18 datasets found

The dataset is used for 3D human motion-language tasks, where 3D human motions are paired with their corresponding text descriptions.

The ACTOR dataset is used for action-conditioned 3D human motion synthesis.

The dataset used in the paper is a collection of kinematic data from human motion, including joints' position, rotation, and force.

Human motion modeling is a critical component of animating virtual characters to imitate vivid and rich human movements, which has been a vital topic for many applications, such...

Human motion modeling is a critical component of animating virtual characters to imitate vivid and rich human movements, which has been a vital topic for many applications, such...

Human motion modeling is important for many modern graphics applications, which typically require professional skills. In order to remove the skill barriers for laymen, recent...

UBCFashion is a monocular video dataset containing 500 human videos with natural fashion motions.

A large-scale human motion capture dataset with unique action categories.

TEACH: Temporal Action Composition for 3D Humans.

The BABEL dataset is a multilingual speech recognition dataset containing over 1,000 hours of speech from 6 languages.

LSP: Large-Scale Partial Human Body Part Annotation. LSP: Large-Scale Partial Human Body Part Annotation. LSP: Large-Scale Partial Human Body Part Annotation. LSP: Large-Scale...

A dataset for human motion synthesis, consisting of 3D human motion data and corresponding text descriptions.

A dataset for human motion synthesis, consisting of 3D human motion data and corresponding text descriptions.

A dataset for human motion synthesis, consisting of 3D human motion data and corresponding text descriptions.

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...

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...