HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Multi Object Tracking On Mot17

Metrics

MOTA

Results

Performance results of various models on this benchmark

Paper Title
FeatureSORT81.2FeatureSORT: Essential Features for Effective Tracking
SMILEtrack81.06SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking
SparseTrack81.0SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth
CMTrack80.7A Confidence-Aware Matching Strategy For Generalized Multi-Object Tracking
BoostTrack++80.7BoostTrack++: using tracklet information to detect more objects in multiple object tracking
BoostTrack+80.6BoostTrack: boosting the similarity measure and detection confidence for improved multiple object tracking
BoT-SORT80.5BoT-SORT: Robust Associations Multi-Pedestrian Tracking
UCMCTrack80.5UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation
ByteTrack80.3ByteTrack: Multi-Object Tracking by Associating Every Detection Box
AdapTrack79.9AdapTrack: Adaptive Thresholding-Based Matching For Multi-object Tracking
StrongSORT79.6StrongSORT: Make DeepSORT Great Again
IMM-JHSE79.54One Homography is All You Need: IMM-based Joint Homography and Multiple Object State Estimation
Deep OC-SORT79.4Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification
SFSORT78.8SFSORT: Scene Features-based Simple Online Real-Time Tracker
C-TWiX78.1Learning Data Association for Multi-Object Tracking using Only Coordinates
OC-SORT78.0Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking
Unicorn77.2Towards Grand Unification of Object Tracking
STGT76.7TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking
FCG76.7Multiple Object Tracking from appearance by hierarchically clustering tracklets
SGT76.4Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker
0 of 44 row(s) selected.
Multi Object Tracking On Mot17 | SOTA | HyperAI