 2, February 1988, pp. 131-152.
Computing volume descriptions from sparse 3-D data Kashipati Rao, Ram Nevatia IJCV(2), No. 1, June 1988

Conference Papers
Building an Accurate Range Finder with off the Shelf Components Jean-Luc Jezouin, Philippe Saint-Marc, and Gérard Medioni CVPR pp. 195-200.

Available Papers for 1980

Journal Papers
Anything You Can Do, I Can Do Better (No You Can't) Keith Price CVGIP(36), No. 2-3, November-December 1986, pp. 387-391.
Hierarchial Matching Using Relaxation Keith Price CVGIP(34), No. 1, April 1986, pp. 66-75.
< Segment-Based Stereo Matching Gérard Medioni, Ram Nevatia CVGIP(31), No. 1, July 1985, pp. 2-18.
Visual Inspection Using Linear Features P. Kaufman, Gérard Medioni, Ram Nevatia PR(17), No. 5, 1984, pp. 485-491.
Linear Feature Extraction and Description Ram Nevatia, K. Ramesh Babu CGIP(13), No. 3, July 1980, pp. 257-269.

Available Papers for 1970-1979

Journal Papers
Picture Segmentation by a Recursive Region Splitting Method R. Ohlander, Keith Price, R. Reddy CGIP(8), 1978, pp. 313-333.
Evaluation of a Simplified Hueckel Edge-Line Detector Ram Nevatia CGIP(6), 1977, pp. 582-588.
Description and Recognition of Curved Objects Ram Nevatia, Binford, T.O., AI(8), No. 1, February 1977, pp. 77-98
Depth Measurement by Motion Stereo Ram Nevatia CGIP(5), No. 2, June 1976, pp. 203-214.

Available Theses from the USC Computer Vision Group

Human Pose Estimation from a Single View Point Matheen Siddiqui Thesis, August 2009
Motion Segmentation and Dense Reconstruction of Scenes Containing Moving Objects Observed from a Moving Camera Chang Yuan Thesis, May 2007
A Perceptual Organization Approach for Figure Completion, Binocular and Multiple-View Stereo and Machine Learning using Tensor Voting Philippos Mordohai Thesis, August, 2005
Model-Based Segmentation and Tracking of Multiple Humans in Complex Situations Tao Zhao Thesis, 2003,
A Voting-Based Computational Framework for Visual Motion Analysis and Interpretation Mircea Nicolescu Thesis, 2003, IRIS-03-419
A Unified Bayesian and Logical Approach for Video-Based Event Recognition Somboon Hongeng Thesis, May 2003,
G-Folds: An appearance based model of facial gestures for performance driven facial animation D. Fidaleo Thesis, 2003,
Multi-View 3-D Object Description with Uncertain Reasoning and Machine Learning , ZuWhan Kim Thesis. 2001
Semantic, Interactive Manipulation of Visual Data Alexandre R.J. François Ph.D. dissertation / IRIS Technical Report IRIS-01-409. University of Southern California, Los Angeles, December 2000.
Multi-view Image-Based Rendering and Modeling Qian Chen Ph.D. dissertation / IRIS Technical Report IRIS-00-388, University of Southern California, Los Angeles.
Tensor Voting in Computer Vision, Visualization, and Higher Dimensional Inferences , Chi-Keung Tang Thesis. December 1999
3-D Building Detection and Description from Multiple Intensity Images Using Hierarchical Grouping and Matching of Features, Sanjay Noronha Thesis. December 1999.
Tensor Voting for Salient Feature Inference in Computer Vision , MiSuen Lee Thesis. August 1998. USC IRIS-99-368
Perception of 3-D Objects from an Intensity Image Using Simple Geometric Models, Chung-An Lin Thesis. December 1996 IRIS-96-352
Inference of Multiple Curves and Surfaces from Sparse Data Part 1, Part 2 Part 3 Part 4 Part 5 (pages in each in reverse order) Gideon Guy Thesis. 1996 IRIS-96-345
Description of Complex Objects from Multiple Range Images, Y. Chen Thesis. 1994
Part Decomposition and Description of 3D Shapes, H. Rom Thesis 1993
Structural Indexing for Object Recognition, Fridtjof Stein Thesis August 1992
Surface Description from Binocular Stereo, Steven D. Cochran Thesis 1990.
Perception of 3-D Shape from 2-D Image of Contours Fatih Ulupinar Thesis 1991. IRIS 91-278
Correspondence Based Motion Analysis P1 Part 2 Part 3 Part 4 Salit Levy Gazit Thesis 1991.