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 451500 of 1966 papers

TitleStatusHype
Unifying Visual and Vision-Language Tracking via Contrastive LearningCode1
Learning to Visually Connect Actions and their Effects0
Machine Learning Based Object Tracking0
Dense Optical Flow Estimation Using Sparse Regularizers from Reduced Measurements0
Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and TrackingCode2
A New Dataset and a Distractor-Aware Architecture for Transparent Object Tracking0
Explicit Visual Prompts for Visual Object TrackingCode1
CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event CamerasCode1
DeconfuseTrack: Dealing with Confusion for Multi-Object Tracking0
DiffusionTrack: Point Set Diffusion Model for Visual Object TrackingCode0
Projecting Trackable Thermal Patterns for Dynamic Computer Vision0
Motion State: A New Benchmark Multiple Object Tracking0
Tracking with Human-Intent ReasoningCode1
ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to DescribeCode2
X Modality Assisting RGBT Object Tracking0
A Comprehensive Study of Object Tracking in Low-Light Environments0
iKUN: Speak to Trackers without RetrainingCode1
Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothing0
Prototype-based Cross-Modal Object TrackingCode2
Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale DatasetCode2
Perception Test 2023: A Summary of the First Challenge And Outcome0
Transformer Network for Multi-Person Tracking and Re-Identification in Unconstrained Environment0
Emotion Based Prediction in the Context of Optimized Trajectory Planning for Immersive Learning0
NTrack: A Multiple-Object Tracker and Dataset for Infield Cotton Boll Counting0
Multi-Correlation Siamese Transformer Network with Dense Connection for 3D Single Object TrackingCode0
Robust 3D Tracking with Quality-Aware Shape Completion0
Bi-directional Adapter for Multi-modal TrackingCode1
Tracking Skiers from the Top to the BottomCode0
UCMCTrack: Multi-Object Tracking with Uniform Camera Motion CompensationCode2
Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking0
PhyOT: Physics-informed object tracking in surveillance cameras0
CholecTrack20: A Dataset for Multi-Class Multiple Tool Tracking in Laparoscopic SurgeryCode1
M3SOT: Multi-frame, Multi-field, Multi-space 3D Single Object TrackingCode1
I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions0
Learning Differentiable Particle Filter on the FlyCode0
Instance Tracking in 3D Scenes from Egocentric VideosCode1
Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation0
Markov Chain Monte Carlo Multi-Scan Data Association for Sets of TrajectoriesCode0
Adaptive Confidence Threshold for ByteTrack in Multi-Object TrackingCode0
Zero-Shot Video Question Answering with Procedural Programs0
TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion ModelsCode2
A Simple Video Segmenter by Tracking Objects Along Axial TrajectoriesCode1
TrafficMOT: A Challenging Dataset for Multi-Object Tracking in Complex Traffic Scenarios0
Hy-Tracker: A Novel Framework for Enhancing Efficiency and Accuracy of Object Tracking in Hyperspectral Videos0
Multiple Toddler Tracking in Indoor VideosCode0
Beyond Visual Cues: Synchronously Exploring Target-Centric Semantics for Vision-Language Tracking0
Single-Model and Any-Modality for Video Object TrackingCode1
UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning0
The 2nd Workshop on Maritime Computer Vision (MaCVi) 20240
SeaDSC: A video-based unsupervised method for dynamic scene change detection in unmanned surface vehicles0
Show:102550
← PrevPage 10 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