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
Universal Instance Perception as Object Discovery and RetrievalCode3
TAPIR: Tracking Any Point with per-frame Initialization and temporal RefinementCode3
Local All-Pair Correspondence for Point TrackingCode3
Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV TrackingCode2
Autoregressive Visual TrackingCode2
ODTrack: Online Dense Temporal Token Learning for Visual TrackingCode2
Towards Real-World Visual Tracking with Temporal ContextsCode2
Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel BaselineCode2
XTrack: Multimodal Training Boosts RGB-X Video Object TrackersCode2
An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-TrainingCode2
Similarity-Guided Layer-Adaptive Vision Transformer for UAV TrackingCode2
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream FrameworkCode2
R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement LearningCode2
Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion ApproachCode2
Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale DatasetCode2
Tracking Meets LoRA: Faster Training, Larger Model, Stronger PerformanceCode2
Exploring Enhanced Contextual Information for Video-Level Object TrackingCode2
Fast Online Object Tracking and Segmentation: A Unifying ApproachCode2
You Only Demonstrate Once: Category-Level Manipulation from Single Visual DemonstrationCode2
Long-term Frame-Event Visual Tracking: Benchmark Dataset and BaselineCode2
VastTrack: Vast Category Visual Object TrackingCode2
Learning Spatio-Temporal Transformer for Visual TrackingCode1
HIPTrack: Visual Tracking with Historical PromptsCode1
Learning to Adversarially Blur Visual Object TrackingCode1
IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object TrackingCode1
AiATrack: Attention in Attention for Transformer Visual TrackingCode1
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box EstimationCode1
Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV TrackingCode1
Joint Visual Grounding and Tracking with Natural Language SpecificationCode1
Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam SearchCode1
Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and SegmentationCode1
LaSOT: A High-quality Large-scale Single Object Tracking BenchmarkCode1
Learning to Fuse Asymmetric Feature Maps in Siamese TrackersCode1
High-Performance Long-Term Tracking with Meta-UpdaterCode1
Exploring Lightweight Hierarchical Vision Transformers for Efficient Visual TrackingCode1
How to Train Your Energy-Based Model for RegressionCode1
Explicit Visual Prompts for Visual Object TrackingCode1
Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual TrackingCode1
Efficient Motion Prompt Learning for Robust Visual TrackingCode1
AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal RegularizationCode1
Efficient Visual Tracking via Hierarchical Cross-Attention TransformerCode1
Automatic Failure Recovery and Re-Initialization for Online UAV Tracking with Joint Scale and Aspect Ratio OptimizationCode1
Fully Convolutional Online TrackingCode1
Global Instance Tracking: Locating Target More Like HumansCode1
Tracking-by-Trackers with a Distilled and Reinforced ModelCode1
Transformer TrackingCode1
Improving Underwater Visual Tracking With a Large Scale Dataset and Image EnhancementCode1
Deeper and Wider Siamese Networks for Real-Time Visual TrackingCode1
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