45 datasets found

Human pose estimation requires high-resolution representation to achieve high performance. We present an efficient high-resolution network, Lite-HRNet, for human pose estimation.

The COCO keypoint detection task dataset contains 150K person instances annotated with 17 keypoints.

The SPHP dataset contains synchronized, complementary images of edge and motion vectors along with ground truth labels for 13 joints.

The dataset used for training and testing the proposed TetraTSDF model for 3D human reconstruction from a single image with a tetrahedral outer shell.

Multi-person pose estimation and tracking serve as critical steps for video understanding. Most state-of-the-art approaches rely on first estimating poses in each frame and only...

A dataset for gait analysis using a single RGB camera and a mobile tele-robot for healthcare

Human pose estimation Is the process of recovering anatomical keypoints of the human body given an image or a video, which deeply relies on both visual cues and keypoints...

Human pose estimation Is the process of recovering anatomical keypoints of the human body given an image or a video, which deeply relies on both visual cues and keypoints...

The PanopTOP31K dataset consists of 34k top-view and 34k front-view images coming from video sequences of 24 different actors.

The ITOP dataset contains depth images from top and front view. The training split and the test split consist of 40k and 10k images, respectively.

Human Pose Estimation (HPE) aims at retrieving the 3D position of human joints from images or videos. We show that current 3D HPE methods suffer a lack of viewpoint...

Biwi Kinect is a real-world dataset containing over 15K images of 20 people.

The Human3.6M dataset is a large-scale dataset for 3D human pose estimation in videos. It consists of 3.6 million frames captured by four 50 Hz cameras.

DiffPose: A conditional diffusion model for multi-hypothesis human pose estimation from a single image.

Motion synthesis in real-world 3D scenes has recently attracted much attention. However, the static environment assumption made by most current methods usually cannot be...

A dataset for handgun detection using combined human pose and weapon appearance

Human3.6m: Large scale datasets and predictive methods for 3D human sensing in natural environments.

The TikTok dataset is used for human pose estimation task. It contains videos of humans performing different actions.

The OCHuman dataset is a more challenging dataset, where each human instance is heavily occluded by one or several others and the postures of the human bodies are more complex.

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...