7 datasets found

Tags: text-to-motion

Filter Results

  • MDM

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

  • MotionDiffuse

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

  • TM2T

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

  • Length-Aware Motion Synthesis via Latent Diffusion

    Length-Aware Latent Diffusion (LADiff) is a novel approach for generating motion sequences guided by textual descriptions with dynamics and style conditioned by the target...

  • KIT-ML

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

  • Wild Motion-Caption (WMC)

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

  • BABEL dataset

    The dataset used in this paper is the BABEL dataset, which contains 10881 motion sequences, with 65926 subsequences and the corresponding textual labels.
You can also access this registry using the API (see API Docs).