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 1751–1800 of 1966 papers

TitleStatusHype
Keypoint-based object tracking and localization using networks of low-power embedded smart cameras—0
Heuristic Search for Structural Constraints in Data Association—0
A Survey on Hardware Implementations of Visual Object Trackers—0
Recurrent Autoregressive Networks for Online Multi-Object Tracking—0
DART: Distribution Aware Retinal Transform for Event-based Cameras—0
Deep Neural Networks—0
Deep Convolutional Neural Networks for Thermal Infrared Object TrackingCode1
Visual Tracking via Dynamic Graph Learning—0
Robust Object Tracking Based on Temporal and Spatial Deep Networks—0
Non-Rigid Object Tracking via Deformable Patches Using Shape-Preserved KCF and Level Sets—0
Non-Markovian Globally Consistent Multi-Object Tracking—0
Long Short-Term Memory Kalman Filters: Recurrent Neural Estimators for Pose Regularization—0
Learning Dynamic Siamese Network for Visual Object Tracking—0
Multi-camera Multi-Object Tracking—0
Rotation Adaptive Visual Object Tracking with Motion ConsistencyCode0
ClickBAIT: Click-based Accelerated Incremental Training of Convolutional Neural Networks—0
Real-Time Multiple Object Tracking - A Study on the Importance of SpeedCode0
CoBe -- Coded Beacons for Localization, Object Tracking, and SLAM AugmentationCode0
Efficiently Tracking Homogeneous Regions in Multichannel Images—0
Convolutional Neural Networks for Non-iterative Reconstruction of Compressively Sensed Images—0
Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism—0
Learning Policies for Adaptive Tracking with Deep Feature Cascades—0
Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularization—0
Better Together: Joint Reasoning for Non-rigid 3D Reconstruction with Specularities and Shading—0
Patch-based adaptive weighting with segmentation and scale (PAWSS) for visual tracking—0
Kernalised Multi-resolution Convnet for Visual TrackingCode0
Infinite Latent Feature Selection: A Probabilistic Latent Graph-Based Ranking Approach—0
Video Object Segmentation using Tracked Object Proposals—0
Spectral Filter Tracking—0
Aerial Vehicle Tracking by Adaptive Fusion of Hyperspectral Likelihood Maps—0
Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object TrackingCode0
An Efficient Background Term for 3D Reconstruction and Tracking With Smooth Surface Models—0
Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications—0
Multi-Task Correlation Particle Filter for Robust Object Tracking—0
Multi-Object Tracking With Quadruplet Convolutional Neural Networks—0
Hierarchical Attentive Recurrent TrackingCode0
Deep Network Flow for Multi-Object Tracking—0
End-to-end Active Object Tracking via Reinforcement Learning—0
Learning a Robust Society of Tracking Parts—0
Object Tracking based on Quantum Particle Swarm Optimization—0
Fusion of Head and Full-Body Detectors for Multi-Object Tracking—0
Dynamics Based 3D Skeletal Hand TrackingCode0
Deep-LK for Efficient Adaptive Object Tracking—0
Quadruplet Network with One-Shot Learning for Fast Visual Object Tracking—0
Re3 : Real-Time Recurrent Regression Networks for Visual Tracking of Generic ObjectsCode0
(Quasi)Periodicity Quantification in Video Data, Using TopologyCode0
Measuring the Accuracy of Object Detectors and Trackers—0
Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition—0
A data set for evaluating the performance of multi-class multi-object video tracking—0
Identifying First-person Camera Wearers in Third-person Videos—0
Show:102550
← PrevPage 36 of 40Next →
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