Keypoint Detection

79 papers with code • 6 benchmarks • 5 datasets

Keypoint detection involves simultaneously detecting people and localizing their keypoints. Keypoints are the same thing as interest points. They are spatial locations, or points in the image that define what is interesting or what stand out in the image. They are invariant to image rotation, shrinkage, translation, distortion, and so on.

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

Greatest papers with code

Objects as Points

tensorflow/models 16 Apr 2019

We model an object as a single point --- the center point of its bounding box.

Keypoint Detection Real-Time Object Detection

Mask R-CNN

tensorflow/models ICCV 2017

Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance.

3D Instance Segmentation Human Part Segmentation +7

Data Distillation: Towards Omni-Supervised Learning

facebookresearch/detectron CVPR 2018

We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data.

Keypoint Detection Object Detection

Non-local Neural Networks

facebookresearch/detectron CVPR 2018

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time.

Ranked #7 on Action Classification on Toyota Smarthome dataset (using extra training data)

Action Classification Action Recognition +3

OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

CMU-Perceptual-Computing-Lab/openpose 18 Dec 2018

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Keypoint Detection

RMPE: Regional Multi-person Pose Estimation

MVIG-SJTU/AlphaPose ICCV 2017

In this paper, we propose a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes.

Human Detection Keypoint Detection +1

Distribution-Aware Coordinate Representation for Human Pose Estimation

leoxiaobin/deep-high-resolution-net.pytorch CVPR 2020

Interestingly, we found that the process of decoding the predicted heatmaps into the final joint coordinates in the original image space is surprisingly significant for human pose estimation performance, which nevertheless was not recognised before.

 Ranked #1 on Multi-Person Pose Estimation on COCO (using extra training data)

Keypoint Detection Multi-Person Pose Estimation

Deep High-Resolution Representation Learning for Human Pose Estimation

leoxiaobin/deep-high-resolution-net.pytorch CVPR 2019

We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel.

Instance Segmentation Keypoint Detection +4