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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 11–20 of 525 papers

Title	Date	Tasks	Status	Hype
An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training	Apr 18, 2024	Contrastive LearningCPU	CodeCode Available	2
R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement Learning	Jun 27, 2025	Object TrackingTemplate Matching	CodeCode Available	2
Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking	Mar 9, 2025	Visual Tracking	CodeCode Available	2
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework	Mar 22, 2022	Object TrackingRelation	CodeCode Available	2
Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approach	Aug 2, 2024	cross-modal alignmentMultiple Object Tracking	CodeCode Available	2
Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline	Sep 26, 2023	Knowledge DistillationObject Tracking	CodeCode Available	2
Exploring Enhanced Contextual Information for Video-Level Object Tracking	Dec 15, 2024	ObjectObject Tracking	CodeCode Available	2
Fast Online Object Tracking and Segmentation: A Unifying Approach	Dec 12, 2018	ObjectObject Tracking	CodeCode Available	2
Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking	Dec 28, 2024	Knowledge DistillationVisual Tracking	CodeCode Available	2
ODTrack: Online Dense Temporal Token Learning for Visual Tracking	Jan 3, 2024	Semi-Supervised Video Object SegmentationVideo Object Tracking	CodeCode Available	2

Show:10 25 50

← PrevPage 2 of 53Next →

All datasets TNL2K DAVIS Kinetics Kubric RGB-Stacking LaSOT OTB-100 OTB-2013 Second dialogue state tracking challenge TrackingNet

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ARTrack-L	AUC	60.3	—	Unverified
2	UNINEXT-H	AUC	59.3	—	Unverified
3	JointNLT	AUC	56.9	—	Unverified
4	OSTrack	AUC	55.9	—	Unverified
5	TransT	AUC	50.7	—	Unverified
6	AdaSwitcher	AUC	42	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TAPIR (Panning MOVi-E)	Average Jaccard	61.3	—	Unverified
2	TAPIR (MOVi-E)	Average Jaccard	59.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TAPIR (Panning MOVi-E)	Average Jaccard	57.2	—	Unverified
2	TAPIR (MOVi-E)	Average Jaccard	57.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TAPIR (Panning MOVi-E)	Average Jaccard	84.7	—	Unverified
2	TAPIR (MOVi-E)	Average Jaccard	84.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TAPIR (MOVi-E)	Average Jaccard	66.2	—	Unverified
2	TAPIR (Panning MOVi-E)	Average Jaccard	62.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TATrack-L	AUC	71.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SiamFC-lu (Ours)	AUC	0.32	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SiamFC-lu (Ours)	AUC	0.66	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MDNet	Score	0.64	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TATrack-L	ACCURACY	0.85	—	Unverified