95 datasets found

Human pose estimation using center points

PoseTrack: A benchmark for human pose estimation and tracking.

The COCO2017 dataset is utilized to evaluate the quantization performance for object detection task.

Human pose estimation has achieved significant progress in recent years. However, most of the recent methods focus on improving accuracy using complicated models and ignoring...

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 dataset used in the paper is the LEMO dataset.

The EgoHumans dataset consists of approximately 1 hour of video of up to 5 subjects performing highly dynamic activities.

The Campus and Shelf datasets contain approximately 4000 frames of a single scene.

The CMU Panoptic Studio dataset is a large multi-view pose estimation dataset with several synchronized camera sequences of multiple interacting subjects.

Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs

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.

The Microsoft COCO Keypoints dataset is a large-scale benchmark for 2D human pose estimation and tracking in images.

PandaNet is a single-shot approach for multi-person 3D pose estimation that can handle images with a large number of people, strong occlusions, and varying sizes.

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.

Human 3D pose estimation from a single image is a challenging task with numerous applications. Convolutional Neural Networks (CNNs) have recently achieved superior performance...

Human 3D pose estimation from a single image is a challenging task with numerous applications. Convolutional Neural Networks (CNNs) have recently achieved superior performance...