SOTAVerified

Keypoint Detection

Keypoint Detection is essential for analyzing and interpreting images in computer vision. It involves simultaneously detecting and localizing interesting points in an image. Keypoints, also known as interest points, are spatial locations or points in the image that define what is interesting or what stands out. They are invariant to image rotation, shrinkage, translation, distortion, etc. Keypoints examples are body joints, facial landmarks, or any other salient points in objects. Keypoints have uses in problems such as pose estimation, object detection and tracking, facial analysis, and augmented reality.

( Image credit: PifPaf: Composite Fields for Human Pose Estimation; "Learning to surf" by fotologic, license: CC-BY-2.0 )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 76–100 of 339 papers

TitleStatusHype
DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts using a Single CameraCode1
MarkerPose: Robust Real-time Planar Target Tracking for Accurate Stereo Pose EstimationCode1
Pose Recognition with Cascade TransformersCode1
HoughNet: Integrating near and long-range evidence for visual detectionCode1
DexYCB: A Benchmark for Capturing Hand Grasping of ObjectsCode1
Bottom-Up Human Pose Estimation Via Disentangled Keypoint RegressionCode1
3D3L: Deep Learned 3D Keypoint Detection and Description for LiDARsCode1
End-to-End Trainable Multi-Instance Pose Estimation with TransformersCode1
Deep Dual Consecutive Network for Human Pose EstimationCode1
Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationCode1
TransPose: Keypoint Localization via TransformerCode1
Fast Fourier ConvolutionCode1
Auto Learning AttentionCode1
UKPGAN: A General Self-Supervised Keypoint DetectorCode1
One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection TasksCode1
EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight TransferCode1
Rotate to Attend: Convolutional Triplet Attention ModuleCode1
Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the WildCode1
RelativeNAS: Relative Neural Architecture Search via Slow-Fast LearningCode1
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware SupervisionCode1
Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint EstimatesCode1
SEKD: Self-Evolving Keypoint Detection and DescriptionCode1
GoodPoint: unsupervised learning of keypoint detection and descriptionCode1
Improving Convolutional Networks With Self-Calibrated ConvolutionsCode1
Learning Human-Object Interaction Detection using Interaction PointsCode1
Show:102550
← PrevPage 4 of 14Next →

No leaderboard results yet.