SOTAVerified

Visual Tracking

Visual Tracking is an essential and actively researched problem in the field of computer vision with various real-world applications such as robotic services, smart surveillance systems, autonomous driving, and human-computer interaction. It refers to the automatic estimation of the trajectory of an arbitrary target object, usually specified by a bounding box in the first frame, as it moves around in subsequent video frames.

Source: Learning Reinforced Attentional Representation for End-to-End Visual Tracking

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 401–450 of 525 papers

TitleStatusHype
Automatic Ground Truths: Projected Image Annotations for Omnidirectional Vision—0
Recurrent Filter Learning for Visual TrackingCode0
Learning Rotation for Kernel Correlation Filter—0
Patch-based adaptive weighting with segmentation and scale (PAWSS) for visual tracking—0
Kernalised Multi-resolution Convnet for Visual TrackingCode0
Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking—0
CREST: Convolutional Residual Learning for Visual Tracking—0
Attentional Correlation Filter Network for Adaptive Visual TrackingCode0
Robust Visual Tracking via Hierarchical Convolutional FeaturesCode0
An In-Depth Analysis of Visual Tracking with Siamese Neural Networks—0
BranchOut: Regularization for Online Ensemble Tracking With Convolutional Neural Networks—0
Robust Visual Tracking Using Oblique Random ForestsCode0
Action-Decision Networks for Visual Tracking With Deep Reinforcement LearningCode0
Multi-Task Correlation Particle Filter for Robust Object Tracking—0
Independent Motion Detection with Event-driven Cameras—0
Learning Spatial-Aware Regressions for Visual TrackingCode0
Faster Spatially Regularized Correlation Filters for Visual Tracking—0
Long-term Correlation Tracking using Multi-layer Hybrid Features in Sparse and Dense Environments—0
Development of a N-type GM-PHD Filter for Multiple Target, Multiple Type Visual Tracking—0
Robust Tracking Using Region Proposal Networks—0
Re3 : Real-Time Recurrent Regression Networks for Visual Tracking of Generic ObjectsCode0
TraX: The visual Tracking eXchange Protocol and Library—0
Adaptive Feature Representation for Visual Tracking—0
Real-Time Salient Closed Boundary Tracking via Line Segments Perceptual GroupingCode0
Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition—0
Good Features to Correlate for Visual TrackingCode0
DCFNet: Discriminant Correlation Filters Network for Visual TrackingCode0
Efficient Version-Space Reduction for Visual Tracking—0
Real-time 3D Human Tracking for Mobile Robots with Multisensors—0
Learning Background-Aware Correlation Filters for Visual TrackingCode0
Real-time visual tracking by deep reinforced decision makingCode0
Tracking using Numerous Anchor pointsCode0
Deep Reinforcement Learning for Visual Object Tracking in Videos—0
SafeDrive: A Robust Lane Tracking System for Autonomous and Assisted Driving Under Limited Visibility—0
Robust and Real-time Deep Tracking Via Multi-Scale Domain Adaptation—0
Deep Motion Features for Visual Tracking—0
Dual Deep Network for Visual TrackingCode0
Visual motion processing and human tracking behavior—0
SANet: Structure-Aware Network for Visual Tracking—0
Convolutional Regression for Visual Tracking—0
Visual Tracking via Boolean Map Representations—0
Counterfactual Reasoning about Intent for Interactive Navigation in Dynamic Environments—0
SPiKeS: Superpixel-Keypoints Structure for Robust Visual Tracking—0
Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking—0
Object Tracking via Dynamic Feature Selection Processes—0
Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning—0
Modeling and Propagating CNNs in a Tree Structure for Visual Tracking—0
Fundamental principles of cortical computation: unsupervised learning with prediction, compression and feedbackCode0
Learning Spatially Regularized Correlation Filters for Visual Tracking—0
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual TrackingCode0
Show:102550
← PrevPage 9 of 11Next →
All datasetsTNL2KDAVISKineticsKubricRGB-StackingLaSOTOTB-100OTB-2013Second dialogue state tracking challengeTrackingNet

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ARTrack-LAUC60.3—Unverified
2UNINEXT-HAUC59.3—Unverified
3JointNLTAUC56.9—Unverified
4OSTrackAUC55.9—Unverified
5TransTAUC50.7—Unverified
6AdaSwitcherAUC42—Unverified
#ModelMetricClaimedVerifiedStatus
1TAPIR (Panning MOVi-E)Average Jaccard61.3—Unverified
2TAPIR (MOVi-E)Average Jaccard59.8—Unverified
#ModelMetricClaimedVerifiedStatus
1TAPIR (Panning MOVi-E)Average Jaccard57.2—Unverified
2TAPIR (MOVi-E)Average Jaccard57.1—Unverified
#ModelMetricClaimedVerifiedStatus
1TAPIR (Panning MOVi-E)Average Jaccard84.7—Unverified
2TAPIR (MOVi-E)Average Jaccard84.3—Unverified
#ModelMetricClaimedVerifiedStatus
1TAPIR (MOVi-E)Average Jaccard66.2—Unverified
2TAPIR (Panning MOVi-E)Average Jaccard62.7—Unverified
#ModelMetricClaimedVerifiedStatus
1TATrack-LAUC71.1—Unverified
#ModelMetricClaimedVerifiedStatus
1SiamFC-lu (Ours)AUC0.32—Unverified
#ModelMetricClaimedVerifiedStatus
1SiamFC-lu (Ours)AUC0.66—Unverified
#ModelMetricClaimedVerifiedStatus
1MDNetScore0.64—Unverified
#ModelMetricClaimedVerifiedStatus
1TATrack-LACCURACY0.85—Unverified