Multi Object Tracking On Mot16

Metrics

IDF1

MOTA

Results

Performance results of various models on this benchmark

Model Name	IDF1	MOTA	Paper Title	Repository
QDTrack	67.1	69.8	Quasi-Dense Similarity Learning for Multiple Object Tracking
FairMOT	-	74.9	FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
DEFT	-	68.03	DEFT: Detection Embeddings for Tracking
OUTrack_fm	71.1	74.2	Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation	-
HopTrack[Embedded GPU]	-	63.12	HopTrack: A Real-time Multi-Object Tracking System for Embedded Devices
MPNTrack	61.7	58.6	Learning a Neural Solver for Multiple Object Tracking
NOMT	-	46.4	Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor	-
LMOT	72.3	73.2	LMOT: Efficient Light-Weight Detection and Tracking in Crowds
FWT	-	47.8	Fusion of Head and Full-Body Detectors for Multi-Object Tracking	-
MOTR	67.0	66.8	MOTR: End-to-End Multiple-Object Tracking with Transformer
GSDT	-	66.7	Joint Object Detection and Multi-Object Tracking with Graph Neural Networks
TNT	-	49.2	Exploit the Connectivity: Multi-Object Tracking with TrackletNet
JDE	-	64.4	Towards Real-Time Multi-Object Tracking
DMMOT	-	46.1	Online Multi-Object Tracking with Dual Matching Attention Networks
GCRA	-	48.2	Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking	-
SGT	73.5	76.8	Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker
Lif_T	64.7	61.3	Lifted Disjoint Paths with Application in Multiple Object Tracking
PPTracking	-	77.7	PP-YOLOE: An evolved version of YOLO
TraDeS	64.7	70.1	Track to Detect and Segment: An Online Multi-Object Tracker	-
ReMOT	-	76.9	ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation	-

0 of 24 row(s) selected.