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 151–200 of 318 papers

TitleStatusHype
SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos—0
Exploiting Temporal Relations on Radar Perception for Autonomous Driving—0
SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Tasks—0
PP-YOLOE: An evolved version of YOLOCode4
Interactive Multi-scale Fusion of 2D and 3D Features for Multi-object Tracking—0
Unified Transformer Tracker for Object TrackingCode1
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object TrackingCode3
DR.VIC: Decomposition and Reasoning for Video Individual CountingCode1
GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021Code0
Unsupervised Multiple-Object Tracking with a Dynamical Variational Autoencoder—0
Does Video Compression Impact Tracking Accuracy?—0
Learning Pixel Trajectories with Multiscale Contrastive Random Walks—0
Forward Propagation, Backward Regression, and Pose Association for Hand Tracking in the WildCode1
PatchTrack: Multiple Object Tracking Using Frame Patches—0
LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking—0
Multiple Hypothesis Hypergraph Tracking for Posture Identification in Embryonic Caenorhabditis elegansCode0
SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real WorldCode1
Multi-Object Tracking and Segmentation with a Space-Time Memory Network—0
ByteTrack: Multi-Object Tracking by Associating Every Detection BoxCode1
Multiple Object Trackers in OpenCV: A BenchmarkCode0
KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3DCode1
Extended Object Tracking Using Sets Of Trajectories with a PHD Filter—0
Robust Privacy-Preserving Motion Detection and Object Tracking in Encrypted Streaming Video—0
Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint PathsCode1
Joint Learning Architecture for Multiple Object Tracking and Trajectory ForecastingCode1
Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORTCode1
Semi-TCL: Semi-Supervised Track Contrastive Representation Learning—0
Prototypical Cross-Attention Networks for Multiple Object Tracking and SegmentationCode1
Multiple Object Tracking with Mixture Density Networks for Trajectory Estimation—0
Improving Multiple Object Tracking With Single Object Tracking—0
DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object TrackingCode1
Online and Real-Time Tracking in a Surveillance Scenario—0
A Joint Intensity-Neuromorphic Event Imaging System for Resource Constrained Devices—0
Soccer Player Tracking in Low Quality VideoCode0
Uncertainty in Minimum Cost Multicuts for Image and Motion Segmentation—0
RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation—0
MOTR: End-to-End Multiple-Object Tracking with TransformerCode1
EagerMOT: 3D Multi-Object Tracking via Sensor FusionCode1
Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT PhilosophyCode1
Multiple Object Tracking with Correlation Learning—0
TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking—0
Online Multiple Object Tracking with Cross-Task SynergyCode1
Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object TrackingCode1
TransCenter: Transformers with Dense Representations for Multiple-Object TrackingCode1
Tracking Pedestrian Heads in Dense CrowdCode1
Learning a Proposal Classifier for Multiple Object TrackingCode1
Monocular Quasi-Dense 3D Object TrackingCode1
Simple online and real-time tracking with occlusion handlingCode1
DEFT: Detection Embeddings for TrackingCode1
Temporally Guided Articulated Hand Pose Tracking in Surgical VideosCode1
Show:102550
← PrevPage 4 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