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 1–50 of 525 papers

TitleStatusHype
SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware MemoryCode9
A Distractor-Aware Memory for Visual Object Tracking with SAM2Code3
Local All-Pair Correspondence for Point TrackingCode3
TAPIR: Tracking Any Point with per-frame Initialization and temporal RefinementCode3
Universal Instance Perception as Object Discovery and RetrievalCode3
R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement LearningCode2
Similarity-Guided Layer-Adaptive Vision Transformer for UAV TrackingCode2
Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV TrackingCode2
Exploring Enhanced Contextual Information for Video-Level Object TrackingCode2
Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion ApproachCode2
XTrack: Multimodal Training Boosts RGB-X Video Object TrackersCode2
An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-TrainingCode2
Long-term Frame-Event Visual Tracking: Benchmark Dataset and BaselineCode2
Tracking Meets LoRA: Faster Training, Larger Model, Stronger PerformanceCode2
VastTrack: Vast Category Visual Object TrackingCode2
ODTrack: Online Dense Temporal Token Learning for Visual TrackingCode2
Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale DatasetCode2
Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel BaselineCode2
Towards Real-World Visual Tracking with Temporal ContextsCode2
Autoregressive Visual TrackingCode2
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream FrameworkCode2
You Only Demonstrate Once: Category-Level Manipulation from Single Visual DemonstrationCode2
Fast Online Object Tracking and Segmentation: A Unifying ApproachCode2
Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual TrackingCode1
Efficient Motion Prompt Learning for Robust Visual TrackingCode1
SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual TrackingCode1
Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual TrackingCode1
Less is More: Token Context-aware Learning for Object TrackingCode1
Vision Eagle Attention: a new lens for advancing image classificationCode1
MFTIQ: Multi-Flow Tracker with Independent Matching Quality EstimationCode1
Improving Visual Object Tracking through Visual PromptingCode1
Low-Light Object Tracking: A BenchmarkCode1
MambaEVT: Event Stream based Visual Object Tracking using State Space ModelCode1
Multi-Granularity Language-Guided Multi-Object TrackingCode1
RTracker: Recoverable Tracking via PN Tree Structured MemoryCode1
Unifying Visual and Vision-Language Tracking via Contrastive LearningCode1
Explicit Visual Prompts for Visual Object TrackingCode1
HIPTrack: Visual Tracking with Historical PromptsCode1
ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual TrackingCode1
LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual TrackingCode1
Improving Underwater Visual Tracking With a Large Scale Dataset and Image EnhancementCode1
Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and SegmentationCode1
CiteTracker: Correlating Image and Text for Visual TrackingCode1
Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual TrackingCode1
Robust Object Modeling for Visual TrackingCode1
Cross-Drone Transformer Network for Robust Single Object TrackingCode1
Tracking through Containers and Occluders in the WildCode1
Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object TrackingCode1
ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D DataCode1
Joint Visual Grounding and Tracking with Natural Language SpecificationCode1
Show:102550
← PrevPage 1 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