{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T19:24:44Z","timestamp":1776281084620,"version":"3.50.1"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072334"],"award-info":[{"award-number":["62072334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1016\/j.patcog.2024.111246","type":"journal-article","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:41:54Z","timestamp":1733445714000},"page":"111246","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["A large-scale combinatorial benchmark for sign language recognition"],"prefix":"10.1016","volume":"161","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4518-2154","authenticated-orcid":false,"given":"Liqing","family":"Gao","sequence":"first","affiliation":[]},{"given":"Liang","family":"Wan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9974-4920","authenticated-orcid":false,"given":"Lianyu","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Ruize","family":"Han","sequence":"additional","affiliation":[]},{"given":"Zekang","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6414-4642","authenticated-orcid":false,"given":"Peng","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Fanhua","family":"Shang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2024.111246_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109233","article-title":"Multi-scale local-temporal similarity fusion for continuous sign language recognition","volume":"136","author":"Xie","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.111246_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109901","article-title":"Mask-guided multiscale feature aggregation network for hand gesture recognition","volume":"145","author":"Liang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.111246_b3","series-title":"ACM MM","article-title":"Adabrowse: Adaptive video browser for efficient continuous sign language recognition","author":"Hu","year":"2023"},{"key":"10.1016\/j.patcog.2024.111246_b4","article-title":"Scalable frame resolution for efficient continuous sign language recognition","author":"Hu","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.111246_b5","series-title":"Findings of the 2019 conference on machine translation (WMT19)","author":"Barrault","year":"2019"},{"key":"10.1016\/j.patcog.2024.111246_b6","series-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019"},{"key":"10.1016\/j.patcog.2024.111246_b7","series-title":"CVPR","article-title":"Improving sign language translation with monolingual data by sign back-translation","author":"Zhou","year":"2021"},{"key":"10.1016\/j.patcog.2024.111246_b8","series-title":"ICLR","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2017"},{"key":"10.1016\/j.patcog.2024.111246_b9","series-title":"LREC","article-title":"RWTH-PHOENIX-weather: A large vocabulary sign language recognition and translation corpus","author":"Forster","year":"2012"},{"key":"10.1016\/j.patcog.2024.111246_b10","series-title":"CVPR","article-title":"Neural sign language translation","author":"Camgoz","year":"2018"},{"key":"10.1016\/j.patcog.2024.111246_b11","first-page":"2205","article-title":"Sign language recognition using sub-units","volume":"13","author":"Cooper","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2024.111246_b12","unstructured":"X. Chai, G. Li, Y. Lin, Z. Xu, Y. Tang, X. Chen, M. Zhou, Sign language recognition and translation with kinect, in: IEEE Conf. on AFGR, 2013."},{"key":"10.1016\/j.patcog.2024.111246_b13","series-title":"ECCV","article-title":"Chalearn looking at people challenge 2014: Dataset and results","author":"Escalera","year":"2014"},{"key":"10.1016\/j.patcog.2024.111246_b14","series-title":"CACIC","article-title":"LSA64: an argentinian sign language dataset","author":"Ronchetti","year":"2016"},{"key":"10.1016\/j.patcog.2024.111246_b15","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.neucom.2016.08.132","article-title":"A multimodal framework for sensor based sign language recognition","volume":"259","author":"Kumar","year":"2017","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2024.111246_b16","series-title":"WACV","article-title":"Word-level deep sign language recognition from video: A new large-scale dataset and methods comparison","author":"Li","year":"2020"},{"key":"10.1016\/j.patcog.2024.111246_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.113336","article-title":"Hand sign language recognition using multi-view hand skeleton","volume":"150","author":"Rastgoo","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2024.111246_b18","series-title":"AAAI","article-title":"Video-based sign language recognition without temporal segmentation","author":"Huang","year":"2018"},{"key":"10.1016\/j.patcog.2024.111246_b19","series-title":"CVPR","article-title":"How2sign: a large-scale multimodal dataset for continuous american sign language","author":"Duarte","year":"2021"},{"key":"10.1016\/j.patcog.2024.111246_b20","series-title":"ICML","article-title":"Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks","author":"Graves","year":"2006"},{"key":"10.1016\/j.patcog.2024.111246_b21","series-title":"CVPR","first-page":"2529","article-title":"Continuous sign language recognition with correlation network","author":"Hu","year":"2023"},{"key":"10.1016\/j.patcog.2024.111246_b22","series-title":"AAAI","article-title":"Tcnet: Continuous sign language recognition from trajectories and correlated regions","author":"Lu","year":"2024"},{"key":"10.1016\/j.patcog.2024.111246_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108044","article-title":"Normalized edge convolutional networks for skeleton-based hand gesture recognition","volume":"118","author":"Guo","year":"2021","journal-title":"Pattern Recognit."},{"issue":"4","key":"10.1016\/j.patcog.2024.111246_b24","doi-asserted-by":"crossref","first-page":"1406","DOI":"10.3390\/s22041406","article-title":"American sign language words recognition of skeletal videos using processed video driven multi-stacked deep LSTM","volume":"22","author":"Abdullahi","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.patcog.2024.111246_b25","doi-asserted-by":"crossref","first-page":"15911","DOI":"10.1109\/ACCESS.2022.3148132","article-title":"American sign language words recognition using spatio-temporal prosodic and angle features: A sequential learning approach","volume":"10","author":"Abdullahi","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.patcog.2024.111246_b26","series-title":"CVPR","article-title":"C2SLR: Consistency-enhanced continuous sign language recognition","author":"Zuo","year":"2022"},{"key":"10.1016\/j.patcog.2024.111246_b27","series-title":"CVPR","article-title":"Distilling cross-temporal contexts for continuous sign language recognition","author":"Guo","year":"2023"},{"key":"10.1016\/j.patcog.2024.111246_b28","article-title":"Gloss prior guided visual feature learning for continuous sign language recognition","author":"Guo","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2024.111246_b29","series-title":"CVPR","article-title":"Cvt-slr: Contrastive visual-textual transformation for sign language recognition with variational alignment","author":"Zheng","year":"2023"},{"key":"10.1016\/j.patcog.2024.111246_b30","series-title":"AAAI","article-title":"BEST: BERT pre-training for sign language recognition with coupling tokenization","author":"Zhao","year":"2023"},{"key":"10.1016\/j.patcog.2024.111246_b31","article-title":"Spatial temporal aggregation for efficient continuous sign language recognition","author":"Hu","year":"2024","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.patcog.2024.111246_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123258","article-title":"Spatial\u2013temporal feature-based end-to-end Fourier network for 3D sign language recognition","volume":"248","author":"Abdullahi","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2024.111246_b33","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1162\/tacl_a_00314","article-title":"Crosswoz: A large-scale chinese cross-domain task-oriented dialogue dataset","volume":"8","author":"Zhu","year":"2020","journal-title":"TACL"},{"key":"10.1016\/j.patcog.2024.111246_b34","series-title":"ICCV","article-title":"Visual alignment constraint for continuous sign language recognition","author":"Min","year":"2021"},{"key":"10.1016\/j.patcog.2024.111246_b35","series-title":"CVPR","article-title":"Depth-aware generative adversarial network for talking head video generation","author":"Hong","year":"2022"},{"key":"10.1016\/j.patcog.2024.111246_b36","series-title":"CVPR","article-title":"Sign language transformers: Joint end-to-end sign language recognition and translation","author":"Camgoz","year":"2020"},{"key":"10.1016\/j.patcog.2024.111246_b37","series-title":"AAAI","article-title":"Self-emphasizing network for continuous sign language recognition","author":"Hu","year":"2023"},{"key":"10.1016\/j.patcog.2024.111246_b38","series-title":"ICCV","article-title":"Self-mutual distillation learning for continuous sign language recognition","author":"Hao","year":"2021"},{"key":"10.1016\/j.patcog.2024.111246_b39","series-title":"ECCV","article-title":"Temporal lift pooling for continuous sign language recognition","author":"Hu","year":"2022"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032400997X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032400997X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T12:06:09Z","timestamp":1740053169000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S003132032400997X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":39,"alternative-id":["S003132032400997X"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2024.111246","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2025,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A large-scale combinatorial benchmark for sign language recognition","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2024.111246","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"111246"}}