SOTAVerified

Multi-Object Tracking

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.

Papers

Showing 101–125 of 671 papers

TitleStatusHype
3DMOTFormer: Graph Transformer for Online 3D Multi-Object TrackingCode1
Uncertainty-aware Unsupervised Multi-Object TrackingCode1
Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in SportsCode1
TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory HypothesesCode1
SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-DepthCode1
Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object TrackingCode1
GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-TrainingCode1
You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object TrackingCode1
OVTrack: Open-Vocabulary Multiple Object TrackingCode1
Referring Multi-Object TrackingCode1
3D Multi-Object Tracking Based on Uncertainty-Guided Data AssociationCode1
DFR-FastMOT: Detection Failure Resistant Tracker for Fast Multi-Object Tracking Based on Sensor FusionCode1
DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open ScenesCode1
Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot InteractionCode1
Context-Aware Relative Object Queries To Unify Video Instance and Panoptic SegmentationCode1
A Fast Unified System for 3D Object Detection and TrackingCode1
Multiple Object Tracking Challenge Technical Report for Team MT_IoTCode1
Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching SpaceCode1
MEVID: Multi-view Extended Videos with Identities for Video Person Re-IdentificationCode1
Large Scale Real-World Multi-Person TrackingCode1
Strong-TransCenter: Improved Multi-Object Tracking based on Transformers with Dense RepresentationsCode1
Multi-view Tracking Using Weakly Supervised Human Motion PredictionCode1
Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?Code1
Multiple Object Tracking from appearance by hierarchically clustering trackletsCode1
BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in VideoCode1
Show:102550
← PrevPage 5 of 27Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1STGTMOTA76.7—Unverified
2TransCenterMOTA76—Unverified
3TrackFormerMOTA74.1—Unverified
4FairMOTMOTA73.7—Unverified
5OUTrack_fmMOTA73.5—Unverified
6LMOTMOTA72—Unverified
7TraDeSMOTA69.1—Unverified
8TADNMOTA69—Unverified
9QDTrackMOTA68.7—Unverified
10CenterTrack + TrajEMOTA67.8—Unverified
#ModelMetricClaimedVerifiedStatus
1SAM2MOTHOTA75.9—Unverified
2MOTIP (Deformable DETR, with DanceTrack val and CrowdHuman)HOTA73.7—Unverified
3MOTRv2HOTA73.4—Unverified
4MOTIP (Deformable DETR, with CrowdHuman)HOTA71.4—Unverified
5MOTIP (DAB-Deformable DETR)HOTA70—Unverified
6CO-MOTHOTA69.4—Unverified
7CAMELTrack (fully online)HOTA69.3—Unverified
8MeMOTRHOTA68.5—Unverified
9MOTIP (Deformable DETR)HOTA67.5—Unverified
10MT_IOTHOTA66.66—Unverified
#ModelMetricClaimedVerifiedStatus
1STGTMOTA77.5—Unverified
2TransCenterMOTA72.4—Unverified
3OUTrack_fmMOTA68.5—Unverified
4GSDTMOTA67.1—Unverified
5BoostTrack++HOTA66.4—Unverified
6BoostTrack+HOTA66.2—Unverified
7TrackTrackHOTA65.7—Unverified
8AdapTrackHOTA65—Unverified
9CMTrackHOTA64.8—Unverified
10Deep OC-SORTHOTA63.9—Unverified
#ModelMetricClaimedVerifiedStatus
1PPTrackingMOTA77.7—Unverified
2ReMOTMOTA76.9—Unverified
3SGTMOTA76.8—Unverified
4STGTMOTA76.7—Unverified
5FairMOTMOTA74.9—Unverified
6UniTrackMOTA74.7—Unverified
7OUTrack_fmMOTA74.2—Unverified
8LMOTMOTA73.2—Unverified
9TraDeSMOTA70.1—Unverified
10QDTrackMOTA69.8—Unverified
#ModelMetricClaimedVerifiedStatus
1DeepEIoU + GTAHOTA81—Unverified
2HAT-FastReID-MOTHOTA80.8—Unverified
3CAMELTrack (fully online)HOTA80.4—Unverified
4Deep HM-SORTHOTA80.1—Unverified
5AEDHOTA79.1—Unverified
6DeepMoveSORTHOTA78.7—Unverified
7Deep-EIoUHOTA77.2—Unverified
8MoveSORTHOTA74.6—Unverified
9ETTrackHOTA74.3—Unverified
10MixSort-OCHOTA74.1—Unverified
#ModelMetricClaimedVerifiedStatus
1OmniTrackHOTA26.92—Unverified
2OC-SORTHOTA25.04—Unverified
3HybridSORTHOTA25.01—Unverified
4ByteTrackHOTA25—Unverified
5SORTHOTA23.49—Unverified
6Bot-SORTHOTA22.9—Unverified
7DeepSORTHOTA22.15—Unverified
8DiffMOTHOTA19.96—Unverified
9TrackFormerHOTA19.16—Unverified
10MOTRv2HOTA18.22—Unverified
#ModelMetricClaimedVerifiedStatus
1AED (Co-DETR)TETA55.3—Unverified
2GLEE-ProTETA47.2—Unverified
3GLEE-PlusTETA41.5—Unverified
4GLEE-LiteTETA40.1—Unverified
5AED (RegionCLIP)TETA37—Unverified
6TETer-HTCTETA36.85—Unverified
7TETer-SwinTTETA34.61—Unverified
8TETerTETA33.25—Unverified
9AOATETA25.27—Unverified
#ModelMetricClaimedVerifiedStatus
1MCBLTIDF195.6—Unverified
2TrackTacular (Bilinear Sampling)IDF195.3—Unverified
3MVFlowIDF193.5—Unverified
4EarlyBirdIDF192.3—Unverified
5ReSTIDF186.7—Unverified
6DMCT StackIDF181.9—Unverified
7DMCTIDF177.8—Unverified
8GLMB-YOLOv3IDF174.3—Unverified
9GLMB-DOIDF172.5—Unverified
#ModelMetricClaimedVerifiedStatus
1MCBLTHOTA81.22—Unverified
2YachiyoHOTA71.94—Unverified
3SJTU-LenovoHOTA67.22—Unverified
4NotaHOTA60.93—Unverified
5FraunhoferIOSBHOTA60.88—Unverified
6UW-ETRIHOTA57.14—Unverified
7ARVHOTA51.06—Unverified
8AsillaHOTA40.34—Unverified
#ModelMetricClaimedVerifiedStatus
1ReMOTSsMOTSA70.4—Unverified
2UniTracksMOTSA68.9—Unverified
3UnicornsMOTSA65.3—Unverified
4TrackFormersMOTSA54.9—Unverified
5TraDessMOTSA50.8—Unverified
6Track R-CNNsMOTSA40.6—Unverified