SOTAVerified|Agents Browse Leaderboard About

Multiple Object Tracking

Multiple Object Tracking is the problem of automatically identifying multiple objects in a video and representing them as a set of trajectories with high accuracy.

Source: SOT for MOT

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 141–150 of 318 papers

Title	Date	Tasks	Status	Hype	Score
Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOT	Jul 25, 2024	Knowledge DistillationMulti-Object Tracking	CodeCode Available	0	5
MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking	Apr 8, 2015	3D ReconstructionMultiple Object Tracking	CodeCode Available	0	5
Lucid Data Dreaming for Video Object Segmentation	Mar 28, 2017	Multiple Object TrackingObject	CodeCode Available	0	5
Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detection	May 21, 2025	3D Pedestrian TrackingMultiple Object Tracking	CodeCode Available	0	5
Appearance-free Tripartite Matching for Multiple Object Tracking	Aug 9, 2020	Cell TrackingMultiple Object Tracking	CodeCode Available	0	5
Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking	Feb 26, 2018	Multi-Object TrackingMultiple Object Tracking	CodeCode Available	0	5
Joint Monocular 3D Vehicle Detection and Tracking	Nov 26, 2018	3D Object Detection3D Pose Estimation	CodeCode Available	0	5
Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Tracking	Feb 15, 2024	Deep LearningMulti-Object Tracking	CodeCode Available	0	5
Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications	Jul 1, 2017	Combinatorial OptimizationMultiple Object Tracking	—Unverified	0	0
Does Video Compression Impact Tracking Accuracy?	Feb 2, 2022	Multiple Object TrackingObject	—Unverified	0	0

Show:10 25 50

← PrevPage 15 of 32Next →

All datasets KITTI Test (Online Methods)BDD100K val BDD100K test CroHD SportsMOT KITTI Test (Offline Methods)RADIATE Waymo Open Dataset GMOT-40 UA-DETRAC YouTube-Hands

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	SRK ODESA	MOTA	90.03	—	Unverified
2	MOSTFusion	MOTA	84.83	—	Unverified
3	mmMOT-normal	MOTA	84.77	—	Unverified
4	3DT	MOTA	84.52	—	Unverified
5	Mono3DT	MOTA	84.52	—	Unverified
6	RRC-IIITH	MOTA	84.24	—	Unverified
7	RobMOT (Dynamic)	HOTA	81.8	—	Unverified
8	RobMOT	HOTA	81.76	—	Unverified
9	MCTrack	HOTA	81.07	—	Unverified
10	KFDL	HOTA	81.06	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ByteTrack	mMOTA	45.5	—	Unverified
2	UNINEXT-H	mMOTA	44.2	—	Unverified
3	MOTRv2	mMOTA	43.6	—	Unverified
4	QDTrack	mMOTA	42.1	—	Unverified
5	ContrasTR	mMOTA	41.7	—	Unverified
6	Unicorn	mMOTA	41.2	—	Unverified
7	TETer	mMOTA	39.1	—	Unverified
8	QDTrack	mMOTA	36.6	—	Unverified
9	Adaptive-searching -windows Tracker	mMOTA	34.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ContrasTR	mMOTA	42.8	—	Unverified
2	SUSHI	mMOTA	40.2	—	Unverified
3	ByteTrack	mMOTA	40.1	—	Unverified
4	QDtrack	mMOTA	35.6	—	Unverified
5	Yu et al.	mMOTA	26.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PP-Tracking	MOTA	72.6	—	Unverified
2	OC-SORT	MOTA	67.9	—	Unverified
3	HeadHunter-T	MOTA	63.6	—	Unverified
4	Tracktor	MOTA	58.9	—	Unverified
5	SORT	MOTA	46.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MOTIP (Deformable DETR, with SportsMOT val)	HOTA	75.2	—	Unverified
2	TrackSSM	HOTA	74.4	—	Unverified
3	MOTIP (Deformable DETR)	HOTA	71.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MCTrack	HOTA	82.75	—	Unverified
2	BiTrack	HOTA	82.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SIRA	MOTA	47.79	—	Unverified
2	TempoRadar	MOTA	37.91	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	QDTrack	MOTA	55.6	—	Unverified
2	RetinaTrack	MOTA	44.92	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MAC-SORT	HOTA	58.58	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	EB & TADN	MOTA	23.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	HandLer	MOTA	70	—	Unverified