Point Tracking

Point Tracking, often referred to as Tracking any Point (TAP) involves acquiring, focusing on, and continuously tracking specific target point/points across video frames. The system identifies the target point, maintains focus, and predicts its movement, enabling smooth tracking even if the target moves unpredictably, or through occlusions. TAP has wide applications like object tracking, surveillance, and autonomous navigation.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 101–110 of 151 papers

Title	Date	Tasks	Status	Hype
Segment Anything Meets Point Tracking	Jul 3, 2023	Interactive Video Object SegmentationObject	CodeCode Available	3
TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement	Jun 14, 2023	GPUMotion Estimation	CodeCode Available	3
Require Process Control? LSTMc is all you need!	Jun 13, 2023	AllPoint Tracking	—Unverified	0
Context-PIPs: Persistent Independent Particles Demands Spatial Context Features	Jun 3, 2023	Point Tracking	—Unverified	0
Perception Test: A Diagnostic Benchmark for Multimodal Video Models	May 23, 2023	DiagnosticGrounded Video Question Answering	CodeCode Available	2
MFT: Long-Term Tracking of Every Pixel	May 22, 2023	Point Tracking	CodeCode Available	1
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold	May 18, 2023	Image ManipulationPoint Tracking	CodeCode Available	7
Dual Control of Exploration and Exploitation for Auto-Optimisation Control with Active Learning	Jan 27, 2023	Active LearningPoint Tracking	—Unverified	0
TAP-Vid: A Benchmark for Tracking Any Point in a Video	Nov 7, 2022	Optical Flow EstimationPoint Tracking	CodeCode Available	3
Multilevel Robustness for 2D Vector Field Feature Tracking, Selection, and Comparison	Sep 19, 2022	Point Tracking	—Unverified	0

Show:10 25 50

← PrevPage 11 of 16Next →

All datasets TAP-Vid-DAVIS PointOdyssey TAP-Vid-DAVIS-First TAP-Vid-Kinetics TAP-Vid-Kinetics-First TAP-Vid-RGB-Stacking Perception Test TAP-Vid

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	LocoTrack-B	Average Jaccard	69.4	—	Unverified
2	BootsTAPIR	Average Jaccard	66.2	—	Unverified
3	CoTracker	Average Jaccard	65.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PIPs++	Survival	50.47	—	Unverified
2	PIPs+	Survival	49.88	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LocoTrack-B	Average Jaccard	64.8	—	Unverified
2	CoTracker	Average Jaccard	62.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BootsTAPIR	Average Jaccard	61.4	—	Unverified
2	LocoTrack-B	Average Jaccard	59.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LocoTrack-B	Average Jaccard	52.3	—	Unverified
2	CoTracker	Average Jaccard	48.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BootsTAPIR	Average Jaccard	72.4	—	Unverified
2	LocoTrack-B	Average Jaccard	70.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Static Baseline	Average Jaccard	0.36	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PIPs++	MTE	4.6	—	Unverified