Multi-Object Tracking

Also known as MOT

Multi-object tracking studies how to detect multiple objects and keep their identities consistent as they move, disappear, and reappear in video, supporting applications such as autonomous driving, surveillance, and biological monitoring. Common approaches combine detection with motion prediction and data association, using tools such as Kalman filters, appearance-based re-identification, and graph matching; newer end-to-end Transformer and query-based trackers learn detection and association together. Evaluation spans crowded pedestrian benchmarks such as MOT17, MOT20, and DanceTrack, as well as 3D driving, aerial, multi-camera, and specialized animal or cell-tracking settings. A central challenge is preserving identities under long occlusions, dense interactions, and domain shifts while keeping methods efficient and making benchmark scores reflect real deployment conditions.

Latest papers

189 papers19 papers in the last four weeks, down 41% on the four weeks before. 0.1% of all new papers.

DepTR-MOT: Unveiling the Potential of Depth-Informed Trajectory Refinement for Multi-Object Tracking
Sep 22, 2025Buyin Deng, Lingxin Huang, Kai Luo +2Multi-Object Tracking Robotic Perception
Decentralized Vision-Based Autonomous Aerial Wildlife Monitoring
Aug 20, 2025Makram Chahine, William Yang, Alaa Maalouf +6Multi-Robot Coordination Drone-Based Wildlife Monitoring
Project CETI, New York 10003, NY, USA · CSAIL MIT, Cambridge MA 02139, USA · SEAS Harvard University, Boston MA 02134, USA
SoccerTrack v2: A Full-Pitch Panoramic Video Dataset for Game State Reconstruction and Ball Action Spotting
Aug 3, 2025Atom Scott, Ikuma Uchida, Kento Kuroda +2Sports Video Analysis Multi-Object Tracking
Nagoya University∗ · University of Tsukuba
Towards Accurate State Estimation: Motion Dynamics Kalman Filter for 3D Multi-Object Tracking
May 12, 2025Mohamed Nagy, Naoufel Werghi, Bilal Hassan +2Kalman Filtering 3D MOT
Khalifa University, Abu Dhabi, UAE · New York University of Abu Dhabi
Cell as Point: One-Stage Framework for Efficient Cell Tracking
Nov 22, 2024Yaxuan Song, Jianan Fan, Heng Huang +2Multi-Object Tracking
School of Computer Science, The University of Sydney, Sydney, 2006, NSW, Australia · Department of Computer Science, University of Maryland College Park, College Park, 20742, Maryland, United States · Microsoft, Redmond, 98052, Washington, United States
Multi-view Optimal Transport for Multi-view Crowd Localization and Tracking
Sep 3, 2024Kaiyi Zhang, Qi Zhang, Jixuan Chen +2Multi-Object Tracking Optimal Transport
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), China · Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China · Department of Computer Science, City University of Hong Kong, HK SAR, China
XS-VID: A Large-Scale Benchmark for Small Object Detection and Tracking in Videos
Jul 25, 2024Jiahao Guo, Ziyang Xu, Lianjun Wu +3Small Object Detection Video Object Detection
Huazhong University of Science and Technology
SSP-GNN: Learning to Track via Bilevel Optimization
Jul 5, 2024Griffin Golias, Masa Nakura-Fan, Vitaly AblavskyGraph Neural Networks Visual Object Tracking
Applied Physics Laboratory University of Washington Seattle, WA 98105 USA · Paul G. Allen School of Computer Science University of Washington Seattle, WA 98105 USA
Referring Multi-Object Tracking with Diverse Dynamic Expressions
Jun 7, 2024Yani Zhang, Dongming Wu, Wencheng Han +3Referring MOT Multi-Object Tracking
School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan 430072, China. · Multimedia Lab (MMLab), Department of Information Engineering, the Chinese University of Hong Kong, Hong Kong, China. · State Key Laboratory of Internet of Things for Smart City, Department of Computer and Information Science, University of Macau, Macau, China. +1

Sep 22, 2025J/K move · Enter open · S save

DepTR-MOT: Unveiling the Potential of Depth-Informed Trajectory Refinement for Multi-Object Tracking

Buyin Deng, Lingxin Huang, Kai Luo, Fei Teng+1

Multi-Object Tracking Robotic Perception

Open paper AskPDF arXiv

Visual Multi-Object Tracking (MOT) is a crucial component of robotic perception, yet existing Tracking-By-Detection (TBD) methods often rely on 2D cues, such as bounding boxes and motion modeling, which struggle under occlusions and close-proximity interactions. Trackers relying on these 2D cues are particularly unreliable in robotic environments, where dense targets and frequent occlusions are common. While depth information has the potential to alleviate these issues, most existing MOT datasets lack depth annotations, leading to its underexploited role in the domain. To unveil the potential of depth-informed trajectory refinement, we introduce DepTR-MOT, a category-agnostic DETR-based detector enhanced with instance-level depth information. Specifically, we propose two key innovations: (i) foundation model-based instance-level soft depth label supervision, which refines depth prediction, and (ii) the distillation of dense depth maps to maintain global depth consistency. These strategies enable DepTR-MOT to embed instance-level depth awareness into detector and to output instance-level depth during inference. All designs strictly follow the prevailing Tracking-By-Detection (TBD) paradigm, requiring no additional training or inference stages. By incorporating depth cues, our method enhances the robustness of the TBD paradigm and effectively resolves occlusion and close-proximity challenges. Experiments on the QuadTrack, DanceTrack, SportsMOT, and VisDrone19 datasets demonstrate the effectiveness of our approach, achieving HOTA scores of 27.59, 44.939, 61.2, and 42.5, respectively. These consistent gains across aerial, sports, and surveillance platforms highlight the advantages of our method in handling occlusion and close-proximity challenges in robotic tracking. The source code will be made publicly available at https://github.com/warriordby/DepTR-MOT.