SOTAVerified

Object Tracking

Object tracking is the task of taking an initial set of object detections, creating a unique ID for each of the initial detections, and then tracking each of the objects as they move around frames in a video, maintaining the ID assignment. State-of-the-art methods involve fusing data from RGB and event-based cameras to produce more reliable object tracking. CNN-based models using only RGB images as input are also effective. The most popular benchmark is OTB. There are several evaluation metrics specific to object tracking, including HOTA, MOTA, IDF1, and Track-mAP.

( Image credit: Towards-Realtime-MOT )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 1966 papers

TitleStatusHype
MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results—0
YOLOv8-SMOT: An Efficient and Robust Framework for Real-Time Small Object Tracking via Slice-Assisted Training and Adaptive AssociationCode0
HiM2SAM: Enhancing SAM2 with Hierarchical Motion Estimation and Memory Optimization towards Long-term TrackingCode1
Robustifying 3D Perception through Least-Squares Multi-Agent Graphs Object Tracking—0
UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather ConditionsCode1
Visual and Memory Dual Adapter for Multi-Modal Object TrackingCode0
Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object TrackingCode1
R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement LearningCode2
USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways—0
Lightweight RGB-T Tracking with Mobile Vision Transformers—0
RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and TrackingCode2
Probabilistic Trajectory GOSPA: A Metric for Uncertainty-Aware Multi-Object Tracking Performance Evaluation—0
Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Art—0
Focusing on Tracks for Online Multi-Object TrackingCode2
SAM2Auto: Auto Annotation Using FLASH—0
SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot SegmentationCode2
Fully Spiking Neural Networks for Unified Frame-Event Object Tracking—0
ReaMOT: A Benchmark and Framework for Reasoning-based Multi-Object TrackingCode1
Progressive Scaling Visual Object Tracking—0
EOTNet: Deep Memory Aided Bayesian Filter for Extended Object TrackingCode0
Distributed Expectation Propagation for Multi-Object Tracking over Sensor Networks—0
FusionTrack: End-to-End Multi-Object Tracking in Arbitrary Multi-View Environment—0
Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Tracking—0
Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detectionCode0
ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding ValidationCode0
Show:102550
← PrevPage 1 of 79Next →
All datasetsCOESOTFE108QuadTrackSeaDronesSeeBIRDSAI - ICVGIP 2020KITTIMMPTRACKPerception TestVisEvent

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HR-CEUTrack-LargeSuccess Rate65—Unverified
2HR-CEUTrack-BaseSuccess Rate63.2—Unverified
3CEUTrack-LargeSuccess Rate62.8—Unverified
4CEUTrack-BaseSuccess Rate62—Unverified
5SiamR-CNNSuccess Rate60.9—Unverified
6TransTSuccess Rate60.5—Unverified
7SuperDiMPSuccess Rate60.2—Unverified
8TrDiMPSuccess Rate60.1—Unverified
9KeepTrackSuccess Rate59.6—Unverified
10AiATrackSuccess Rate59—Unverified
#ModelMetricClaimedVerifiedStatus
1HR-MonTrack-BaseSuccess Rate68.5—Unverified
2HR-MonTrack-TinySuccess Rate66.3—Unverified
3Multi-modalSuccess Rate63.4—Unverified
4PrDiMPSuccess Rate59—Unverified
5DiMPSuccess Rate57.1—Unverified
6MonTrackSuccess Rate54.9—Unverified
7ATOMSuccess Rate46.5—Unverified
8KYSSuccess Rate26.6—Unverified
#ModelMetricClaimedVerifiedStatus
1OmniTrackHOTA23.45—Unverified
2DeepSORTHOTA21.16—Unverified
3OC-SORTHOTA20.83—Unverified
4ByteTrackHOTA20.66—Unverified
5TrackFormerHOTA19.62—Unverified
6HybridSORTHOTA16.64—Unverified
7DiffMOTHOTA16.4—Unverified
8Bot-SORTHOTA15.77—Unverified
#ModelMetricClaimedVerifiedStatus
1DiMP50Success Rate67.33—Unverified
2PrDiMP50Success Rate67—Unverified
3PrDiMP18Success Rate65.9—Unverified
4DiMP18Success Rate64.6—Unverified
5AtomSuccess Rate63.8—Unverified
#ModelMetricClaimedVerifiedStatus
1finalHumans0.14—Unverified
2night_furyHumans0.05—Unverified
3Yolo based methodHumans0.02—Unverified
4finalHumans0—Unverified
#ModelMetricClaimedVerifiedStatus
1M2-Trackmean precision83.4—Unverified
2BATmean precision75.2—Unverified
#ModelMetricClaimedVerifiedStatus
1UMMT3DMOTA95—Unverified
2MMPTRACK3DMOTA94.8—Unverified
#ModelMetricClaimedVerifiedStatus
1Siam-FCAverage IOU0.66—Unverified
#ModelMetricClaimedVerifiedStatus
1RT-MDNetPrecision Plot0.63—Unverified