4 datasets found

Tags: co-speech gesture

Filter Results

  • GestureDiffuCLIP

    GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents

  • TalkSHOW

    A high-quality audiovisual dataset for speech-to-motion generation, consisting of 3D holistic body meshes and synchronized speech.

  • BEAT2

    A dataset for co-speech gesture generation, containing 35,758 clips.

  • GES-X

    A large-scale co-speech gesture dataset containing more than 40M high-quality 3D meshed postures across 4.3K speakers from in-the-wild talk show videos.
You can also access this registry using the API (see API Docs).