Browse State-of-the-Art › Multi-Object Tracking

Multi-Object Tracking

279 papers with code · 22 benchmarks · 43 datasets archive 2025-07-28

Computer Vision

Multi-Object Tracking is a task in computer vision that involves detecting and tracking multiple objects within a video sequence. The goal is to identify and locate objects of interest in each frame and then associate them across frames to keep track of their movements over time. This task is challenging due to factors such as occlusion, motion blur, and changes in object appearance, and is typically solved using algorithms that integrate object detection and data association techniques.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

22 leaderboard tables shown for this task, 22 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 22 until expanded.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
MOT17 (48 rows) TrackTrack Focusing on Tracks for Online Multi-Object Tracking code — Compare
DanceTrack (37 rows) SAM2MOT SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation code — Compare
MOT20 (27 rows) BoostTrack++ BoostTrack++: using tracklet information to detect more objects in... code — Compare
MOT16 (24 rows) PPTracking PP-YOLOE: An evolved version of YOLO code Syntology ran 5 of 27 samples · 22 unverified Compare
SportsMOT (22 rows) DeepEIoU + GTA GTA: Global Tracklet Association for Multi-Object Tracking in Sports code — Compare
JRDB (10 rows) OmniTrack Omnidirectional Multi-Object Tracking code — Compare
TAO (9 rows) AED (Co-DETR) Associate Everything Detected: Facilitating Tracking-by-Detection... code — Compare
Wildtrack (9 rows) MCBLT MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos — — Compare
2024 AI City Challenge (8 rows) MCBLT MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos — — Compare
MOTS20 (6 rows) ReMOTS ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation — — Compare
2D MOT 2015 (4 rows) GSDT Joint Object Detection and Multi-Object Tracking with Graph Neural Networks code — Compare
HiEve (4 rows) CSTrack Rethinking the competition between detection and ReID in... code Syntology ran 2 of 15 samples · 13 unverified Compare
PersonPath22 (4 rows) ByteTrack Large Scale Real-World Multi-Person Tracking code Syntology ran 0 of 3 samples · 3 unverified Compare
SeaDronesSee (3 rows) Tracktor++ SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water — — Compare
2DMOT15 (2 rows) FairMOT FairMOT: On the Fairness of Detection and Re-Identification in... code Syntology ran 8 of 53 samples · 45 unverified Compare
MOT15 (2 rows) Baseline+MFW Track to Detect and Segment: An Online Multi-Object Tracker code Syntology ran 4 of 4 samples · 0 unverified Compare
MultiviewX (2 rows) TrackTacular (Bilinear Sampling) Lifting Multi-View Detection and Tracking to the Bird's Eye View code — Compare
UAVDT (2 rows) SAM2MOT SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation code — Compare
BDD100K (1 row) CO-MOT Bridging the Gap Between End-to-end and Non-End-to-end... code — Compare
MOT15_3D (1 row) MPLT Using Panoramic Videos for Multi-person Localization and Tracking... code — Compare
Synthehicle (1 row) Baseline Synthehicle: Multi-Vehicle Multi-Camera Tracking in Virtual Cities code — Compare
VisDrone2019 (1 row) DroneMOT DroneMOT: Drone-based Multi-Object Tracking Considering Detection... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

43 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 43 until expanded.

Subtasks archive 2025-07-28

6 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 279 papers with code (671 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

Syntology lines on 18 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.

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