32 datasets found

The H36M-Original dataset consists of 6 action classes, with 16 frames per class.

The NTU-4A dataset is derived from the NTU-Original dataset, using the 4A pipeline to generate synthetic data.

The NTU-Original dataset consists of 49 single-person action classes from the real world.

The 4A pipeline generates realistic animations in varied game environments, viewed from multiple viewpoints.

Humanoid Reaction Synthesis is pivotal for creating highly interactive and empathetic robots that can seamlessly integrate into human environments, enhancing the way we live,...

HumanML3D is a text-to-motion dataset built upon AMASS dataset and HumanAct12. It provides a wide range of motion-language pairs which cover ordinary activities, such as...

Realtime multi-person 2D pose estimation using part affinity fields.

Generating holistic 3D human motion from speech.

The UCF101 dataset contains 13320 videos distributed in 101 action categories. This dataset is different from the above ones in that it contains mostly coarse sports activities...

Video classification is a fundamental problem in many video-based tasks. Applications such as autonomous driving technology, controlling drones and robots are driving the demand...

A new indoor human motion dataset for autonomous robots, RoAM is a synchronised and timestamped image-action pair sequence dataset, recorded with a Turtlebot3 Burger robot with...

MPI-INF-3DHP: A Large-Scale Benchmark for 3D Human Pose Estimation in the Wild. MPI-INF-3DHP: A Large-Scale Benchmark for 3D Human Pose Estimation in the Wild. MPI-INF-3DHP: A...