Multi Object Tracking On Mot17

Metrics

MOTA

Results

Performance results of various models on this benchmark

Model Name	MOTA	Paper Title	Repository
JBNOT	52.6	Multiple People Tracking using Body and Joint Detections	-
SparseTrack	81.0	SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth
StrongSORT	79.6	StrongSORT: Make DeepSORT Great Again
Fast-StrongSORT	-	When to Extract ReID Features: A Selective Approach for Improved Multiple Object Tracking
DEFT	66.6	DEFT: Detection Embeddings for Tracking
Unicorn	77.2	Towards Grand Unification of Object Tracking
CenterTrack + TrajE	67.8	Multiple Object Tracking with Mixture Density Networks for Trajectory Estimation	-
CMTrack	80.7	A Confidence-Aware Matching Strategy For Generalized Multi-Object Tracking
BoostTrack+	80.6	BoostTrack: boosting the similarity measure and detection confidence for improved multiple object tracking
STGT	76.7	TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking	-
Deep OC-SORT	79.4	Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification
TraDeS	69.1	Track to Detect and Segment: An Online Multi-Object Tracker	-
BoT-SORT	80.5	BoT-SORT: Robust Associations Multi-Pedestrian Tracking
C-TWiX	78.1	Learning Data Association for Multi-Object Tracking using Only Coordinates
GTR	75.3	Global Tracking Transformers
QDTrack	68.7	Quasi-Dense Similarity Learning for Multiple Object Tracking
IMM-JHSE	79.54	One Homography is All You Need: IMM-based Joint Homography and Multiple Object State Estimation
DeepMOT-Tracktor	53.7	How To Train Your Deep Multi-Object Tracker
TrackFormer	74.1	TrackFormer: Multi-Object Tracking with Transformers
MOTR	67.4	MOTR: End-to-End Multiple-Object Tracking with Transformer

0 of 44 row(s) selected.