SOTAVerified

Multiple Object Tracking

Multiple Object Tracking is the problem of automatically identifying multiple objects in a video and representing them as a set of trajectories with high accuracy.

Source: SOT for MOT

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 318 papers

TitleStatusHype
Matching Anything by Segmenting AnythingCode5
Trackastra: Transformer-based cell tracking for live-cell microscopyCode4
SiamMask: A Framework for Fast Online Object Tracking and SegmentationCode4
PP-YOLOE: An evolved version of YOLOCode4
Multiple Object Tracking as ID PredictionCode3
BoostTrack: boosting the similarity measure and detection confidence for improved multiple object trackingCode3
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object TrackingCode3
Universal Instance Perception as Object Discovery and RetrievalCode3
BoostTrack++: using tracklet information to detect more objects in multiple object trackingCode3
MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous DrivingCode3
MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object TrackingCode2
QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object TrackingCode2
Towards Grand Unification of Object TrackingCode2
GTA: Global Tracklet Association for Multi-Object Tracking in SportsCode2
Towards Real-Time Multi-Object TrackingCode2
Tracking Objects as PointsCode2
Simple Online and Realtime TrackingCode2
Delving into the Trajectory Long-tail Distribution for Muti-object TrackingCode2
The 1st-place Solution for ECCV 2022 Multiple People Tracking in Group Dance ChallengeCode2
UCMCTrack: Multi-Object Tracking with Uniform Camera Motion CompensationCode2
Hybrid-SORT: Weak Cues Matter for Online Multi-Object TrackingCode2
Virtual Sparse Convolution for Multimodal 3D Object DetectionCode2
SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object TrackingCode2
OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with TransformerCode2
MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object DetectorsCode2
Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion ApproachCode2
RaTrack: Moving Object Detection and Tracking with 4D Radar Point CloudCode2
SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports ScenesCode2
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask LearningCode1
Lifted Disjoint Paths with Application in Multiple Object TrackingCode1
Learning Data Association for Multi-Object Tracking using Only CoordinatesCode1
Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint PathsCode1
Learning a Neural Solver for Multiple Object TrackingCode1
Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object TrackingCode1
Learning a Neural Solver for Multiple Object TrackingCode1
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3DCode1
Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT PhilosophyCode1
Learnable Graph Matching: A Practical Paradigm for Data AssociationCode1
Learning a Proposal Classifier for Multiple Object TrackingCode1
Monocular Quasi-Dense 3D Object TrackingCode1
Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in SportsCode1
Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching SpaceCode1
Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T VideosCode1
Joint Learning Architecture for Multiple Object Tracking and Trajectory ForecastingCode1
History-Aware Transformation of ReID Features for Multiple Object TrackingCode1
3D-POP - An automated annotation approach to facilitate markerless 2D-3D tracking of freely moving birds with marker-based motion captureCode1
TransCenter: Transformers with Dense Representations for Multiple-Object TrackingCode1
DARTH: Holistic Test-time Adaptation for Multiple Object TrackingCode1
DR.VIC: Decomposition and Reasoning for Video Individual CountingCode1
Associate Everything Detected: Facilitating Tracking-by-Detection to the UnknownCode1
Show:102550
← PrevPage 1 of 7Next →
All datasetsKITTI Test (Online Methods)BDD100K valBDD100K testCroHDSportsMOTKITTI Test (Offline Methods)RADIATEWaymo Open DatasetGMOT-40UA-DETRACYouTube-Hands

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SRK ODESAMOTA90.03—Unverified
2MOSTFusionMOTA84.83—Unverified
3mmMOT-normalMOTA84.77—Unverified
43DTMOTA84.52—Unverified
5Mono3DTMOTA84.52—Unverified
6RRC-IIITHMOTA84.24—Unverified
7RobMOT (Dynamic)HOTA81.8—Unverified
8RobMOTHOTA81.76—Unverified
9MCTrackHOTA81.07—Unverified
10KFDLHOTA81.06—Unverified
#ModelMetricClaimedVerifiedStatus
1ByteTrackmMOTA45.5—Unverified
2UNINEXT-HmMOTA44.2—Unverified
3MOTRv2mMOTA43.6—Unverified
4QDTrackmMOTA42.1—Unverified
5ContrasTRmMOTA41.7—Unverified
6UnicornmMOTA41.2—Unverified
7TETermMOTA39.1—Unverified
8QDTrackmMOTA36.6—Unverified
9Adaptive-searching -windows TrackermMOTA34.4—Unverified
#ModelMetricClaimedVerifiedStatus
1ContrasTRmMOTA42.8—Unverified
2SUSHImMOTA40.2—Unverified
3ByteTrackmMOTA40.1—Unverified
4QDtrackmMOTA35.6—Unverified
5Yu et al.mMOTA26.3—Unverified
#ModelMetricClaimedVerifiedStatus
1PP-TrackingMOTA72.6—Unverified
2OC-SORTMOTA67.9—Unverified
3HeadHunter-TMOTA63.6—Unverified
4TracktorMOTA58.9—Unverified
5SORTMOTA46.4—Unverified
#ModelMetricClaimedVerifiedStatus
1MOTIP (Deformable DETR, with SportsMOT val)HOTA75.2—Unverified
2TrackSSMHOTA74.4—Unverified
3MOTIP (Deformable DETR)HOTA71.9—Unverified
#ModelMetricClaimedVerifiedStatus
1MCTrackHOTA82.75—Unverified
2BiTrackHOTA82.7—Unverified
#ModelMetricClaimedVerifiedStatus
1SIRAMOTA47.79—Unverified
2TempoRadarMOTA37.91—Unverified
#ModelMetricClaimedVerifiedStatus
1QDTrackMOTA55.6—Unverified
2RetinaTrackMOTA44.92—Unverified
#ModelMetricClaimedVerifiedStatus
1MAC-SORTHOTA58.58—Unverified
#ModelMetricClaimedVerifiedStatus
1EB & TADNMOTA23.7—Unverified
#ModelMetricClaimedVerifiedStatus
1HandLerMOTA70—Unverified