{"url":"/dataset/how2sign","name":"How2Sign","full_name":"A Large-scale Multimodal Dataset for Continuous American Sign Language","description_markdown":"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.","description_withheld":null,"homepage":"https://how2sign.github.io/","introduced_date":"2020-08-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/how2sign-a-large-scale-multimodal-dataset-for","title":"How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language","first_author":"Amanda Duarte","url":null},"license":{"name":"Creative Commons Attribution-NonCommercial 4.0 International License","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"3D","url":"/datasets/modality/3d"},{"name":"RGB-D","url":"/datasets/modality/rgb-d"},{"name":"RGB Video","url":"/datasets/modality/rgb-video"}],"tasks":[{"name":"Video Generation","url":"/task/video-generation","datasets_with_task":"/datasets/task/video-generation"},{"name":"Sign Language Recognition","url":"/task/sign-language-recognition","datasets_with_task":"/datasets/task/sign-language-recognition"},{"name":"Video Inpainting","url":"/task/video-inpainting","datasets_with_task":"/datasets/task/video-inpainting"},{"name":"Sign Language Translation","url":"/task/sign-language-translation","datasets_with_task":"/datasets/task/sign-language-translation"},{"name":"Gloss-free Sign Language Translation","url":"/task/gloss-free-sign-language-translation","datasets_with_task":"/datasets/task/gloss-free-sign-language-translation"},{"name":"Topic Classification","url":"/task/topic-classification","datasets_with_task":"/datasets/task/topic-classification"},{"name":"Sign Language Production","url":"/task/sign-language-production","datasets_with_task":"/datasets/task/sign-language-production"}],"languages":[{"name":"American Sign Language","url":"/datasets/language/american-sign-language"}],"variants":["How2Sign"],"data_loaders":[],"num_papers_in_archive":44,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sign-language-translation-on-how2sign","task":"Sign Language Translation","dataset_variant":"How2Sign","rows":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"","paper":"/paper/sign-language-translation-from-instructional","metrics":{"BLEU":"8.03"},"code_links":[{"title":"imatge-upc/slt_how2sign_wicv2023","url":"https://github.com/imatge-upc/slt_how2sign_wicv2023"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-generation-on-how2sign","task":"Video Generation","dataset_variant":"How2Sign","rows":1,"metrics":["FVD16"],"first_row_in_archive_order":{"model":"INR-V","paper":"/paper/inr-v-a-continuous-representation-space-for","metrics":{"FVD16":"144"},"code_links":[{"title":"bipashasen/INRV","url":"https://github.com/bipashasen/INRV"},{"title":"MindSpore-scientific-2/code-5","url":"https://github.com/MindSpore-scientific-2/code-5/tree/main/INR-Implicit-Neural-Representations-with-Periodic-Activation-Functions"},{"title":"MindSpore-scientific/code-11","url":"https://github.com/MindSpore-scientific/code-11/tree/main/INR-Implicit-Neural-Representations-with-Periodic-Activation-Functions"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-inpainting-on-how2sign","task":"Video Inpainting","dataset_variant":"How2Sign","rows":1,"metrics":["L1 error"],"first_row_in_archive_order":{"model":"INR-V","paper":"/paper/inr-v-a-continuous-representation-space-for","metrics":{"L1 error":"4.51"},"code_links":[{"title":"bipashasen/INRV","url":"https://github.com/bipashasen/INRV"},{"title":"MindSpore-scientific-2/code-5","url":"https://github.com/MindSpore-scientific-2/code-5/tree/main/INR-Implicit-Neural-Representations-with-Periodic-Activation-Functions"},{"title":"MindSpore-scientific/code-11","url":"https://github.com/MindSpore-scientific/code-11/tree/main/INR-Implicit-Neural-Representations-with-Periodic-Activation-Functions"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/sign-language-translation-from-instructional","title":"Sign Language Translation from Instructional Videos","date":"2023-04-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/inr-v-a-continuous-representation-space-for","title":"INR-V: A Continuous Representation Space for Video-based Generative Tasks","date":"2022-10-29","rows_on_this_dataset":2,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}