ACCV Workshop on Detection and Tracking in Challenging Environments (DTCE)

(in conjunction with ACCV 2012, Daejeon, Korea)

Organizers
Bohyung Han, POSTECH
Jongwoo Lim, Hanyang Univ.
Bill Triggs, CNRS
Ahmed Elgammal, Rutgers
Jason Corso, Buffalo


Program Committee

Serge Belongie, UCSD
Terrence Chen, Siemens Corp. Research
Naresh Cuntoor, Kitware Larry Davis, U Maryland
Jan Feyereisl, POSTECH Kikuo Fujimura, Honda Research Inst. Abhinav Gupta, CMU Iasonas Kokkinos, Ecole Centrale Paris
Tony X. Han, Missouri
Ser-Nam Lim, GE Global Research
Haibin Ling, Temple Univ. Sangmin Oh, Kitware David Ross, Google Yoichi Sato, U Tokyo
Zhuowen Tu, MSRA / UCLA
Jianxin Wu, NTU Ming-hsuan Yang, UC Merced Kuk-Jin Yoon, GIST
Lei Zhang, Hong Kong Polytechnic Univ.

 
Program (Nov. 6th Tuesday)
 8:50 - 9:00 Opening and Welcome 
 9:00 - 10:00 Keynote presentation Prof. Ming-hsuan Yang (UC Merced)
 10:00 - 10:20 Coffee break
 10:20 - 11:40 Morning session (4 papers x 20 min.)
- Disagreement-Based Multi-System Tracking Quannan Li, Xinggang Wang, Wei Wang, Yuan Jiang, Zhi-Hua Zhou, Zhuowen Tu - Monocular Pedestrian Tracking from a Moving Vehicle Zipei Fan, Zeliang Wang, Jinshi Cui, Franck Davoine, Huijing Zhao, Hongbin Zha - Tracking the Untrackable: How to Track When Your Object Is Featureless Karel Lebeda, Jiri Matas, Richard Bowden - A Robust Particle Tracker via Markov Chain Monte Carlo Posterior Sampling Fasheng Wang, Mingyu Lu, Liran Shen
 11:40 - 13:00 Lunch break
 13:00 - 14:30 Poster session (90 min.) - Object Tracking across Non-overlapping Cameras using Adaptive Models Xiaotang Chen, Kaiqi Huang, Tieniu Tan - Novel Adaptive Eye Detection and Tracking for Challenging Lighting Conditions Mahdi Rezaei, Reinhard Klette - Motion Segmentation by Velocity Clustering with Estimation of Subspace Dimension Liangjing Ding, Adrian Barbu, Anke Meyer-Baese - Disagreement-Based Multi-System Tracking Quannan Li, Xinggang Wang, Wei Wang, Yuan Jiang, Zhi-Hua Zhou, Zhuowen Tu - Efficient Model based Single and Double Thresholding for Real Time Recognition Dror Aiger, Silvio Jamil Ferzoli Guimares - Iterative Hypothesis Testing for Multi-object Tracking with Noisy/Missing Appearance Features Amit Kumar K.C., Damien Delannay, Laurent Jacques, Christophe De Vleeschouwer - A Framework for Inter-Camera Association of Multi-Target Trajectories by Invariant Target Models Shahar Daliyot, Nathan S. Netanyahu - Combining Fast Extracted Edge Descriptors and Feature Sharing for Rapid Object Detection Yali Li, Fei He, Wenhao Lu, Shengjin Wang - Colour Descriptors for Tracking in Spatial Augmented Reality Thijs Kooi, Francois de Sorbier, Hideo Saito - A Robust Particle Tracker via Markov Chain Monte Carlo Posterior Sampling Fasheng Wang, Mingyu Lu, Liran Shen - Monocular Pedestrian Tracking from a Moving Vehicle Zipei Fan, Zeliang Wang, Jinshi Cui, Franck Davoine, Huijing Zhao, Hongbin Zha - Covariance Descriptor Multiple Object Tracking and Re-Identi cation with Colorspace Evaluation Andrés Romero, Michèle Gouiffés, Lionel Lacassagne - Tracking the Untrackable: How to Track When Your Object Is Featureless Karel Lebeda, Jiri Matas, Richard Bowden - Obstacles Extraction Using a Moving Camera Shaohua Qian, Joo Kooi Tan, Hyoungseop Kim, Seiji Ishikawa, Takashi Morie - Scene Text Detection and Tracking for a Camera-equipped Wearable Reading Assistant for the Blind Faustin Pégeot, Hideaki Goto
 14:30 - 14:50 Coffee break
14:50 - 16:10 Afternoon session (4 papers x 20 min.) - Object Tracking across Non-overlapping Cameras using Adaptive Models Xiaotang Chen, Kaiqi Huang, Tieniu Tan - Efficient Model based Single and Double Thresholding for Real Time Recognition Dror Aiger, Silvio Jamil Ferzoli Guimares - Combining Fast Extracted Edge Descriptors and Feature Sharing for Rapid Object Detection Yali Li, Fei He, Wenhao Lu, Shengjin Wang - Motion Segmentation by Velocity Clustering with Estimation of Subspace Dimension Liangjing Ding, Adrian Barbu, Anke Meyer-Baese
 16:10 - 16:30 Closing

Paper Decision The list of accepted papers is as follows. 
Note that all accepted papers including oral papers need to be presented in the poster session
The reviews and meta-review of each paper can be found in DTCE 2012 CMT system now. If your paper is accepted, at least one of the authors should register to ACCV as regular rate by 10/10 (Thursday) and the final camera-ready version of paper should be submitted to DTCE 2012 CMT system by 10/17 (Wednesday). The guideline for the registration and the preparation of the camera-ready version can be found at http://www.accv2012.org/sub/sub04_01.asp and http://www.accv2012.org/sub/sub03_02.asp, respectively.
  • Object Tracking across Non-overlapping Cameras using Adaptive Models [oral]
  • Novel Adaptive Eye Detection and Tracking for Challenging Lighting Conditions 
  • Motion Segmentation by Velocity Clustering with Estimation of Subspace Dimension [oral]
  • Disagreement-Based Multi-System Tracking [oral]
  • Efficient Model Based Single and Double Thresholding for Real Time Recognition [oral]
  • Iterative Hypothesis Testing for Multi-object Tracking with Noisy/Missing Appearance Features 
  • A Framework for Inter-camera Association of Multi-target Trajectories by Invariant Target Models 
  • Combining Fast Extracted Edge Descriptors and Feature Sharing for Rapid Object Detection [oral]
  • Colour Descriptors for Tracking in Spatial Augmented Reality
  • A Robust Particle Tracker via Markov Chain Monte Carlo Posterior Sampling [oral]
  • Monocular Pedestrian Tracking from a Moving Vehicle [oral]
  • Covariance Descriptor Multiple Object Tracking and Re-Identification with Colorspace Evaluation
  • Tracking the Untrackable: How to Track When Your Object Is Featureless [oral]
  • Obstacles Extraction Using a Moving Camera 
  • Scene Text Detection and Tracking for a Camera-Equipped Wearable Reading Assistant for the Blind
Workshop Introduction
Recent progress in computer vision opened a lot of new possibilities in robust visual tracking and detection of humans and objects, which can be used in many practical applications.
This workshop aims to bring researchers working on challenging real world problems together to promote their recent achievements and provide a place to share their experiences and visions with others.
This workshop calls for submissions of original research paper on (but not limited to) the following topics:
Sensing / Data collection with - multiple and heterogeneous sensors such as multi-camera systems, mocap devices, depth cameras, etc. - benchmark dataset
Detection and tracking with - large deformations and appearance changes - occlusion and background clutter - severe illumination changes and viewpoint changes - motion blurs and noises, data in compressed domain
Methodology - appearance and motion model for robust tracking - Bayesian inference for object detection - deep learning for visual/motion features - hybrid methods
Applications - visual surveillance - human-computer and human-robot interaction - human activity detection in large-scale video dataset
Important Dates
Submission of full papers: Notification of acceptance: Camera-ready copy: Workshop date: Sep. 6. 2012 Oct. 6. 2012 Oct. 17. 2012 Nov. 6. 2012

Paper Submission If the paper is submitted for review to ACCV 2012, you can simply mark the checkbox at "Object Detection and Tracking in Challenging Env." under "Which workshop do you like your paper to be considered?". To submit the paper directly to the workshop, use the following workshop CMT site. https://cmt.research.microsoft.com/DTCE2012/ The submission guidelines for the workshop is same as the main conference. Instructions and necessary author kits are available at the submission guideline page of the ACCV 2012. Publication All accepted papers will be included in ACCV2012 USB proceeding and published in Springer's Lecture Note in Computer Science after conference. If you have any questions about the workshop, feel free to contact the organizers (dtce2012@gmail.com).