Multi-Object Tracking
22개 벤치마크 · 논문 812편 · 이 태스크의 논문 보기 →
Benchmarks
MOT17
DanceTrack
MOT20
MOT16
SportsMOT
JRDB
Wildtrack
TAO
2024 AI City Challenge
MOTS20
2D MOT 2015
HiEve
PersonPath22
SeaDronesSee
2DMOT15
MOT15
MultiviewX
UAVDT
BDD100K
VisDrone2019
MOT15_3D
Synthehicle
Most implemented
Simple Online and Realtime Tracking
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
StrongSORT: Make DeepSORT Great Again
Tracking without bells and whistles
Towards Real-Time Multi-Object Tracking
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
Papers
ByteTraX: Enhancing the ByteTrack Architecture with Optimised Thresholding
The ByteTrack algorithm is a widely used and computationally efficient multi-object tracking architecture. Its core innovation lies in the combination of lenient bounding box associations with tracklet similarity matchin…
Multi-Object TrackingObject DetectionTracking the Unseen: An Occlusion-Robust Framework for Target Tracking Under Full and Long-Term Occlusion
Real-time multi-object tracking systems remain highly vulnerable to full and long-term occlusion, where targets temporarily or completely disappear from the camera's field of view. Conventional trackers may terminate tra…
Multiple Object TrackingMulti-Object TrackingObject DetectionTeach a Molmo2Fish: Towards interactive fish tracking with natural language guidance
Computer vision is increasingly used to automate recognition tasks in large ecological datasets, but more complex tasks such as multi-object tracking continue to pose challenges. As researchers seek to incorporate vision…
Multi-Object TrackingProbing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Tracking
Training query-propagation end-to-end multi-object tracking (MOT) models requires dense bounding-box and identity annotations across video sequences, making dataset construction expensive. Clip-level active learning redu…
Multi-Object TrackingActive LearningCD-RMOT-Bench: Benchmarking the Cross-Domain Referring Multi-Object Tracking
Referring multi-object tracking (RMOT) extends tracking from category-driven perception to language-guided understanding by grounding object trajectories in natural-language expressions. Despite recent progress, existing…
Multi-Object TrackingObject DetectionIncremental Optimal Assignment for Real-Time Crowd Tracking
Multi-object tracking in dense crowds requires solving a bipartite assignment problem between detections and trajectories at every video frame. The classical Hungarian algorithm solves this in $O(N^3)$ time, which become…
Multi-Object Tracking