7 datasets found

Tags: text descriptions

Filter Results

  • ShapeNetSem

    The ShapeNetSem dataset used in the paper for 3D object understanding and manipulation.

  • FLIR, MFNet, COME15K, MCXFace

    Cross-modal datasets with text descriptions for cross-modal image generation under various layout conditions.

  • You2Me

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

  • UMPM

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

  • ExPI

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

  • HumanML3D

    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...

  • Fashion-Gen

    A fashion dataset containing 293,008 fashion images.
You can also access this registry using the API (see API Docs).