47 datasets found

The Leeds Sports Pose dataset contains 1000 images for training, which are combined with 4000 images from its extended version.

The Olympic Sports dataset consists of video sequences of athletes practicing 16 different sports. The dataset contains an overall number of 113,516 frames, covering a rich set...

The Pose dataset is a subset of the Panoptic dataset, containing scenes with a single person and cameras.

The Mafia and Ultimatum datasets are subsets of the Panoptic dataset, containing scenes with multiple people and cameras.

The Panoptic dataset is a dense camera grid setup, capturing real video data of scenes with multiple people and cameras densely covering the viewing sphere.

A fully automated system that estimates the camera intrinsics, the ground plane, and physical distances between people from a single RGB image or video.

AR dataset is a dataset of images with a single or few people in the scene in common poses and 25K images with a single person in the scene performing fitness exercises.

TotalCapture dataset is a real-time capture of human motion and surface geometry using a single depth camera.

A 2D pose refinement network for bias-free multi-view 3D human pose estimation.

A dataset for human pose estimation that consists of images with annotated body parts.

A dataset for human pose estimation that consists of images with annotated body parts.

A dataset for human pose estimation that consists of images with annotated body parts.

A dataset for human pose estimation that consists of images with annotated body parts.

A dataset for human pose estimation that consists of images with annotated body parts.

A graphical model for human pose estimation that exploits the fact that local image measurements can be used to detect parts and predict spatial relationships between them.

Human pose estimation refers to the task of recognizing postures by localizing body keypoints (head, shoulders, elbows, wrists, knees, ankles, etc.) from images.

The MPII Pose Descriptions Dataset is a dataset created in this paper, containing up to four pose descriptions for each annotated image.

A large-scale dataset of human poses and their text descriptions extracted from large-scale image datasets.

Simultaneously-collected multimodal lying pose dataset for in-bed human pose monitoring under adverse vision conditions.

Human pose estimation from ambiguous pressure data using a temporal adaptation of ViTPose.