{"url":"/task/sign-language-translation","name":"Sign Language Translation","slug":"sign-language-translation","description_markdown":"Given a video containing sign language, the task is to predict the translation into (written) spoken language.\r\n\r\nImage credit: [How2Sign](https://how2sign.github.io/)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":153,"papers_with_code":56,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":17,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/sign-language-translation-on-rwth-phoenix","slug":"sign-language-translation-on-rwth-phoenix","dataset":"RWTH-PHOENIX-Weather 2014 T","dataset_url":"/dataset/rwth-phoenix-weather-2014-t","rows_in_archive":11,"metrics":["BLEU-4","ROUGE"],"first_row_in_archive_order":{"model":"MSKA-SLT","paper_title":"Multi-Stream Keypoint Attention Network for Sign Language Recognition and Translation","paper_url":"/paper/multi-stream-keypoint-attention-network-for","paper_date":"2024-05-09","arxiv_id":"2405.05672","code_links":[{"title":"sutwangyan/MSKA","url":"https://github.com/sutwangyan/MSKA"}],"syntology":null}},{"leaderboard":"/sota/sign-language-translation-on-csl-daily","slug":"sign-language-translation-on-csl-daily","dataset":"CSL-Daily","dataset_url":"/dataset/csl-daily","rows_in_archive":8,"metrics":["BLEU-4"],"first_row_in_archive_order":{"model":"TwoStream-SLT","paper_title":"Two-Stream Network for Sign Language Recognition and Translation","paper_url":"/paper/two-stream-network-for-sign-language","paper_date":"2022-11-02","arxiv_id":"2211.01367","code_links":[{"title":"FangyunWei/SLRT","url":"https://github.com/FangyunWei/SLRT"}],"syntology":null}},{"leaderboard":"/sota/sign-language-translation-on-aslg-pc12-1","slug":"sign-language-translation-on-aslg-pc12-1","dataset":"ASLG-PC12","dataset_url":"/dataset/aslg-pc12","rows_in_archive":1,"metrics":["BLEU-4"],"first_row_in_archive_order":{"model":"Transformer Ens.","paper_title":"Better Sign Language Translation with STMC-Transformer","paper_url":"/paper/sign-language-translation-with-transformers","paper_date":"2020-04-01","arxiv_id":"2004.00588","code_links":[{"title":"kayoyin/transformer-slt","url":"https://github.com/kayoyin/transformer-slt"}],"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/sign-language-translation-on-how2sign","slug":"sign-language-translation-on-how2sign","dataset":"How2Sign","dataset_url":"/dataset/how2sign","rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":null,"paper_title":"Sign Language Translation from Instructional Videos","paper_url":"/paper/sign-language-translation-from-instructional","paper_date":"2023-04-13","arxiv_id":"2304.06371","code_links":[{"title":"imatge-upc/slt_how2sign_wicv2023","url":"https://github.com/imatge-upc/slt_how2sign_wicv2023"}],"syntology":null}},{"leaderboard":"/sota/sign-language-translation-on-lsa-t","slug":"sign-language-translation-on-lsa-t","dataset":"LSA-T","dataset_url":"/dataset/lsa-t","rows_in_archive":1,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"Keypoints-Transformer-UNLP","paper_title":"LSA-T: The first continuous Argentinian Sign Language dataset for Sign Language Translation","paper_url":"/paper/lsa-t-the-first-continuous-argentinian-sign","paper_date":"2022-11-14","arxiv_id":"2211.15481","code_links":[{"title":"midusi/lsa-t","url":"https://github.com/midusi/lsa-t"}],"syntology":null}},{"leaderboard":"/sota/sign-language-translation-on-mediapi-rgb","slug":"sign-language-translation-on-mediapi-rgb","dataset":"Mediapi-RGB","dataset_url":"/dataset/mediapi-rgb","rows_in_archive":1,"metrics":["BLEU-4"],"first_row_in_archive_order":{"model":"Transformer Baseline","paper_title":"Mediapi-RGB: Enabling Technological Breakthroughs in French Sign Language (LSF) Research through an Extensive Video-Text Corpus","paper_url":"/paper/mediapi-rgb-enabling-technological","paper_date":"2024-02-29","arxiv_id":null,"code_links":[{"title":"youakrim/sign_language_translation_Mediapi-RGB","url":"https://github.com/youakrim/sign_language_translation_Mediapi-RGB"}],"syntology":null}}],"datasets":[{"url":"/dataset/rwth-phoenix-weather-2014-t","name":"RWTH-PHOENIX-Weather 2014 T","full_name":"","num_papers_in_archive":114},{"url":"/dataset/wlasl","name":"WLASL","full_name":"Word-Level American Sign Language","num_papers_in_archive":66},{"url":"/dataset/csl-daily","name":"CSL-Daily","full_name":"","num_papers_in_archive":63},{"url":"/dataset/how2sign","name":"How2Sign","full_name":"A Large-scale Multimodal Dataset for Continuous American Sign Language","num_papers_in_archive":44},{"url":"/dataset/openasl","name":"OpenASL","full_name":"","num_papers_in_archive":15},{"url":"/dataset/ms-asl","name":"MSASL-1000","full_name":"","num_papers_in_archive":9},{"url":"/dataset/bosphorussign22k","name":"BosphorusSign22k","full_name":"","num_papers_in_archive":8},{"url":"/dataset/content4all","name":"Content4All","full_name":"","num_papers_in_archive":3},{"url":"/dataset/isltranslate","name":"ISLTranslate","full_name":"","num_papers_in_archive":2},{"url":"/dataset/aslg-pc12","name":"ASLG-PC12","full_name":"English-ASL Gloss Parallel Corpus 2012","num_papers_in_archive":1},{"url":"/dataset/azsld","name":"AzSLD","full_name":"AzSLD - Azerbaijani Sign Language Dataset","num_papers_in_archive":1},{"url":"/dataset/csl-news","name":"CSL-News","full_name":"","num_papers_in_archive":1},{"url":"/dataset/dailymoth-70h","name":"DailyMoth-70h","full_name":"","num_papers_in_archive":1},{"url":"/dataset/lsa-t","name":"LSA-T","full_name":"Lengua de Señas Argentina - Traducción","num_papers_in_archive":1},{"url":"/dataset/lsfb-datasets","name":"LSFB Datasets","full_name":"French Belgian Sign Language Datasets","num_papers_in_archive":1},{"url":"/dataset/mediapi-rgb","name":"Mediapi-RGB","full_name":"Mediapi-RGB","num_papers_in_archive":1},{"url":"/dataset/wmt-slt22","name":"WMT-SLT","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":56,"tagged_in_all":153,"items":[{"url":"/paper/a-simple-multi-modality-transfer-learning","title":"A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation","date":"2022-03-08","arxiv_id":"2203.04287","repositories_listed":4,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":9}},{"url":"/paper/word-level-deep-sign-language-recognition","title":"Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison","date":"2019-10-24","arxiv_id":"1910.11006","repositories_listed":3,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/signbank-multilingual-sign-language","title":"SignBank+: Preparing a Multilingual Sign Language Dataset for Machine Translation Using Large Language Models","date":"2023-09-20","arxiv_id":"2309.11566","repositories_listed":2,"syntology":null},{"url":"/paper/an-open-source-gloss-based-baseline-for","title":"An Open-Source Gloss-Based Baseline for Spoken to Signed Language Translation","date":"2023-05-28","arxiv_id":"2305.17714","repositories_listed":2,"syntology":null},{"url":"/paper/tspnet-hierarchical-feature-learning-via","title":"TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation","date":"2020-10-12","arxiv_id":"2010.05468","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/sign-language-transformers-joint-end-to-end","title":"Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation","date":"2020-03-30","arxiv_id":"2003.13830","repositories_listed":2,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/multilingual-gloss-free-sign-language","title":"Multilingual Gloss-free Sign Language Translation: Towards Building a Sign Language Foundation Model","date":"2025-05-30","arxiv_id":"2505.24355","repositories_listed":1,"syntology":null},{"url":"/paper/geo-sign-hyperbolic-contrastive-1","title":"Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation","date":"2025-05-30","arxiv_id":"2506.00129","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/sign-language-translation-using-frame-and","title":"Sign Language Translation using Frame and Event Stream: Benchmark Dataset and Algorithms","date":"2025-03-09","arxiv_id":"2503.06484","repositories_listed":1,"syntology":null},{"url":"/paper/uni-sign-toward-unified-sign-language","title":"Uni-Sign: Toward Unified Sign Language Understanding at Scale","date":"2025-01-25","arxiv_id":"2501.15187","repositories_listed":1,"syntology":{"n":15,"n_ran":14,"n_unverified":1,"n_pointer_only":15}},{"url":"/paper/real-time-bangla-sign-language-translator","title":"Real-time Bangla Sign Language Translator","date":"2024-12-21","arxiv_id":"2412.16497","repositories_listed":1,"syntology":null},{"url":"/paper/improvement-in-sign-language-translation","title":"Improvement in Sign Language Translation Using Text CTC Alignment","date":"2024-12-12","arxiv_id":"2412.09014","repositories_listed":1,"syntology":null},{"url":"/paper/signformer-is-all-you-need-towards-edge-ai-1","title":"Signformer is all you need: Towards Edge AI for Sign Language","date":"2024-11-19","arxiv_id":"2411.12901","repositories_listed":1,"syntology":null},{"url":"/paper/diverse-sign-language-translation","title":"Diverse Sign Language Translation","date":"2024-10-25","arxiv_id":"2410.19586","repositories_listed":1,"syntology":null},{"url":"/paper/signattention-on-the-interpretability-of","title":"SignAttention: On the Interpretability of Transformer Models for Sign Language Translation","date":"2024-10-18","arxiv_id":"2410.14506","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/sign-language-sense-disambiguation","title":"Sign Language Sense Disambiguation","date":"2024-09-13","arxiv_id":"2409.08780","repositories_listed":1,"syntology":null},{"url":"/paper/less-is-more-concatenating-videos-for-sign","title":"Less is more: concatenating videos for Sign Language Translation from a small set of signs","date":"2024-09-03","arxiv_id":"2409.01506","repositories_listed":1,"syntology":null},{"url":"/paper/event-stream-based-sign-language-translation","title":"Event Stream based Sign Language Translation: A High-Definition Benchmark Dataset and A New Algorithm","date":"2024-08-20","arxiv_id":"2408.10488","repositories_listed":1,"syntology":null},{"url":"/paper/an-efficient-sign-language-translation-using","title":"An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMs","date":"2024-08-20","arxiv_id":"2408.10593","repositories_listed":1,"syntology":null},{"url":"/paper/an-open-source-american-sign-language","title":"An Open-Source American Sign Language Fingerspell Recognition and Semantic Pose Retrieval Interface","date":"2024-08-17","arxiv_id":"2408.09311","repositories_listed":1,"syntology":null},{"url":"/paper/sign-language-translation-with-sentence","title":"Sign Language Translation with Sentence Embedding Supervision","date":"2024-08-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/gloss2text-sign-language-gloss-translation","title":"Gloss2Text: Sign Language Gloss translation using LLMs and Semantically Aware Label Smoothing","date":"2024-07-01","arxiv_id":"2407.01394","repositories_listed":1,"syntology":null},{"url":"/paper/signbleu-automatic-evaluation-of-multi","title":"SignBLEU: Automatic Evaluation of Multi-channel Sign Language Translation","date":"2024-06-10","arxiv_id":"2406.06648","repositories_listed":1,"syntology":null},{"url":"/paper/improving-gloss-free-sign-language","title":"Improving Gloss-free Sign Language Translation by Reducing Representation Density","date":"2024-05-23","arxiv_id":"2405.14312","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/multi-stream-keypoint-attention-network-for","title":"Multi-Stream Keypoint Attention Network for Sign Language Recognition and Translation","date":"2024-05-09","arxiv_id":"2405.05672","repositories_listed":1,"syntology":null},{"url":"/paper/corrnet-sign-language-recognition-and","title":"CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal Correlation","date":"2024-04-17","arxiv_id":"2404.11111","repositories_listed":1,"syntology":null},{"url":"/paper/factorized-learning-assisted-with-large","title":"Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation","date":"2024-03-19","arxiv_id":"2403.12556","repositories_listed":1,"syntology":null},{"url":"/paper/mediapi-rgb-enabling-technological","title":"Mediapi-RGB: Enabling Technological Breakthroughs in French Sign Language (LSF) Research through an Extensive Video-Text Corpus","date":"2024-02-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-privacy-aware-sign-language","title":"Towards Privacy-Aware Sign Language Translation at Scale","date":"2024-02-14","arxiv_id":"2402.09611","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":12}},{"url":"/paper/a-simple-baseline-for-spoken-language-to-sign","title":"A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars","date":"2024-01-09","arxiv_id":"2401.04730","repositories_listed":1,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}