11 datasets found

A dataset of 2000 motions, with 400 motions for each of the five baseline models.

A dataset of 2000 motions, with 400 motions for each of the five baseline models.

A dataset of 2000 motions, with 400 motions for each of the five baseline models.

Human motion generation stands as a significant pursuit in generative computer vision, while achieving long-sequence and efficient motion generation remains challenging.

Human motion generation has paramount importance in computer animation. It is a challenging generative temporal modelling task due to the vast possibilities of human motion,...

KIT-ML is a dataset of human motion sequences, each annotated with 1-4 natural language descriptions.

A large-scale Wild Motion-Caption dataset (WMC) is constructed, which comprises 141k motion-caption pairs.

AIST++ is a large-scale dance motion dataset built from [31]. It contains 1409 sequences of dance motions, covering 10 different dance genres with hundreds of choreographies.

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 dataset used in this paper is the BABEL dataset, which contains 10881 motion sequences, with 65926 subsequences and the corresponding textual labels.

Human motion generation includes the intuitive description, editing, and generation of 3D sequences of human poses. It is relevant to many applications that require virtual or...