{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:28:13Z","timestamp":1777656493566,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100017623","name":"Zhejiang Provincial Outstanding Youth Science Foundation","doi-asserted-by":"publisher","award":["LR19F020006"],"award-info":[{"award-number":["LR19F020006"]}],"id":[{"id":"10.13039\/501100017623","id-type":"DOI","asserted-by":"publisher"}]},{"name":"X Lab, the Second Academy of CASIC, Beijing, 100854, China"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836002,62072397,62077041"],"award-info":[{"award-number":["61836002,62072397,62077041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFC0832505"],"award-info":[{"award-number":["2020YFC0832505"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3547957","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:46Z","timestamp":1665416566000},"page":"5486-5495","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["DualSign: Semi-Supervised Sign Language Production with Balanced Multi-Modal Multi-Task Dual Transformation"],"prefix":"10.1145","author":[{"given":"Wencan","family":"Huang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"given":"Jinzheng","family":"He","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"given":"Mingmin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Unsupervised Neural Machine Translation. In International Conference on Learning Representations.","author":"Artetxe Mikel","year":"2018","unstructured":"Mikel Artetxe , Gorka Labaka , Eneko Agirre , and Kyunghyun Cho . 2018 . Unsupervised Neural Machine Translation. In International Conference on Learning Representations. Mikel Artetxe, Gorka Labaka, Eneko Agirre, and Kyunghyun Cho. 2018. Unsupervised Neural Machine Translation. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_2_1","volume-title":"3rd International Conference on Learning Representations, ICLR","author":"Bahdanau Dzmitry","year":"2015","unstructured":"Dzmitry Bahdanau , Kyung Hyun Cho , and Yoshua Bengio . 2015 . Neural machine translation by jointly learning to align and translate . In 3rd International Conference on Learning Representations, ICLR 2015. Dzmitry Bahdanau, Kyung Hyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations, ICLR 2015."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01135"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1105"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1175"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00812"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413623"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/638249.638287"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3352587"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-5102"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-007-0102-z"},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLRWorkshop and Conference Proceedings, 249--256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio . 2010 . Understanding the difficulty of training deep feedforward neural networks . In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLRWorkshop and Conference Proceedings, 249--256 . Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLRWorkshop and Conference Proceedings, 249--256."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_2_2_17_1","volume-title":"Dual learning for machine translation. Advances in neural information processing systems 29","author":"He Di","year":"2016","unstructured":"Di He , Yingce Xia , Tao Qin , Liwei Wang , Nenghai Yu , Tie-Yan Liu , and Wei-Ying Ma. 2016. Dual learning for machine translation. Advances in neural information processing systems 29 ( 2016 ). Di He, Yingce Xia, Tao Qin, Liwei Wang, Nenghai Yu, Tie-Yan Liu, and Wei-Ying Ma. 2016. Dual learning for machine translation. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_2_18_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton , Oriol Vinyals , and Jeff Dean . 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 ( 2015 ). Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_2_19_1","volume-title":"Towards Fast and High-Quality Sign Language Production. In MM '21: ACM Multimedia Conference","author":"Huang Wencan","year":"2021","unstructured":"Wencan Huang , Wenwen Pan , Zhou Zhao , and Qi Tian . 2021 . Towards Fast and High-Quality Sign Language Production. In MM '21: ACM Multimedia Conference , Virtual Event, China, October 20 - 24 , 2021. ACM, 3172--3181. Wencan Huang, Wenwen Pan, Zhou Zhao, and Qi Tian. 2021. Towards Fast and High-Quality Sign Language Production. In MM '21: ACM Multimedia Conference, Virtual Event, China, October 20 - 24, 2021. ACM, 3172--3181."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/INISTA.2019.8778347"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"e_1_3_2_2_22_1","volume-title":"Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings.","author":"Diederik","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015 . Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings."},{"key":"e_1_3_2_2_23_1","unstructured":"Dimitris Kouremenos Klimis S Ntalianis Giorgos Siolas and Andreas Stafylopatis. 2018. Statistical Machine Translation for Greek to Greek Sign Language Using Parallel Corpora Produced via Rule-Based Machine Translation.. In CIMA@ ICTAI. 28--42.  Dimitris Kouremenos Klimis S Ntalianis Giorgos Siolas and Andreas Stafylopatis. 2018. Statistical Machine Translation for Greek to Greek Sign Language Using Parallel Corpora Produced via Rule-Based Machine Translation.. In CIMA@ ICTAI. 28--42."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00902"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413715"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350986"},{"key":"e_1_3_2_2_28_1","volume-title":"Proc. Interspeech","author":"Nakatani Tomohiro","year":"2019","unstructured":"Tomohiro Nakatani . 2019 . Improving transformer-based end-to-end speech recognition with connectionist temporal classification and language model integration . In Proc. Interspeech 2019. Tomohiro Nakatani. 2019. Improving transformer-based end-to-end speech recognition with connectionist temporal classification and language model integration. In Proc. Interspeech 2019."},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni , Salim Roukos , Todd Ward , and Wei-Jing Zhu . 2002 . Bleu: a method for automatic evaluation of machine translation . In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318 . Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413931"},{"key":"e_1_3_2_2_31_1","volume-title":"International Conference on Machine Learning. PMLR, 5410--5419","author":"Ren Yi","year":"2019","unstructured":"Yi Ren , Xu Tan , Tao Qin , Sheng Zhao , Zhou Zhao , and Tie-Yan Liu . 2019 . Almost unsupervised text to speech and automatic speech recognition . In International Conference on Machine Learning. PMLR, 5410--5419 . Yi Ren, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2019. Almost unsupervised text to speech and automatic speech recognition. In International Conference on Machine Learning. PMLR, 5410--5419."},{"key":"e_1_3_2_2_32_1","volume-title":"Adversarial Training for Multi-Channel Sign Language Production. In 31st British Machine Vision Conference 2020, BMVC 2020","author":"Saunders Ben","year":"2020","unstructured":"Ben Saunders , Richard Bowden , and Necati Cihan Camg\u00f6z . 2020 . Adversarial Training for Multi-Channel Sign Language Production. In 31st British Machine Vision Conference 2020, BMVC 2020 , Virtual Event, UK, September 7--10 , 2020. BMVA Press. Ben Saunders, Richard Bowden, and Necati Cihan Camg\u00f6z. 2020. Adversarial Training for Multi-Channel Sign Language Production. In 31st British Machine Vision Conference 2020, BMVC 2020, Virtual Event, UK, September 7--10, 2020. BMVA Press."},{"key":"e_1_3_2_2_33_1","volume-title":"Necati Cihan Camgoz, and Richard Bowden","author":"Saunders Ben","year":"2020","unstructured":"Ben Saunders , Necati Cihan Camgoz, and Richard Bowden . 2020 . Everybody sign now: Translating spoken language to photo realistic sign language video. arXiv preprint arXiv:2011.09846 (2020). Ben Saunders, Necati Cihan Camgoz, and Richard Bowden. 2020. Everybody sign now: Translating spoken language to photo realistic sign language video. arXiv preprint arXiv:2011.09846 (2020)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_40"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01457-9"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00193"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"e_1_3_2_2_38_1","volume-title":"Non-attentive tacotron: Robust and controllable neural TTS synthesis including unsupervised duration modeling. arXiv preprint arXiv:2010.04301","author":"Shen Jonathan","year":"2020","unstructured":"Jonathan Shen , Ye Jia , Mike Chrzanowski , Yu Zhang , Isaac Elias , Heiga Zen , and Yonghui Wu. 2020. Non-attentive tacotron: Robust and controllable neural TTS synthesis including unsupervised duration modeling. arXiv preprint arXiv:2010.04301 ( 2020 ). Jonathan Shen, Ye Jia, Mike Chrzanowski, Yu Zhang, Isaac Elias, Heiga Zen, and Yonghui Wu. 2020. Non-attentive tacotron: Robust and controllable neural TTS synthesis including unsupervised duration modeling. arXiv preprint arXiv:2010.04301 (2020)."},{"key":"e_1_3_2_2_39_1","volume-title":"Proceedings of the 29th British Machine Vision Conference (BMVC","author":"Stoll Stephanie","year":"2018","unstructured":"Stephanie Stoll , Necati Cihan Camg\u00f6z , Simon Hadfield , and Richard Bowden . 2018 . Sign language production using neural machine translation and generative adversarial networks . In Proceedings of the 29th British Machine Vision Conference (BMVC 2018). University of Surrey. Stephanie Stoll, Necati Cihan Camg\u00f6z, Simon Hadfield, and Richard Bowden. 2018. Sign language production using neural machine translation and generative adversarial networks. In Proceedings of the 29th British Machine Vision Conference (BMVC 2018). University of Surrey."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01281-2"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_2_42_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017. Attention is all you need. Advances in neural information processing systems 30 ( 2017 ). Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_2_43_1","volume-title":"International conference on machine learning. PMLR, 3789--3798","author":"Xia Yingce","year":"2017","unstructured":"Yingce Xia , Tao Qin , Wei Chen , Jiang Bian , Nenghai Yu , and Tie-Yan Liu . 2017 . Dual supervised learning . In International conference on machine learning. PMLR, 3789--3798 . Yingce Xia, Tao Qin, Wei Chen, Jiang Bian, Nenghai Yu, and Tie-Yan Liu. 2017. Dual supervised learning. In International conference on machine learning. PMLR, 3789--3798."},{"key":"e_1_3_2_2_44_1","volume-title":"Skeleton-based Chinese sign language recognition and generation for bidirectional communication between deaf and hearing people. Neural networks 125","author":"Xiao Qinkun","year":"2020","unstructured":"Qinkun Xiao , Minying Qin , and Yuting Yin . 2020. Skeleton-based Chinese sign language recognition and generation for bidirectional communication between deaf and hearing people. Neural networks 125 ( 2020 ), 41--55. Qinkun Xiao, Minying Qin, and Yuting Yin. 2020. Skeleton-based Chinese sign language recognition and generation for bidirectional communication between deaf and hearing people. Neural networks 125 (2020), 41--55."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403331"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.400"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.323"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.570"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.273"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093516"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00119"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11248"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132920"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547957","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3547957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:31Z","timestamp":1750186831000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547957"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":56,"alternative-id":["10.1145\/3503161.3547957","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3547957","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}