SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 151 papers

TitleStatusHype
Leveraging Object Priors for Point TrackingCode0
DynOMo: Online Point Tracking by Dynamic Online Monocular Gaussian Reconstruction—0
Can Visual Foundation Models Achieve Long-term Point Tracking?—0
Kalib: Easy Hand-Eye Calibration with Reference Point Tracking—0
A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-ShotCode0
Autogenic Language Embedding for Coherent Point TrackingCode0
Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in VideosCode2
PlantTrack: Task-Driven Plant Keypoint Tracking with Zero-Shot Sim2Real Transfer—0
Local All-Pair Correspondence for Point TrackingCode3
Long-Term 3D Point Tracking By Cost Volume Fusion—0
Motion-prior Contrast Maximization for Dense Continuous-Time Motion EstimationCode1
Power System Architecture and Control for Green Hydrogen Production via Power Converter-less Photovoltaic-Electrolyser Integration—0
Decomposition Betters Tracking Everything EverywhereCode2
TAPVid-3D: A Benchmark for Tracking Any Point in 3DCode5
Optimal Video Compression using Pixel Shift TrackingCode0
Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular VideosCode2
Training-Free Robust Interactive Video Object Segmentation—0
EchoTracker: Advancing Myocardial Point Tracking in EchocardiographyCode2
FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient DescentCode4
Fast Encoder-Based 3D from Casual Videos via Point Track Processing—0
Multiple model estimation under perspective of random-fuzzy dual interpretation of unknown uncertaintyCode0
Solution for Point Tracking Task of ICCV 1st Perception Test Challenge 2023—0
DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video—0
TAPTR: Tracking Any Point with Transformers as Detection—0
Hierarchical Provision of Distribution Grid Flexibility with Online Feedback Optimization—0
Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment AnythingCode1
PIPsUS: Self-Supervised Dense Point Tracking in UltrasoundCode0
StableDrag: Stable Dragging for Point-based Image Editing—0
Tracking-in-range Formulations for Numerical Optimal Control—0
DivaTrack: Diverse Bodies and Motions from Acceleration-Enhanced Three-Point TrackersCode0
BootsTAP: Bootstrapped Training for Tracking-Any-PointCode5
Analysis and implementation of the Buck-Boost Modified Series Forward converter applied to photovoltaic systems—0
Analysis, design, and implementation of the AFZ converter applied to photovoltaic systems—0
Real-Time Dynamic Layout Optimization for Floating Offshore Wind Farm Control—0
LEAP-VO: Long-term Effective Any Point Tracking for Visual OdometryCode3
VGGSfM: Visual Geometry Grounded Deep Structure From MotionCode5
Perception Test 2023: A Summary of the First Challenge And Outcome—0
DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videos—0
Visual Geometry Grounded Deep Structure From MotionCode3
Drag-A-Video: Non-rigid Video Editing with Point-based Interaction—0
Dense Optical Tracking: Connecting the DotsCode2
Improve Myocardial Strain Estimation based on Deformable Groupwise Registration with a Locally Low-Rank Dissimilarity Metric—0
Nonlinear Model Predictive Control for Uranium Extraction-Scrubbing Operation in Spent Nuclear Fuel Treatment Process—0
Visual Material Characteristics Learning for Circular HealthcareCode0
RoboTAP: Tracking Arbitrary Points for Few-Shot Visual ImitationCode0
TROPHY: A Topologically Robust Physics-Informed Tracking Framework for Tropical Cyclones—0
PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point TrackingCode2
Set-Point Tracking MPC with Avoidance Features—0
CoTracker: It is Better to Track TogetherCode4
FreeDrag: Feature Dragging for Reliable Point-based Image EditingCode2
Show:102550
← PrevPage 2 of 4Next →
All datasetsTAP-Vid-DAVISPointOdysseyTAP-Vid-DAVIS-FirstTAP-Vid-KineticsTAP-Vid-Kinetics-FirstTAP-Vid-RGB-StackingPerception TestTAP-Vid

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1LocoTrack-BAverage Jaccard69.4—Unverified
2BootsTAPIRAverage Jaccard66.2—Unverified
3CoTrackerAverage Jaccard65.9—Unverified
#ModelMetricClaimedVerifiedStatus
1PIPs++Survival50.47—Unverified
2PIPs+Survival49.88—Unverified
#ModelMetricClaimedVerifiedStatus
1LocoTrack-BAverage Jaccard64.8—Unverified
2CoTrackerAverage Jaccard62.2—Unverified
#ModelMetricClaimedVerifiedStatus
1BootsTAPIRAverage Jaccard61.4—Unverified
2LocoTrack-BAverage Jaccard59.1—Unverified
#ModelMetricClaimedVerifiedStatus
1LocoTrack-BAverage Jaccard52.3—Unverified
2CoTrackerAverage Jaccard48.8—Unverified
#ModelMetricClaimedVerifiedStatus
1BootsTAPIRAverage Jaccard72.4—Unverified
2LocoTrack-BAverage Jaccard70.8—Unverified
#ModelMetricClaimedVerifiedStatus
1Static BaselineAverage Jaccard0.36—Unverified
#ModelMetricClaimedVerifiedStatus
1PIPs++MTE4.6—Unverified