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
Nonlinear optical encoding enabled by recurrent linear scatteringCode1
Flowmind2Digital: The First Comprehensive Flowmind Recognition and Conversion ApproachCode1
Dense Interspecies Face EmbeddingCode1
2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point CloudsCode1
MulT: An End-to-End Multitask Learning TransformerCode1
DexYCB: A Benchmark for Capturing Hand Grasping of ObjectsCode1
Greedy Offset-Guided Keypoint Grouping for Human Pose EstimationCode1
Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationCode1
Auto Learning AttentionCode1
Bottom-Up Human Pose Estimation Via Disentangled Keypoint RegressionCode1
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware SupervisionCode1
Explicit Box Detection Unifies End-to-End Multi-Person Pose EstimationCode1
HoughNet: Integrating near and long-range evidence for visual detectionCode1
HPRNet: Hierarchical Point Regression for Whole-Body Human Pose EstimationCode1
PDC-Net+: Enhanced Probabilistic Dense Correspondence NetworkCode1
Edge Weight Prediction For Category-Agnostic Pose EstimationCode1
EEEA-Net: An Early Exit Evolutionary Neural Architecture SearchCode1
Cascaded Pyramid Network for Multi-Person Pose EstimationCode1
CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage RefinementCode1
AggPose: Deep Aggregation Vision Transformer for Infant Pose EstimationCode1
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential InformationCode1
Centroid Distance Keypoint Detector for Colored Point CloudsCode1
End-to-End Trainable Multi-Instance Pose Estimation with TransformersCode1
EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual LocalizationCode1
EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight TransferCode1
Show:102550
← PrevPage 4 of 14Next →

No leaderboard results yet.