Papers › TransTrack: Multiple Object Tracking with Transformer

TransTrack: Multiple Object Tracking with Transformer

31 Dec 2020arXiv:2012.15460archive 2025-07-28

Peize Sun, Jinkun Cao, Yi Jiang, Rufeng Zhang, Enze Xie, Zehuan Yuan, Changhu Wang, Ping Luo

In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems. TransTrack leverages the transformer architecture, which is an attention-based query-key mechanism. It applies object features from the previous frame as a query of the current frame and introduces a set of learned object queries to enable detecting new-coming objects. It builds up a novel joint-detection-and-tracking paradigm by accomplishing object detection and object association in a single shot, simplifying complicated multi-step settings in tracking-by-detection methods. On MOT17 and MOT20 benchmark, TransTrack achieves 74.5\% and 64.5\% MOTA, respectively, competitive to the state-of-the-art methods. We expect TransTrack to provide a novel perspective for multiple object tracking. The code is available at: \url{https://github.com/PeizeSun/TransTrack}.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

PeizeSun/TransTrack officialmentioned in papermentioned on GitHubpytorch report

ligaripash/KWtQ-face-alignment mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-Object Tracking Multiple Object Tracking Multiple Object Tracking with Transformer Object Object Detection Object Tracking object-detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Multi-Object Tracking	DanceTrack	TransTrack	AssA	27.5	#34 of 37	Archive leaderboard	report
Multi-Object Tracking	DanceTrack	TransTrack	DetA	72.1	#34 of 37	Archive leaderboard	report
Multi-Object Tracking	DanceTrack	TransTrack	HOTA	45.7	#34 of 37	Archive leaderboard	report
Multi-Object Tracking	DanceTrack	TransTrack	IDF1	44.8	#34 of 37	Archive leaderboard	report
Multi-Object Tracking	DanceTrack	TransTrack	MOTA	83.0	#34 of 37	Archive leaderboard	report
Multi-Object Tracking	SportsMOT	TransTrack	AssA	57.5	#15 of 22	Archive leaderboard	report
Multi-Object Tracking	SportsMOT	TransTrack	DetA	82.7	#15 of 22	Archive leaderboard	report
Multi-Object Tracking	SportsMOT	TransTrack	HOTA	68.9	#15 of 22	Archive leaderboard	report
Multi-Object Tracking	SportsMOT	TransTrack	IDF1	71.5	#15 of 22	Archive leaderboard	report
Multi-Object Tracking	SportsMOT	TransTrack	MOTA	92.6	#15 of 22	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections