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

Showing 13511400 of 1966 papers

TitleStatusHype
Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets0
Object Tracking by Least Spatiotemporal Searches0
Tracking the Untrackable0
Scale Equivariance Improves Siamese TrackingCode1
CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions0
Unsupervised Spatio-temporal Latent Feature Clustering for Multiple-object Tracking and SegmentationCode0
Correlation filter tracking with adaptive proposal selection for accurate scale estimation0
End-to-End Multi-Object Tracking with Global Response Map0
Learning to associate detections for real-time multiple object tracking0
Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching0
Efficient resource management in UAVs for Visual Assistance0
Tracking-by-Trackers with a Distilled and Reinforced ModelCode1
ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation0
PointTrack++ for Effective Online Multi-Object Tracking and SegmentationCode1
Segment as Points for Efficient Online Multi-Object Tracking and SegmentationCode1
4D Spatio-Temporal Convolutional Networks for Object Position Estimation in OCT Volumes0
Motion Prediction in Visual Object Tracking0
Optimisation of a Siamese Neural Network for Real-Time Energy Efficient Object Tracking0
Enhancing the Association in Multi-Object Tracking via Neighbor Graph0
Tackling Occlusion in Siamese Tracking with Structured Dropouts0
1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking0
Lifted Disjoint Paths with Application in Multiple Object TrackingCode1
IA-MOT: Instance-Aware Multi-Object Tracking with Motion Consistency0
Joint Object Detection and Multi-Object Tracking with Graph Neural NetworksCode1
Instant 3D Object Tracking with Applications in Augmented Reality0
Object Tracking through Residual and Dense LSTMs0
Semi-Supervised Object Detection with Sparsely Annotated Dataset0
Center-based 3D Object Detection and TrackingCode2
Accurate Anchor Free Tracking0
GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature LearningCode1
Benchmarking Unsupervised Object Representations for Video SequencesCode1
Multiple-Vehicle Tracking in the Highway Using Appearance Model and Visual Object Tracking0
Quasi-Dense Similarity Learning for Multiple Object TrackingCode1
Map3D: Registration Based Multi-Object Tracking on 3D Serial Whole Slide ImagesCode0
TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training ModelCode1
RGB-D-E: Event Camera Calibration for Fast 6-DOF Object TrackingCode1
Metro-haul Project Vertical Service Demo: Video Surveillance Real-time Low-latency Object Tracking0
Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping0
Siamese Keypoint Prediction Network for Visual Object TrackingCode1
Simple Unsupervised Multi-Object Tracking0
COMET: Context-Aware IoU-Guided Network for Small Object Tracking0
GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking With 2D-3D Multi-Feature LearningCode1
Cross-Modal Pattern-Propagation for RGB-T Tracking0
One-Shot Adversarial Attacks on Visual Tracking With Dual Attention0
D3S - A Discriminative Single Shot Segmentation Tracker0
Learning a Neural Solver for Multiple Object TrackingCode1
Computing Representations for Lie Algebraic NetworksCode0
P2B: Point-to-Box Network for 3D Object Tracking in Point CloudsCode1
AFAT: Adaptive Failure-Aware Tracker for Robust Visual Object Tracking0
TAO: A Large-Scale Benchmark for Tracking Any Object0
Show:102550
← PrevPage 28 of 40Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HR-CEUTrack-LargeSuccess Rate65Unverified
2HR-CEUTrack-BaseSuccess Rate63.2Unverified
3CEUTrack-LargeSuccess Rate62.8Unverified
4CEUTrack-BaseSuccess Rate62Unverified
5SiamR-CNNSuccess Rate60.9Unverified
6TransTSuccess Rate60.5Unverified
7SuperDiMPSuccess Rate60.2Unverified
8TrDiMPSuccess Rate60.1Unverified
9KeepTrackSuccess Rate59.6Unverified
10AiATrackSuccess Rate59Unverified
#ModelMetricClaimedVerifiedStatus
1HR-MonTrack-BaseSuccess Rate68.5Unverified
2HR-MonTrack-TinySuccess Rate66.3Unverified
3Multi-modalSuccess Rate63.4Unverified
4PrDiMPSuccess Rate59Unverified
5DiMPSuccess Rate57.1Unverified
6MonTrackSuccess Rate54.9Unverified
7ATOMSuccess Rate46.5Unverified
8KYSSuccess Rate26.6Unverified
#ModelMetricClaimedVerifiedStatus
1OmniTrackHOTA23.45Unverified
2DeepSORTHOTA21.16Unverified
3OC-SORTHOTA20.83Unverified
4ByteTrackHOTA20.66Unverified
5TrackFormerHOTA19.62Unverified
6HybridSORTHOTA16.64Unverified
7DiffMOTHOTA16.4Unverified
8Bot-SORTHOTA15.77Unverified
#ModelMetricClaimedVerifiedStatus
1DiMP50Success Rate67.33Unverified
2PrDiMP50Success Rate67Unverified
3PrDiMP18Success Rate65.9Unverified
4DiMP18Success Rate64.6Unverified
5AtomSuccess Rate63.8Unverified
#ModelMetricClaimedVerifiedStatus
1finalHumans0.14Unverified
2night_furyHumans0.05Unverified
3Yolo based methodHumans0.02Unverified
4finalHumans0Unverified
#ModelMetricClaimedVerifiedStatus
1M2-Trackmean precision83.4Unverified
2BATmean precision75.2Unverified
#ModelMetricClaimedVerifiedStatus
1UMMT3DMOTA95Unverified
2MMPTRACK3DMOTA94.8Unverified
#ModelMetricClaimedVerifiedStatus
1Siam-FCAverage IOU0.66Unverified
#ModelMetricClaimedVerifiedStatus
1RT-MDNetPrecision Plot0.63Unverified