Papers › MOTR: End-to-End Multiple-Object Tracking with Transformer

MOTR: End-to-End Multiple-Object Tracking with Transformer

7 May 2021arXiv:2105.03247archive 2025-07-28

Fangao Zeng, Bin Dong, Yuang Zhang, Tiancai Wang, Xiangyu Zhang, Yichen Wei

Temporal modeling of objects is a key challenge in multiple object tracking (MOT). Existing methods track by associating detections through motion-based and appearance-based similarity heuristics. The post-processing nature of association prevents end-to-end exploitation of temporal variations in video sequence. In this paper, we propose MOTR, which extends DETR and introduces track query to model the tracked instances in the entire video. Track query is transferred and updated frame-by-frame to perform iterative prediction over time. We propose tracklet-aware label assignment to train track queries and newborn object queries. We further propose temporal aggregation network and collective average loss to enhance temporal relation modeling. Experimental results on DanceTrack show that MOTR significantly outperforms state-of-the-art method, ByteTrack by 6.5% on HOTA metric. On MOT17, MOTR outperforms our concurrent works, TrackFormer and TransTrack, on association performance. MOTR can serve as a stronger baseline for future research on temporal modeling and Transformer-based trackers. Code is available at https://github.com/megvii-research/MOTR.

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

megvii-model/MOTR officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

megvii-research/motr officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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 Detection Object Tracking

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Multi-Object Tracking	DanceTrack	MOTR	AssA	40.2	#30 of 37	Archive leaderboard	report
Multi-Object Tracking	DanceTrack	MOTR	DetA	73.5	#30 of 37	Archive leaderboard	report
Multi-Object Tracking	DanceTrack	MOTR	HOTA	54.2	#30 of 37	Archive leaderboard	report
Multi-Object Tracking	DanceTrack	MOTR	IDF1	51.5	#30 of 37	Archive leaderboard	report
Multi-Object Tracking	DanceTrack	MOTR	MOTA	79.7	#30 of 37	Archive leaderboard	report
Multi-Object Tracking	MOT16	MOTR	IDF1	67.0	#12 of 24	Archive leaderboard	report
Multi-Object Tracking	MOT16	MOTR	MOTA	66.8	#12 of 24	Archive leaderboard	report
Multi-Object Tracking	MOT17	MOTR	IDF1	67.0	#38 of 48	Archive leaderboard	report
Multi-Object Tracking	MOT17	MOTR	MOTA	67.4	#38 of 48	Archive leaderboard	report
Multi-Object Tracking	MOT17	MOTR	e2e-MOT	Yes	#38 of 48	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 Convolution Dense Connections Detr Dropout Feedforward Network 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