paper-with-me

How2Sign

A Large-scale Multimodal Dataset for Continuous American Sign Language

홈페이지 · 논문 44편

The How2Sign is a multimodal and multiview continuous American Sign Language (ASL) dataset consisting of a parallel corpus of more than 80 hours of sign language videos and a set of corresponding modalities including speech, English transcripts, and depth. A three-hour subset was further recorded in the Panoptic studio enabling detailed 3D pose estimation.

Texts3DRGB-DRGB Video American Sign Language

벤치마크

Sign Language Translation on How2Sign 결과 4개
Video Generation on How2Sign 결과 2개
Video Inpainting on How2Sign 결과 2개