• ReMOTS: Refining Multi-Object Tracking and Segmentation
  Fan Yang, Xin Chang, Chenyu Dang, Ziqiang Zheng, Sakriani Sakti, Satoshi Nakamura, Yang Wu
  1. Place Track 1
  4. Place Track 3

• PointTrack++ for Effective Online Multi-Object Tracking and Segmentation
  Zhenbo Xu, Wei Zhang, Xiao Tan, Wei Yang, Xiangbo Su, Yuchen Yuan, Hongwu Zhang, Shilei Wen, Errui Ding, Liusheng Huang
  1. Place Track 2

• IA-MOT: Instance-Aware Multi-Object Tracking with Motion Consistency
  Jiarui Cai, Yizhou Wang, Haotian Zhang, Hung-Min Hsu, Chengqian Ma, Jenq-Neng Hwang
  1. Place Track 3
  6. Place Track 1

• Re-Identification and Tracklet-Plane Matching for Multi-Object Tracking and Segmentation
  Yuchen Yuan, Xiangbo Su, Wei Zhang, Tao Wang, Wei Shi, Zhenbo Xu, Mian Peng, Xiao Tan, Weiyao Lin, Hongwu Zhang, Shilei Wen, Errui Ding
  2. Place Track 1
  3. Place Track 3

• Min-Cost Network Flow and Trajectory Fix for Multiple Objects Tracking
  Jiasheng Tang, Xiong Xiong, Chenwei Xie, Yanhao Zhang, Pichao Wang, Fan Wang, Fei Du, Liang Han, Yun Zheng, Pan Pan, Hao Li
  3. Place Track 2
  2. Place Track 3

• LIFTS: Lidar and Monocular Image Fusion for Multi-Object Tracking and Segmentation
  Haotian Zhang, Yizhou Wang, Jiarui Cai, Hung-Min Hsu, Haorui Ji, Jenq-Neng Hwang
  2. Place Track 2

• Online Multi-Object Tracking and Segmentation with GMPHD Filter and Simple Affinity Fusion
  Young-min Song, Moongu Jeon
  Gwangju Institute of Science and Technology, Gwangju 61005, South Korea
  8. Place Track 1
  4. Place Track 2
  5. Place Track 3

• Fast Multiple Object Tracking Using Siamese Random Forest without Online Tracker Updating
  Jimi Lee, Sangwon Kim, Byoung Chul Ko
  Dept. of Computer Engineering, Keimyung University, Daegu, Korea 42601
  7. Place Track 3

• EagerMOT: Real-time 3D Multi-Object Tracking and Segmentation via Sensor Fusion
  Aleksandr Kim, Aljoša Ošep, Laura Leal-Taixé
  8. Place Track 2

• Tracking by Segmentation: Person-ReID and Optical Flow Based Offline Tracker for the MOTSChallenge 2020
  Yang Liu, Lyuwei Wang, Yuan Zhao, Haifeng Shen, Jieping Ye
  9. Place Track 1

• Application of SORT on Multi-Object Tracking and Segmentation
  Franz Koeferl, Johannes Link, Bjoern Eskofier
  Machine Learning and Data Analytics Lab, University of Erlangen-Nürnberg (FAU)
  12. Place Track 3

• Bernt Schiele - The Bright and Dark Sides of Computer Vision and Machine Learning Challenges and Opportunities for Robustness and Security

• Xin Wang - Motion Understanding via Heterogeneous Multitask Learning

• Alexei Efros - Using Video to Learn about Visual Correspondence

• Live stream!

• Schedule and Keynote Speaker list can be found here

• Thank you to all challenge participants. Requests for short papers and videos have now been sent out.
• Paper and video submission deadline: June 11, 2020

Challenge Details

Dates

For this 5th edition of our Benchmarking Multi-Target Tracking (MOTChallenge) Workshop, we want to push the limits of tracking by focusing on tracking at pixel accurate level. To achieve this we introduce the MOTS20 (Multi-Object Tracking and Segmentation 2020) benchmark. For this we have densely annotated 4 training sequences and 4 challenging test sequences from the challenging MOT17 dataset with pixel accurate segmentation masks. The data features crowded pedestrian scenes with many difficult cases of occlusion.

In order to enourage research towards end-to-end systems which solve the whole MOTS task together, for this challenge the partipants are not required to use "public detections", but can rather use any detector. We also include a challenge track where we provide state-of-the-art segmentation predictions and participants can focus on the tracking aspect without having to perform detection and segmentation.

We also host another challenge track on the KITTI-MOTS dataset, where methods are required to detect, segment and track both cars and people in an autonomous vehicle setting.

Our workshop has three major goals: (i) Analyzing the performance of state-of-the-art detection, tracking, and segmentation algorithms, and their combinations on crowded pedestrian scenes, (ii) opening new Multi-Object Tracking and Segmentation Challenges on 4 the MOTS20 and KITTI MOTS datasets, and (iii) discussing the limitations of current methods for producing accurate segmentation masks under severe occlusion scenarios.

An important part of the workshop will also be dedicated to a discussion among participants on how to improve Multi-Object Tracking and Segmentation evaluation and ideas on how to expand the current benchmark. These discussions in previous editions of the workshop have helped us tremendously in shaping MOTChallenge and significantly contributed to creating a widely used and perhaps the most popular multi-object tracking benchmark in the community.

For any questions, please contact Paul Voigtlaender