{"url":"/sota/sign-language-recognition-on-rwth-phoenix-1","task":{"name":"Sign Language Recognition","url":"/task/sign-language-recognition","note":null},"dataset":{"name":"RWTH-PHOENIX-Weather 2014 T","url":"/dataset/rwth-phoenix-weather-2014-t"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Sign Language Recognition** is a computer vision and natural language processing task that involves automatically recognizing and translating sign language gestures into written or spoken language. The goal of sign language recognition is to develop algorithms that can understand and interpret sign language, enabling people who use sign language as their primary mode of communication to communicate more easily with non-signers.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Word-level Deep Sign Language Recognition from Video:\r\nA New Large-scale Dataset and Methods Comparison](https://arxiv.org/pdf/1910.11006v1.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Word Error Rate (WER)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Word Error Rate (WER)":"lower"}},"counts":{"rows":15,"rows_with_code":10,"rows_with_paper_page":15,"rows_dated":14,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SlowFastSign","metrics":{"Word Error Rate (WER)":"18.7"},"uses_additional_data":false,"paper_date":"2023-09-21","paper":"/paper/slowfast-network-for-continuous-sign-language","paper_url":"https://arxiv.org/abs/2309.12304v1","paper_title":"SlowFast Network for Continuous Sign Language Recognition","code":"https://github.com/kaistmm/SlowFastSign","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"TwoStream-SLR","metrics":{"Word Error Rate (WER)":"19.3"},"uses_additional_data":false,"paper_date":"2022-11-02","paper":"/paper/two-stream-network-for-sign-language","paper_url":"https://arxiv.org/abs/2211.01367v2","paper_title":"Two-Stream Network for Sign Language Recognition and Translation","code":"https://github.com/FangyunWei/SLRT","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"TCNet","metrics":{"Word Error Rate (WER)":"19.4"},"uses_additional_data":false,"paper_date":"2024-03-18","paper":"/paper/tcnet-continuous-sign-language-recognition","paper_url":"https://arxiv.org/abs/2403.11818v1","paper_title":"TCNet: Continuous Sign Language Recognition from Trajectories and Correlated Regions","code":"https://github.com/hotfinda/tcnet","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":4,"model":"SLA-LoRA","metrics":{"Word Error Rate (WER)":"19.4"},"uses_additional_data":false,"paper_date":"2025-04-02","paper":"/paper/clip-sla-parameter-efficient-clip-adaptation","paper_url":"https://arxiv.org/abs/2504.01666v1","paper_title":"CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language Recognition","code":"https://github.com/snalyami/CLIP-SLA","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Swin-MSTP","metrics":{"Word Error Rate (WER)":"19.7"},"uses_additional_data":false,"paper_date":"2025-02-07","paper":"/paper/swin-mstp-swin-transformer-with-multi-scale","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0925231224017867","paper_title":"Swin-MSTP: Swin transformer with multi-scale temporal perception for continuous sign language recognition","code":"https://github.com/snalyami/Swin-MSTP","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"SignBERT+","metrics":{"Word Error Rate (WER)":"19.9"},"uses_additional_data":false,"paper_date":"2023-05-08","paper":"/paper/signbert-hand-model-aware-self-supervised-pre","paper_url":"https://arxiv.org/abs/2305.04868v1","paper_title":"SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"C2SLR","metrics":{"Word Error Rate (WER)":"20.4"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/c2slr-consistency-enhanced-continuous-sign","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Zuo_C2SLR_Consistency-Enhanced_Continuous_Sign_Language_Recognition_CVPR_2022_paper.html","paper_title":"C2SLR: Consistency-Enhanced Continuous Sign Language Recognition","code":"https://github.com/2000zrl/lcsa_c2slr_srm","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"MSKA-SLR","metrics":{"Word Error Rate (WER)":"20.5"},"uses_additional_data":false,"paper_date":"2024-05-09","paper":"/paper/multi-stream-keypoint-attention-network-for","paper_url":"https://arxiv.org/abs/2405.05672v1","paper_title":"Multi-Stream Keypoint Attention Network for Sign Language Recognition and Translation","code":"https://github.com/sutwangyan/MSKA","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"WRNN + LET","metrics":{"Word Error Rate (WER)":"20.73"},"uses_additional_data":false,"paper_date":"2023-08-22","paper":"/paper/multimodal-locally-enhanced-transformer-for","paper_url":"https://www.isca-archive.org/interspeech_2023/papadimitriou23_interspeech.html","paper_title":"Multimodal Locally Enhanced Transformer for Continuous Sign Language Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"STMC","metrics":{"Word Error Rate (WER)":"21.0"},"uses_additional_data":false,"paper_date":"2020-02-08","paper":"/paper/spatial-temporal-multi-cue-network-for","paper_url":"https://arxiv.org/abs/2002.03187v1","paper_title":"Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"SMKD","metrics":{"Word Error Rate (WER)":"22.4"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/self-mutual-distillation-learning-for","paper_url":"http://openaccess.thecvf.com//content/ICCV2021/html/Hao_Self-Mutual_Distillation_Learning_for_Continuous_Sign_Language_Recognition_ICCV_2021_paper.html","paper_title":"Self-Mutual Distillation Learning for Continuous Sign Language Recognition","code":"https://github.com/ycmin95/VAC_CSLR","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"MMTLB","metrics":{"Word Error Rate (WER)":"22.45"},"uses_additional_data":false,"paper_date":"2022-03-08","paper":"/paper/a-simple-multi-modality-transfer-learning","paper_url":"https://arxiv.org/abs/2203.04287v2","paper_title":"A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation","code":"https://github.com/FangyunWei/SLRT","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":9}},{"rank_in_archive_order":13,"model":"SignBT","metrics":{"Word Error Rate (WER)":"23.9"},"uses_additional_data":false,"paper_date":"2021-05-26","paper":"/paper/improving-sign-language-translation-with","paper_url":"https://arxiv.org/abs/2105.12397v1","paper_title":"Improving Sign Language Translation with Monolingual Data by Sign Back-Translation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"CrossModal","metrics":{"Word Error Rate (WER)":"24.3"},"uses_additional_data":false,"paper_date":"2020-05-11","paper":"/paper/continuous-sign-language-recognition-through","paper_url":"https://ieeexplore.ieee.org/document/9090828","paper_title":"Continuous Sign Language Recognition Through Cross-Modal Alignment of Video and Text Embeddings in a Joint-Latent Space","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"Stochastic CSLR","metrics":{"Word Error Rate (WER)":"26.1"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/stochastic-fine-grained-labeling-of-multi","paper_url":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/2527_ECCV_2020_paper.php","paper_title":"Stochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition","code":"https://github.com/zheniu/stochastic-cslr","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":11,"n_unverified":6,"n_samples":17,"n_pointer_only_licence":16,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":11,"n_unverified":6,"n_samples":17,"n_pointer_only_licence":16,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}