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 51–100 of 339 papers

TitleStatusHype
Learning Keypoints from Synthetic Data for Robotic Cloth FoldingCode1
Multi-Grained Contrast for Data-Efficient Unsupervised Representation LearningCode1
Poseur: Direct Human Pose Regression with TransformersCode1
PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose EstimationCode1
One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection TasksCode1
CoFiNet: Reliable Coarse-to-fine Correspondences for Robust PointCloud RegistrationCode1
RegionViT: Regional-to-Local Attention for Vision TransformersCode1
RelativeNAS: Relative Neural Architecture Search via Slow-Fast LearningCode1
Generative Partition Networks for Multi-Person Pose EstimationCode1
Dense Interspecies Face EmbeddingCode1
Improving Convolutional Networks With Self-Calibrated ConvolutionsCode1
Scale-Free Image Keypoints Using Differentiable Persistent HomologyCode1
Joint Representation Learning and Keypoint Detection for Cross-view Geo-localizationCode1
HPRNet: Hierarchical Point Regression for Whole-Body Human Pose EstimationCode1
DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts using a Single CameraCode1
HoughNet: Integrating near and long-range evidence for visual detectionCode1
Key.Net: Keypoint Detection by Handcrafted and Learned CNN FiltersCode1
Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D FeaturesCode1
Explicit Box Detection Unifies End-to-End Multi-Person Pose EstimationCode1
EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight TransferCode1
2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point CloudsCode1
Deep Dual Consecutive Network for Human Pose EstimationCode1
Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture BreedingCode1
Deep High-Resolution Representation Learning for Human Pose EstimationCode1
A lightweight 3D dense facial landmark estimation model from position map dataCode1
Nonlinear optical encoding enabled by recurrent linear scatteringCode1
GRIT: General Robust Image Task BenchmarkCode1
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware SupervisionCode1
ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor ExtractionCode1
Auto Learning AttentionCode1
DexYCB: A Benchmark for Capturing Hand Grasping of ObjectsCode1
Learning Delicate Local Representations for Multi-Person Pose EstimationCode1
Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint EstimatesCode1
Learning Transferable Parameters for Unsupervised Domain AdaptationCode1
Bottom-Up Human Pose Estimation Via Disentangled Keypoint RegressionCode1
Mask R-CNNCode1
BPFNet: A Unified Framework for Bimodal Palmprint Alignment and FusionCode1
Few-shot Keypoint Detection with Uncertainty Learning for Unseen SpeciesCode1
Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationCode1
NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same ActionCode1
GPU optimization of the 3D Scale-invariant Feature Transform Algorithm and a Novel BRIEF-inspired 3D Fast DescriptorCode1
EEEA-Net: An Early Exit Evolutionary Neural Architecture SearchCode1
Cascaded Pyramid Network for Multi-Person Pose EstimationCode1
Non-local Neural NetworksCode1
CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage RefinementCode1
Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential InformationCode1
AggPose: Deep Aggregation Vision Transformer for Infant Pose EstimationCode1
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
Fast Fourier ConvolutionCode1
Show:102550
← PrevPage 2 of 7Next →

No leaderboard results yet.