mlsanityData to 14 Oct 2026

YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus

arXiv 2306.15162 ↗First posted 27 Jun 2023cs.CL cs.CVcited by 75

Not on the map. Why?

Abstract (arXiv)

Machine learning for sign languages is bottlenecked by data. In this paper, we present YouTube-ASL, a large-scale, open-domain corpus of American Sign Language (ASL) videos and accompanying English captions drawn from YouTube. With ~1000 hours of videos and >2500 unique signers, YouTube-ASL is ~3x as large and has ~10x as many unique signers as the largest prior ASL dataset. We train baseline models for ASL to English translation on YouTube-ASL and evaluate them on How2Sign, where we achieve a new finetuned state of the art of 12.39 BLEU and, for the first time, report zero-shot results.

Key facts. Cited by 75 papers in the map (data through 14 Oct 2026). Builds on 34 of its 48 references that are in the map. First posted on arXiv 27 Jun 2023.

Builds on

34 of 48 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  5. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  6. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  7. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
  8. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  9. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 905
  10. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  11. 2019MediaPipe: A Framework for Building Perception Pipelinescited by 583
  12. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 560
22 more
  1. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 469
  2. 2016YouTube-8M: A Large-Scale Video Classification Benchmarkcited by 324
  3. 2020Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translationcited by 256
  4. 2019Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparisoncited by 218
  5. 2021Improving Sign Language Translation with Monolingual Data by Sign Back-Translationcited by 179
  6. 2020How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Languagecited by 173
  7. 2018MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Languagecited by 118
  8. 2021Learning Compact Metrics for MTcited by 93
  9. 2019Sign Language Recognition, Generation, and Translation: An Interdisciplinary Perspectivecited by 87
  10. 2020Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognitioncited by 74
  11. 2022Open-Domain Sign Language Translation Learned from Online Videocited by 72
  12. 2021Including Signed Languages in Natural Language Processingcited by 68
  13. 2018Neural Sign Language Translation based on Human Keypoint Estimationcited by 65
  14. 2023Sign Language Translation from Instructional Videoscited by 39
  15. 2023SLTUNET: A Simple Unified Model for Sign Language Translationcited by 35
  16. 2023Gloss-Free End-to-End Sign Language Translationcited by 32
  17. 2021OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languagescited by 31
  18. 2021Content4All Open Research Sign Language Translation Datasetscited by 30
  19. 2019Fingerspelling recognition in the wild with iterative visual attentioncited by 28
  20. 2021Evaluating the Immediate Applicability of Pose Estimation for Sign Language Recognitioncited by 25
  21. 2018American Sign Language fingerspelling recognition in the wildcited by 20
  22. 2022Machine Translation from Signed to Spoken Languages: State of the Art and Challengescited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 21; 2025: 21; 2026: 33.

75 papers.

Sort:

By area:

  1. 2024Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translationcited by 57
  2. 2025Uni-Sign: Toward Unified Sign Language Understanding at Scalecited by 56
  3. 2024Towards Privacy-Aware Sign Language Translation at Scalecited by 44
  4. 2024T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Textcited by 30
  5. 2025Lost in Translation, Found in Context: Sign Language Translation with Contextual Cuescited by 26
  6. 2024C2RL: Content and Context Representation Learning for Gloss-free Sign Language Translation and Retrievalcited by 24
  7. 2024SHuBERT: Self-Supervised Sign Language Representation Learning via Multi-Stream Cluster Predictioncited by 22
  8. 2024SignCLIP: Connecting Text and Sign Language by Contrastive Learningcited by 20
  9. 2024Casablanca: Data and Models for Multidialectal Arabic Speech Recognitioncited by 20
  10. 2024SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scalecited by 19
  11. 2025SignRep: Enhancing Self-Supervised Sign Representationscited by 15
  12. 2025Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translationcited by 12
38 more
  1. 2025Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translationcited by 12
  2. 2024FLEURS-ASL: Including American Sign Language in Massively Multilingual Multitask Evaluationcited by 10
  3. 2024An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMscited by 9
  4. 2026Gloss-Free Sign Language Translation: An Unbiased Evaluation of Progress in the Fieldcited by 9
  5. 2024Scaling Sign Language Translationcited by 8
  6. 2024ASL STEM Wiki: Dataset and Benchmark for Interpreting STEM Articlescited by 7
  7. 2024iSign: A Benchmark for Indian Sign Language Processingcited by 6
  8. 2024EvSign: Sign Language Recognition and Translation with Streaming Eventscited by 6
  9. 2024FSboard: Over 3 million characters of ASL fingerspelling collected via smartphonescited by 6
  10. 2025Isharah: A Large-Scale Multi-Scene Dataset for Continuous Sign Language Recognitioncited by 6
  11. 2025Meaningful Pose-Based Sign Language Evaluationcited by 6
  12. 2025Sign Language Translation with Sentence Embedding Supervisioncited by 6
  13. 2025Lost in Translation, Found in Embeddings: Sign Language Translation and Alignmentcited by 6
  14. 2024A Spatio-Temporal Representation Learning as an Alternative to Traditional Glosses in Sign Language Translation and Productioncited by 5
  15. 2024Reconsidering Sentence-Level Sign Language Translationcited by 4
  16. 2025EmoSign: A Multimodal Dataset for Understanding Emotions in American Sign Languagecited by 4
  17. 20242M-BELEBELE: Highly Multilingual Speech and American Sign Language Comprehension Datasetcited by 3
  18. 2025SONAR-SLT: Multilingual Sign Language Translation via Language-Agnostic Sentence Embedding Supervisioncited by 3
  19. 2024A Chinese Continuous Sign Language Dataset Based on Complex Environmentscited by 2
  20. 2025Exploring Pose-based Sign Language Translation: Ablation Studies and Attention Insightscited by 2
  21. 2025Generative Modeling of Shape-Dependent Self-Contact Human Posescited by 2
  22. 2025RVLF: A Reinforcing Vision-Language Framework for Gloss-Free Sign Language Translationcited by 2
  23. 2025Segment, Embed, and Align: A Universal Recipe for Aligning Subtitles to Signingcited by 2
  24. 2026M3T: Discrete Multi-Modal Motion Tokens for Sign Language Productioncited by 2
  25. 2026Sign Language Question Answering: A New Task, Benchmark, and Baseline for Sign Language Understandingcited by 2
  26. 2024AirLetters: An Open Video Dataset of Characters Drawn in the Aircited by 1
  27. 2024The American Sign Language Knowledge Graph: Infusing ASL Models with Linguistic Knowledgecited by 1
  28. 2025Towards Inclusive Communication: A Unified Framework for Generating Spoken Language from Sign, Lip, and Audiocited by 1
  29. 2025SignBind-LLM: Multi-Stage Modality Fusion for Sign Language Translationcited by 1
  30. 2025MultimodalHugs: Enabling Sign Language Processing in Hugging Facecited by 1
  31. 2025SignMouth: Leveraging Mouthing Cues for Sign Language Translation by Multimodal Contrastive Fusioncited by 1
  32. 2025Saudi Sign Language Translation Using T5cited by 1
  33. 2026SignAgent: Agentic LLMs for Linguistically-Grounded Sign Language Annotation and Dataset Curationcited by 1
  34. 2026Think in Latent Thoughts: A New Paradigm for Gloss-Free Sign Language Translationcited by 1
  35. 2026SignDATA: Data Pipeline for Sign Language Translationcited by 1
  36. 2026SIGNET: Motion-Level Knowledge Transfer for Cross-Language Sign Language Translationcited by 1
  37. 2025Seeing, Signing, and Saying: A Vision-Language Model-Assisted Pipeline for Sign Language Data Acquisition and Curation from Social Mediacited by 0
  38. 2026Beyond a Single Reference: Training and Evaluation with Paraphrases in Sign Language Translationcited by 0

50 most cited of 75 All 75 (JSON)