{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T07:19:13Z","timestamp":1783063153925,"version":"3.54.6"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017548","name":"National Defense Science and Technology Innovation Fund of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["19-H863-00-KX-001-002-01"],"award-info":[{"award-number":["19-H863-00-KX-001-002-01"]}],"id":[{"id":"10.13039\/501100017548","id-type":"DOI","asserted-by":"publisher"}]},{"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":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114189","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T06:31:10Z","timestamp":1781245870000},"page":"114189","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["SSL-SSAW: Self-supervised Learning with Sigmoid Self-attention Weighting for question-based Sign Language Translation"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5003-1900","authenticated-orcid":false,"given":"Zekang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fanhua","family":"Shang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianyu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jichao","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4518-2154","authenticated-orcid":false,"given":"Liqing","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114189_b1","doi-asserted-by":"crossref","unstructured":"N.C. Camgoz, S. Hadfield, O. Koller, H. Ney, R. Bowden, Neural sign language translation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7784\u20137793.","DOI":"10.1109\/CVPR.2018.00812"},{"key":"10.1016\/j.patcog.2026.114189_b2","unstructured":"N.C. Camgoz, O. Koller, S. Hadfield, R. Bowden, Sign language transformers: Joint end-to-end sign language recognition and translation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10023\u201310033."},{"key":"10.1016\/j.patcog.2026.114189_b3","doi-asserted-by":"crossref","unstructured":"B. Zhou, Z. Chen, A. Clap\u00e9s, J. Wan, Y. Liang, S. Escalera, Z. Lei, D. Zhang, Gloss-free sign language translation: Improving from visual-language pretraining, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 20871\u201320881.","DOI":"10.1109\/ICCV51070.2023.01908"},{"key":"10.1016\/j.patcog.2026.114189_b4","doi-asserted-by":"crossref","unstructured":"A. Yin, T. Zhong, L. Tang, W. Jin, T. Jin, Z. Zhao, Gloss attention for gloss-free sign language translation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 2551\u20132562.","DOI":"10.1109\/CVPR52729.2023.00251"},{"key":"10.1016\/j.patcog.2026.114189_b5","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2024.3419089","article-title":"Overcoming modality bias in question-driven sign language video translation","author":"Gao","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114189_b6","series-title":"Proceedings of International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.114189_b7","article-title":"Vlab: Enhancing video language pre-training by feature adapting and blending","author":"He","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114189_b8","doi-asserted-by":"crossref","unstructured":"B. He, H. Li, Y.K. Jang, M. Jia, X. Cao, A. Shah, A. Shrivastava, S.-N. Lim, Ma-lmm: Memory-augmented large multimodal model for long-term video understanding, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 13504\u201313514.","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"10.1016\/j.patcog.2026.114189_b9","doi-asserted-by":"crossref","unstructured":"D. Qiao, Y. Gao, Z. Yang, D. Yang, Z. Wu, P. Lu, M. Qiu, J. Li, M. Zhang, Decoder-only LLMs can be masked auto-encoders, in: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2025, pp. 713\u2013723.","DOI":"10.18653\/v1\/2025.acl-short.57"},{"key":"10.1016\/j.patcog.2026.114189_b10","doi-asserted-by":"crossref","unstructured":"A. Graves, S. Fern\u00e1ndez, F. Gomez, J. Schmidhuber, Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks, in: Proceedings of the 23rd International Conference on Machine Learning, 2006, pp. 369\u2013376.","DOI":"10.1145\/1143844.1143891"},{"key":"10.1016\/j.patcog.2026.114189_b11","doi-asserted-by":"crossref","first-page":"7728","DOI":"10.1109\/TIP.2025.3633145","article-title":"Perception-oriented bidirectional attention network for image super-resolution quality assessment","volume":"34","author":"Li","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114189_b12","doi-asserted-by":"crossref","unstructured":"X. Li, W. Nie, Y. Zhang, R. Hu, K. Li, X. Zheng, L. Cao, Distilling spatially-heterogeneous distortion perception for blind image quality assessment, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 2344\u20132354.","DOI":"10.1109\/CVPR52734.2025.00224"},{"issue":"10","key":"10.1016\/j.patcog.2026.114189_b13","doi-asserted-by":"crossref","first-page":"10299","DOI":"10.1109\/TCSVT.2024.3405789","article-title":"Blind image quality assessment via adaptive graph attention","volume":"34","author":"Wang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114189_b14","series-title":"2024 IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"Deep bi-directional attention network for image super-resolution quality assessment","author":"Li","year":"2024"},{"key":"10.1016\/j.patcog.2026.114189_b15","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1109\/TMM.2021.3059098","article-title":"Spatial-temporal multi-cue network for sign language recognition and translation","volume":"24","author":"Zhou","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114189_b16","series-title":"SLTUNET: A simple unified model for sign language translation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114189_b17","doi-asserted-by":"crossref","unstructured":"H. Yao, W. Zhou, H. Feng, H. Hu, H. Zhou, H. Li, Sign language translation with iterative prototype, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 15592\u201315601.","DOI":"10.1109\/ICCV51070.2023.01429"},{"issue":"9","key":"10.1016\/j.patcog.2026.114189_b18","doi-asserted-by":"crossref","first-page":"11221","DOI":"10.1109\/TPAMI.2023.3269220","article-title":"Signbert+: Hand-model-aware self-supervised pre-training for sign language understanding","volume":"45","author":"Hu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114189_b19","doi-asserted-by":"crossref","unstructured":"Y. Chen, F. Wei, X. Sun, Z. Wu, S. Lin, A simple multi-modality transfer learning baseline for sign language translation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5120\u20135130.","DOI":"10.1109\/CVPR52688.2022.00506"},{"key":"10.1016\/j.patcog.2026.114189_b20","doi-asserted-by":"crossref","first-page":"17043","DOI":"10.52202\/068431-1240","article-title":"Two-stream network for sign language recognition and translation","volume":"35","author":"Chen","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114189_b21","series-title":"Effective approaches to attention-based neural machine translation","author":"Luong","year":"2015"},{"key":"10.1016\/j.patcog.2026.114189_b22","first-page":"12034","article-title":"Tspnet: Hierarchical feature learning via temporal semantic pyramid for sign language translation","volume":"33","author":"Li","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114189_b23","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114189_b24","doi-asserted-by":"crossref","unstructured":"J. Gong, L.G. Foo, Y. He, H. Rahmani, J. Liu, Llms are good sign language translators, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 18362\u201318372.","DOI":"10.1109\/CVPR52733.2024.01738"},{"key":"10.1016\/j.patcog.2026.114189_b25","series-title":"Factorized learning assisted with large language model for gloss-free sign language translation","author":"Chen","year":"2024"},{"key":"10.1016\/j.patcog.2026.114189_b26","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.patcog.2026.114189_b27","doi-asserted-by":"crossref","unstructured":"H. Zhou, W. Zhou, W. Qi, J. Pu, H. Li, Improving sign language translation with monolingual data by sign back-translation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 1316\u20131325.","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"10.1016\/j.patcog.2026.114189_b28","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778."},{"key":"10.1016\/j.patcog.2026.114189_b29","doi-asserted-by":"crossref","first-page":"726","DOI":"10.1162\/tacl_a_00343","article-title":"Multilingual denoising pre-training for neural machine translation","volume":"8","author":"Liu","year":"2020","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.patcog.2026.114189_b30","doi-asserted-by":"crossref","unstructured":"K. Papineni, S. Roukos, T. Ward, W.-J. Zhu, Bleu: a method for automatic evaluation of machine translation, in: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 2002, pp. 311\u2013318.","DOI":"10.3115\/1073083.1073135"},{"key":"10.1016\/j.patcog.2026.114189_b31","unstructured":"C.-Y. Lin, Rouge: A package for automatic evaluation of summaries, in: Proceedings of Text Summarization Branches Out, 2004, pp. 74\u201381."},{"key":"10.1016\/j.patcog.2026.114189_b32","series-title":"Sign2GPT: Leveraging large language models for gloss-free sign language translation","author":"Wong","year":"2024"},{"key":"10.1016\/j.patcog.2026.114189_b33","series-title":"Llava-slt: Visual language tuning for sign language translation","author":"Liang","year":"2024"},{"key":"10.1016\/j.patcog.2026.114189_b34","doi-asserted-by":"crossref","unstructured":"S. Gan, Y. Yin, Z. Jiang, L. Xie, S. Lu, H. Wen, MixSignGraph: A Sign Sequence is Worth Mixed Graphs of Nodes, in: The Thirty-Ninth Annual Conference on Neural Information Processing Systems, 2025.","DOI":"10.1109\/CVPR52733.2024.01279"},{"key":"10.1016\/j.patcog.2026.114189_b35","series-title":"Uni-sign: Toward unified sign language understanding at scale","author":"Li","year":"2025"},{"key":"10.1016\/j.patcog.2026.114189_b36","first-page":"854","article-title":"Self-emphasizing network for continuous sign language recognition","volume":"vol. 37","author":"Hu","year":"2023"},{"key":"10.1016\/j.patcog.2026.114189_b37","series-title":"European Conference on Computer Vision","first-page":"511","article-title":"Temporal lift pooling for continuous sign language recognition","author":"Hu","year":"2022"},{"key":"10.1016\/j.patcog.2026.114189_b38","unstructured":"T.M. Le, V. Le, S. Venkatesh, T. Tran, Hierarchical conditional relation networks for video question answering, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9972\u20139981."},{"key":"10.1016\/j.patcog.2026.114189_b39","doi-asserted-by":"crossref","unstructured":"Y. Yin, F. Meng, J. Su, C. Zhou, Z. Yang, J. Zhou, J. Luo, A novel graph-based multi-modal fusion encoder for neural machine translation, in: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, pp. 3025\u20133035.","DOI":"10.18653\/v1\/2020.acl-main.273"},{"key":"10.1016\/j.patcog.2026.114189_b40","doi-asserted-by":"crossref","unstructured":"C. Li, H. Xu, J. Tian, W. Wang, M. Yan, B. Bi, J. Ye, H. Chen, G. Xu, Z. Cao, et al., mplug: Effective and efficient vision-language learning by cross-modal skip-connections, in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, pp. 7241\u20137259.","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"10.1016\/j.patcog.2026.114189_b41","first-page":"37","article-title":"Long short-term memory","author":"Graves","year":"2012","journal-title":"Supervised Seq. Label. Recurr. Neural Networks"},{"key":"10.1016\/j.patcog.2026.114189_b42","article-title":"Character-level convolutional networks for text classification","volume":"28","author":"Zhang","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114189_b43","doi-asserted-by":"crossref","unstructured":"X. Zhang, X. Zhou, M. Lin, J. Sun, Shufflenet: An extremely efficient convolutional neural network for mobile devices, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6848\u20136856.","DOI":"10.1109\/CVPR.2018.00716"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326011544?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326011544?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:47:55Z","timestamp":1783061275000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326011544"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":43,"alternative-id":["S0031320326011544"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114189","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SSL-SSAW: Self-supervised Learning with Sigmoid Self-attention Weighting for question-based Sign Language Translation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114189","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114189"}}