SOTAVerified

Visual Object Tracking

Visual Object Tracking is an important research topic in computer vision, image understanding and pattern recognition. Given the initial state (centre location and scale) of a target in the first frame of a video sequence, the aim of Visual Object Tracking is to automatically obtain the states of the object in the subsequent video frames.

Source: Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 341 papers

TitleStatusHype
SAM 2: Segment Anything in Images and VideosCode11
SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware MemoryCode9
Awesome Multi-modal Object TrackingCode5
Underwater Camouflaged Object Tracking Meets Vision-Language SAM2Code5
SiamMask: A Framework for Fast Online Object Tracking and SegmentationCode4
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory TreeCode4
Universal Instance Perception as Object Discovery and RetrievalCode3
A Distractor-Aware Memory for Visual Object Tracking with SAM2Code3
Putting the Object Back into Video Object SegmentationCode3
MixFormer: End-to-End Tracking with Iterative Mixed AttentionCode2
Autoregressive Visual TrackingCode2
Tracking Anything in High QualityCode2
Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel BaselineCode2
ODTrack: Online Dense Temporal Token Learning for Visual TrackingCode2
Exploring Enhanced Contextual Information for Video-Level Object TrackingCode2
Elysium: Exploring Object-level Perception in Videos via MLLMCode2
SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object TrackingCode2
Towards Grand Unification of Object TrackingCode2
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream FrameworkCode2
SSD: Single Shot MultiBox DetectorCode2
Tracking Meets LoRA: Faster Training, Larger Model, Stronger PerformanceCode2
You Only Demonstrate Once: Category-Level Manipulation from Single Visual DemonstrationCode2
Roboflow 100: A Rich, Multi-Domain Object Detection BenchmarkCode2
Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition BenchmarkCode2
R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement LearningCode2
Fast Online Object Tracking and Segmentation: A Unifying ApproachCode2
OmniVid: A Generative Framework for Universal Video UnderstandingCode2
ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to DescribeCode2
MixFormer: End-to-End Tracking with Iterative Mixed AttentionCode2
Progressive Representation Learning for Real-Time UAV TrackingCode2
VastTrack: Vast Category Visual Object TrackingCode2
Learning Spatial-Frequency Transformer for Visual Object TrackingCode1
HIPTrack: Visual Tracking with Historical PromptsCode1
Learning Spatio-Temporal Transformer for Visual TrackingCode1
Do Different Tracking Tasks Require Different Appearance Models?Code1
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking TasksCode1
Learning to Adversarially Blur Visual Object TrackingCode1
Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and SegmentationCode1
Learning Spatio-Appearance Memory Network for High-Performance Visual TrackingCode1
IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object TrackingCode1
Improving Underwater Visual Tracking With a Large Scale Dataset and Image EnhancementCode1
Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box EstimationCode1
How to Train Your Energy-Based Model for RegressionCode1
Improving Visual Object Tracking through Visual PromptingCode1
Learning to Fuse Asymmetric Feature Maps in Siamese TrackersCode1
Energy-Based Models for Deep Probabilistic RegressionCode1
All-Day Object Tracking for Unmanned Aerial VehicleCode1
Deep Convolutional Neural Networks for Thermal Infrared Object TrackingCode1
Transformer TrackingCode1
AiATrack: Attention in Attention for Transformer Visual TrackingCode1
Show:102550
← PrevPage 1 of 7Next →
All datasetsLaSOTGOT-10kTrackingNetLaSOT-extOTB-2015UAV123TNL2KVOT2017/18DiDiNeedForSpeedYouTube-VOS 2018AVisT

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SPMTrack-GAUC77.4—Unverified
2SPMTrack-LAUC76.8—Unverified
3MCITrack-L384AUC76.6—Unverified
4LoRAT-g-378AUC76.2—Unverified
5MCITrack-B224AUC75.3—Unverified
6DAM4SAMAUC75.1—Unverified
7LoRAT-L-378AUC75.1—Unverified
8SPMTrack-BAUC74.9—Unverified
9RTracker-LAUC74.7—Unverified
10SAMURAI-LAUC74.2—Unverified
#ModelMetricClaimedVerifiedStatus
1SAMURAI-LAverage Overlap81.7—Unverified
2DAM4SAMAverage Overlap81.1—Unverified
3SPMTrack-GAverage Overlap81—Unverified
4MITSAverage Overlap80.4—Unverified
5MCITrack-L384Average Overlap80—Unverified
6SPMTrack-LAverage Overlap80—Unverified
7ARTrackV2-LAverage Overlap79.5—Unverified
8LoRAT-g-378Average Overlap78.9—Unverified
9ARTrack-LAverage Overlap78.5—Unverified
10ODTrack-LAverage Overlap78.2—Unverified
#ModelMetricClaimedVerifiedStatus
1DropTrackNormalized Precision88.9—Unverified
2MCITrack-L384Accuracy87.9—Unverified
3SPMTrack-GAccuracy87.3—Unverified
4SPMTrack-LAccuracy86.9—Unverified
5MCITrack-B224Accuracy86.3—Unverified
6ODTrack-LAccuracy86.1—Unverified
7ARTrackV2-LAccuracy86.1—Unverified
8SPMTrack-BAccuracy86.1—Unverified
9MixViT-L(ConvMAE)Accuracy86.1—Unverified
10LoRAT-g-378Accuracy86—Unverified
#ModelMetricClaimedVerifiedStatus
1SAMURAI-LAUC61—Unverified
2DAM4SAMAUC60.9—Unverified
3LoRAT-L-378AUC56.6—Unverified
4LoRAT-g-378AUC56.5—Unverified
5UNINEXT-HAUC56.2—Unverified
6MCITrack-L384AUC55.7—Unverified
7RTracker-LAUC54.9—Unverified
8MCITrack-B224AUC54.6—Unverified
9ODTrack-LAUC53.9—Unverified
10ARTrackV2-LAUC53.4—Unverified
#ModelMetricClaimedVerifiedStatus
1GradNetPrecision0.86—Unverified
2SPMTrack-BAUC0.73—Unverified
3ODTrack-LAUC0.72—Unverified
4ODTrack-BAUC0.72—Unverified
5STMTrackAUC0.72—Unverified
6SAMURAI-LAUC0.72—Unverified
7PiVOT-LAUC0.71—Unverified
8HIPTrackAUC0.71—Unverified
9KeepTrackAUC0.71—Unverified
10TRASFUSTAUC0.7—Unverified
#ModelMetricClaimedVerifiedStatus
1LoRAT-g-378AUC0.74—Unverified
2NeighborTrack-OSTrackAUC0.73—Unverified
3LoRAT-L-378AUC0.73—Unverified
4SPMTrack-BAUC0.72—Unverified
5ARTrackV2-LAUC0.72—Unverified
6ARTrack-LAUC0.71—Unverified
7OSTrack -384AUC0.71—Unverified
8AiATrackAUC0.71—Unverified
9HIPTrackAUC0.71—Unverified
10MixFormerAUC0.7—Unverified
#ModelMetricClaimedVerifiedStatus
1MCITrack-L384AUC65.3—Unverified
2SPMTrack-GAUC64.7—Unverified
3SPMTrack-LAUC63.7—Unverified
4MCITrack-B224AUC62.9—Unverified
5LoRAT-g-378AUC62.7—Unverified
6LoRAT-L-378AUC62.3—Unverified
7SPMTrack-BAUC62—Unverified
8ODTrack-LAUC61.7—Unverified
9ARTrackV2-LAUC61.6—Unverified
10ODTrack-BAUC60.9—Unverified
#ModelMetricClaimedVerifiedStatus
1SiamMask_EExpected Average Overlap (EAO)0.45—Unverified
2SiamFC++Expected Average Overlap (EAO)0.43—Unverified
3SiamRPN++_RExpected Average Overlap (EAO)0.42—Unverified
4THOR-SiamRPNExpected Average Overlap (EAO)0.42—Unverified
5SiamRPN++Expected Average Overlap (EAO)0.41—Unverified
6THOR-SiamMaskExpected Average Overlap (EAO)0.41—Unverified