A Large-scale Multimodal Dataset for Continuous American Sign Language
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.
Variants: How2Sign
This dataset is used in 3 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Sign Language Translation | Unknown | Sign Language Translation from Instructional … | 2023-04-13 |
| Video Inpainting | INR-V | INR-V: A Continuous Representation Space … | 2022-10-29 |
| Video Generation | INR-V | INR-V: A Continuous Representation Space … | 2022-10-29 |
Recent papers with results on this dataset: