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

Showing 101150 of 318 papers

TitleStatusHype
SoccerNet 2022 Challenges ResultsCode1
Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT PhilosophyCode1
DR.VIC: Decomposition and Reasoning for Video Individual CountingCode1
Simple online and real-time tracking with occlusion handlingCode1
Learning a Neural Solver for Multiple Object TrackingCode1
Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T VideosCode1
History-Aware Transformation of ReID Features for Multiple Object TrackingCode1
Joint Learning Architecture for Multiple Object Tracking and Trajectory ForecastingCode1
DEFT: Detection Embeddings for TrackingCode1
Joint Graph Decomposition and Node Labeling: Problem, Algorithms, ApplicationsCode0
Into the Fog: Evaluating Robustness of Multiple Object TrackingCode0
3D Multi-Object Tracking: A Baseline and New Evaluation MetricsCode0
One Homography is All You Need: IMM-based Joint Homography and Multiple Object State EstimationCode0
TP-GMOT: Tracking Generic Multiple Object by Textual Prompt with Motion-Appearance Cost (MAC) SORTCode0
A Feasibility Study on Indoor Localization and Multi-person Tracking Using Sparsely Distributed Camera Network with Edge ComputingCode0
An Empirical Analysis of Visual Features for Multiple Object Tracking in Urban ScenesCode0
TGCN: Time Domain Graph Convolutional Network for Multiple Objects TrackingCode0
How To Train Your Deep Multi-Object TrackerCode0
Unsupervised Spatio-temporal Latent Feature Clustering for Multiple-object Tracking and SegmentationCode0
Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object TrackingCode0
Deep Affinity Network for Multiple Object TrackingCode0
A Deep Learning Bidirectional Temporal Tracking Algorithm for Automated Blood Cell Counting from Non-invasive Capillaroscopy VideosCode0
GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021Code0
Soccer Player Tracking in Low Quality VideoCode0
Supervised and Unsupervised Detections for Multiple Object Tracking in Traffic Scenes: A Comparative StudyCode0
Robust Multi-Modality Multi-Object TrackingCode0
COOLer: Class-Incremental Learning for Appearance-Based Multiple Object TrackingCode0
Adaptive Confidence Threshold for ByteTrack in Multi-Object TrackingCode0
Contrastive Learning for Multi-Object Tracking with TransformersCode0
Real-Time Multiple Object Tracking - A Study on the Importance of SpeedCode0
RobMOT: Robust 3D Multi-Object Tracking by Observational Noise and State Estimation Drift Mitigation on LiDAR PointCloudCode0
Psychlab: A Psychology Laboratory for Deep Reinforcement Learning AgentsCode0
Cell tracking for live-cell microscopy using an activity-prioritized assignment strategyCode0
Enhancing Thermal MOT: A Novel Box Association Method Leveraging Thermal Identity and Motion SimilarityCode0
Actor-identified Spatiotemporal Action Detection --- Detecting Who Is Doing What in VideosCode0
Multiple Object Trackers in OpenCV: A BenchmarkCode0
Multiple Object Tracking with Kernelized Correlation Filters in Urban Mixed TrafficCode0
A Region-based Gauss-Newton Approach to Real-Time Monocular Multiple Object TrackingCode0
Leveraging Foundation Models via Knowledge Distillation in Multi-Object Tracking: Distilling DINOv2 Features to FairMOTCode0
Multiple Hypothesis Hypergraph Tracking for Posture Identification in Embryonic Caenorhabditis elegansCode0
Multiple Toddler Tracking in Indoor VideosCode0
MOT20: A benchmark for multi object tracking in crowded scenesCode0
MOTChallenge 2015: Towards a Benchmark for Multi-Target TrackingCode0
Lucid Data Dreaming for Video Object SegmentationCode0
Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detectionCode0
Appearance-free Tripartite Matching for Multiple Object TrackingCode0
Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object TrackingCode0
Joint Monocular 3D Vehicle Detection and TrackingCode0
Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object TrackingCode0
Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications0
Show:102550
← PrevPage 3 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SRK ODESAMOTA90.03Unverified
2MOSTFusionMOTA84.83Unverified
3mmMOT-normalMOTA84.77Unverified
43DTMOTA84.52Unverified
5Mono3DTMOTA84.52Unverified
6RRC-IIITHMOTA84.24Unverified
7RobMOT (Dynamic)HOTA81.8Unverified
8RobMOTHOTA81.76Unverified
9MCTrackHOTA81.07Unverified
10KFDLHOTA81.06Unverified
#ModelMetricClaimedVerifiedStatus
1ByteTrackmMOTA45.5Unverified
2UNINEXT-HmMOTA44.2Unverified
3MOTRv2mMOTA43.6Unverified
4QDTrackmMOTA42.1Unverified
5ContrasTRmMOTA41.7Unverified
6UnicornmMOTA41.2Unverified
7TETermMOTA39.1Unverified
8QDTrackmMOTA36.6Unverified
9Adaptive-searching -windows TrackermMOTA34.4Unverified
#ModelMetricClaimedVerifiedStatus
1ContrasTRmMOTA42.8Unverified
2SUSHImMOTA40.2Unverified
3ByteTrackmMOTA40.1Unverified
4QDtrackmMOTA35.6Unverified
5Yu et al.mMOTA26.3Unverified
#ModelMetricClaimedVerifiedStatus
1PP-TrackingMOTA72.6Unverified
2OC-SORTMOTA67.9Unverified
3HeadHunter-TMOTA63.6Unverified
4TracktorMOTA58.9Unverified
5SORTMOTA46.4Unverified
#ModelMetricClaimedVerifiedStatus
1MOTIP (Deformable DETR, with SportsMOT val)HOTA75.2Unverified
2TrackSSMHOTA74.4Unverified
3MOTIP (Deformable DETR)HOTA71.9Unverified
#ModelMetricClaimedVerifiedStatus
1MCTrackHOTA82.75Unverified
2BiTrackHOTA82.7Unverified
#ModelMetricClaimedVerifiedStatus
1SIRAMOTA47.79Unverified
2TempoRadarMOTA37.91Unverified
#ModelMetricClaimedVerifiedStatus
1QDTrackMOTA55.6Unverified
2RetinaTrackMOTA44.92Unverified
#ModelMetricClaimedVerifiedStatus
1MAC-SORTHOTA58.58Unverified
#ModelMetricClaimedVerifiedStatus
1EB & TADNMOTA23.7Unverified
#ModelMetricClaimedVerifiedStatus
1HandLerMOTA70Unverified