Papers with Code 아카이브

Keypoint Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 0
평가표: 9
보존된 평가 기록: 83

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.

<span style="color:grey; opacity: 0.6">( Image credit: PifPaf: Composite Fields for Human Pose Estimation; "Learning to surf" by fotologic, license: CC-BY-2.0 )</span>

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Keypoint Detection

논문

Learning Transferable Parameters for Unsupervised Domain Adaptation

EEEA-Net: An Early Exit Evolutionary Neural Architecture Search

A Low Rank Promoting Prior for Unsupervised Contrastive Learning

Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle

Exploring Set Similarity for Dense Self-supervised Representation Learning

Task-Aware Sampling Layer for Point-Wise Analysis

Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation

Can Super Resolution be used to improve Human Pose Estimation in Low Resolution Scenarios?

Polarized Self-Attention: Towards High-quality Pixel-wise Regression

SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo

Real-Time Human Pose Estimation on a Smart Walker using Convolutional Neural Networks

GKNet: grasp keypoint network for grasp candidates detection

HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation

RegionViT: Regional-to-Local Attention for Vision Transformers

DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts using a Single Camera

MarkerPose: Robust Real-time Planar Target Tracking for Accurate Stereo Pose Estimation

HoughNet: Integrating near and long-range evidence for visual detection

Pose Recognition with Cascade Transformers

DexYCB: A Benchmark for Capturing Hand Grasping of Objects

Unsupervised Visual Attention and Invariance for Reinforcement Learning

Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression

Learning Spatial Context with Graph Neural Network for Multi-Person Pose Grouping

Unconstrained Face Recognition using ASURF and Cloud-Forest Classifier optimized with VLAD

End-to-end learning of keypoint detection and matching for relative pose estimation

LatentKeypointGAN: Controlling Images via Latent Keypoints

3D3L: Deep Learned 3D Keypoint Detection and Description for LiDARs

Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types

End-to-End Trainable Multi-Instance Pose Estimation with Transformers

Deep Dual Consecutive Network for Human Pose Estimation

Regressive Domain Adaptation for Unsupervised Keypoint Detection

OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association

FisheyeSuperPoint: Keypoint Detection and Description Network for Fisheye Images

Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation

Semi-supervised Keypoint Localization

Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos

TransPose: Keypoint Localization via Transformer