| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://reid-mct.github.io/2017/
x-github-request-id: D9E5:1F53DD:805EA2:900F96:6951A36F
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 21:38:56 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210050-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766957936.070316,VS0,VE199
vary: Accept-Encoding
x-fastly-request-id: ad1d9234110db7a88bd74f485c27f68775fd694f
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Fri, 01 Feb 2019 12:41:21 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"5c543e71-4bf7"
expires: Sun, 28 Dec 2025 21:48:56 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 3A13:318CF6:7F50FE:8EFEA9:6951A370
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 21:38:56 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210050-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766957936.283558,VS0,VE219
vary: Accept-Encoding
x-fastly-request-id: 9edd107342bd0bde8c51b93d444899f12281d621
content-length: 5612
Target Re-Identification and Multi-Target Multi-Camera Tracking
Target Re-Identification and
In conjunction with CVPR 2017
Given a set of videos taken by multiple cameras, multi-target multi-camera tracking places tight bounding boxes around all targets in the videos and partitions the boxes into sets called trajectories. A trajectory is the set of all boxes that bound a unique target, ordered by time.
These two problems are clearly different. However, they share several common aspects as well. Here, you can find some of the (dis)similarities that we could think of. Can you come up with more?
Rita Cucchiara (University of Modena and Reggio Emilia)
Wen Gao (Peking University)
Shaogang Gong (Queen Mary University of London)
Thomas S. Huang (University of Illinois Urbana-Champaign)
Ergys Ristani (Duke University)
Francesco Solera (University of Modena and Reggio Emilia)
Qi Tian (University of Texas at San Antonio)
Carlo Tomasi (Duke University)
Program committee chairs:
Simone Calderara (University of Modena and Reggio Emilia)
Cees G.M. Snoek (University of Amsterdam)
Jingdong Wang (Microsoft Research)
Shiliang Zhang (Peking University)
Program committee members: Horst Bischof, Roman Pflugfelder, Octavia Camps, Amit Roy-Chowdhury, Andrea Cavallaro, Peter Roth, Chen Change Loy, Ling Shao, Dimitrios Makris, Slawomir Bak, Ratnesh Kumar, Gerard Medioni, Xinchao Wang, Christian Micheloni, Liang Zheng and Vittorio Murino.
ReID and MTMCT
Dates:
Submission deadline: 2017 April 7
Rebuttal period: 2017 April 17-21
Camera ready deadline: 2017 April 27
Workshop: July 21, 2017
Navigation:
1st Workshop on
Target Re-Identification and
Multi-Target Multi-Camera Tracking
In conjunction with CVPR 2017
July 2017, Honolulu
This workshop brings together researchers from two subfields of computer vision that have seen growing activity in
the past few years: Target Re-Identification (ReID) and Multi-Target Multi-Camera Tracking (MTMCT). This workshop
explores opportunities for cross-fertilization between these two thriving and important subfields of computer vision
and aims to deepen discussions on future directions.
Program
| Start Time | Paper/Talk Title | Speaker/Author(s) |
| 8:45 | Welcome | - |
| 9:00 | Invited Talk: Towards Learning Universal Feature Representations for Person Search | Xiaogang Wang (Chinese University of Hong Kong) |
| 9:30 | Invited Talk: MOTChallenge: Unifying Detection and Multi-Target Tracking Benchmarks | Laura Leal-Taixé, Anton Milan (Technical University Munich, University of Adelaide) |
| 10:00 | Track-Clustering Error Evaluation for Track-Based Multi-Camera Tracking System Employing Human Re-identification | Chih-Wei Wu, Meng-Ting Zhong, Yu Tsao, Shao-wen Yang, Yen-kuang Chen, Shao-Yi Chien |
| 10:15 | DukeMTMC4ReID: A Large-Scale Multi-Camera Person Re-Identification Dataset | Mengran Gou, Srikrishna Karanam, Wenqian Liu, Octavia Camps, Richard Radke |
| 10:30 | Morning Break | - |
| 11:00 | Invited Talk: Learning to Segment Moving Objects | Cordelia Schmid (INRIA) |
| 11:30 | Invited Talk: How Far Are We From Real-World Person Re-Identification | Ziyan Wu (Siemens) |
| 12:00 | Person Re-Identification by Deep Learning Attribute-Complementary Information | Arne Schumann, Rainer Stiefelhagen |
| 12:15 | Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters | Lucas Beyer, Stefan Breuers, Vitaly Kurin, Bastian Leibe |
| 12:30 | Lunch Break | - |
| 14:00 | Invited Talk: Asymmetrical Person Re-Identification | Wei-Shi Zheng (Sun Yat-sen University) |
| 14:30 | Invited Talk: Practices of Large-Scale Target Re-Identification | Xian-Sheng Hua (Alibaba) |
| 15:00 | Spotlights | |
| - | Video-based Person Re-identification by Deep Feature Guided Pooling | Youjiao Li, Li Zhuo, Jiafeng Li, Jing Zhang, Xi Liang, Qi Tian |
| - | A Dataset for Persistent Multi-Target Multi-Camera Tracking in RGB-D | Ryan Layne, Sion Hannuna, Massimo Camplani, Jake Hall, Timothy Hospedales, Tao Xiang, Majid Mirmehdi, Dima Damen |
| - | Trajectory Ensemble: Multiple Persons Consensus Tracking across Non-overlapping Multiple Cameras over Randomly Dropped Camera Networks | Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase |
| - | Deep Spatial-Temporal Fusion Network for Video-Based Person Re-Identification | Lin Chen, Hua Yang, Ji Zhu, Qin Zhou, Shuang Wu, Zhiyong Gao |
| 15:30 | Poster Session (Afternoon Break) | - |
| 16:15 | Invited Talk: Multi-Target Tracking in Non-Overlapping Cameras Using Constraint Dominant Sets | Mubarak Shah (University of Central Florida) |
| 16:45 | Invited Talk: Scalability in Camera Networks: Leveraging the Network for Person Re-Identification | Amit Roy-Chowdhury (University of California Riverside) |
| 17:15 | Panel Discussion | Moderator: Carlo Tomasi (Duke University) Panelists Shaogang Gong (Queen Mary University of London) Laura Leal-Taixé (Technical University Munich) Anton Milan (University of Adelaide) Amit K. Roy Chowdhury (University of California Riverside) Mubarak Shah (University of Central Florida) Ziyan Wu (Siemens) Wei-Shi Zheng (Sun Yat-Sen University) Octavia Camps (Northeastern University) Xiaogang Wang (Chinese University of Hong Kong) |
| 17:55 | Closing Remarks | Carlo Tomasi |
Call for papers
This one day workshop will host invited speakers, poster sessions and oral presentations. We encourage authors to explore pollination between the fields of ReID and MTMCT and take on research questions, rather than just obtaining state-of-the-art results on benchmarks. Examples of such questions are:- How much do initial detections influence MTMCT or ReID?
- How and which ReID descriptors can be used by MTMCT systems?
- What can we learn by evaluating a MTMCT system in terms of ReID, and vice-versa?
- What makes these problems hard (and easy)?
- How can ReID and MTMCT benefit each other?
- How can MTMCT and ReID capitalize on recent large-scale datasets?
- How to deal with large-scale indexing/optimization in ReID and MTMCT?
- Do we need largely annotated datasets for ReID and MTMCT?
- Do semantic attributes help in matching identities in ReID and MTMCT?
- How can re-ranking schemes improve ReID performance?
Problem definitions and motivation
Let a query be an image that tightly bounds a single instance of a target of interest (people, vehicles, etc.). Assume that a gallery contains images of several targets in this format as well as distractor images with arbitrary content. Target re-identification retrieves all and only the gallery images of the same target as the query.Given a set of videos taken by multiple cameras, multi-target multi-camera tracking places tight bounding boxes around all targets in the videos and partitions the boxes into sets called trajectories. A trajectory is the set of all boxes that bound a unique target, ordered by time.
These two problems are clearly different. However, they share several common aspects as well. Here, you can find some of the (dis)similarities that we could think of. Can you come up with more?
Some differences:
- The gallery in target re-identification may or may not be a set of videos and both targets and queries are assumed to have been isolated ahead of time. The input to multi-target multi-camera tracking on the other hand is necessarily a set of videos.
- Multi-target multi-camera tracking matches all targets symmetrically while target re-identification distinguishes between query and response explicitly.
- They assume a semantic notion of “identity” in that only ground truth can tell if the targets in two bounding boxes share the same identity.
- They could benefit from a detector that separates targets from non-targets.
- When the gallery in target re-identification is a set of videos, both problems can use similar pre-processing techniques. These might rely on knowing the camera topology, considering time elapsed between observations, modeling changes in illumination and viewpoint across cameras, etc.
- Both problems require annotated databases of videos or images and some databases can work for both problems.
- Some components of the solution to either problem can be used to solve the other.
Submission
To submit a new paper to the workshop, you have to do so through the CMT website. The workshop paper submissions should be in the same format as the main conference. Please refer to the CVPR 2017 author guidelines for more details.
Invited speakers
Xiaogang Wang Chinese University of Hong Kong
Laura Leal-Taixé Technical University Munich
Anton Milan University of Adelaide
Cordelia Schmid INRIA
Ziyan Wu Siemens
Wei-Shi Zheng Sun Yat-sen University
Xian-Sheng Hua Alibaba
Mubarak Shah University of Central Florida
Amit Roy-Chowdhury University of California Riverside
People involved
Organizers:
Rita Cucchiara (University of Modena and Reggio Emilia)
Wen Gao (Peking University)
Shaogang Gong (Queen Mary University of London)
Thomas S. Huang (University of Illinois Urbana-Champaign)
Ergys Ristani (Duke University)
Francesco Solera (University of Modena and Reggio Emilia)
Qi Tian (University of Texas at San Antonio)
Carlo Tomasi (Duke University)
Program committee chairs:
Simone Calderara (University of Modena and Reggio Emilia)
Cees G.M. Snoek (University of Amsterdam)
Jingdong Wang (Microsoft Research)
Shiliang Zhang (Peking University)
Program committee members: Horst Bischof, Roman Pflugfelder, Octavia Camps, Amit Roy-Chowdhury, Andrea Cavallaro, Peter Roth, Chen Change Loy, Ling Shao, Dimitrios Makris, Slawomir Bak, Ratnesh Kumar, Gerard Medioni, Xinchao Wang, Christian Micheloni, Liang Zheng and Vittorio Murino.