{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T03:34:31Z","timestamp":1764646471319,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62133012, 61936006, 62103314, 62203354, 61876144, 61876145, 62073255"],"award-info":[{"award-number":["62133012, 61936006, 62103314, 62203354, 61876144, 61876145, 62073255"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Shaanxi","award":["2020ZDLGY04-07"],"award-info":[{"award-number":["2020ZDLGY04-07"]}]},{"name":"Innovation Capability Support Program of Shaanxi","award":["2021TD-05"],"award-info":[{"award-number":["2021TD-05"]}]},{"name":"Open Project of Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University","award":["MMC202105"],"award-info":[{"award-number":["MMC202105"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612527","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"3051-3059","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Unbalanced Multi-view Deep Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7191-7348","authenticated-orcid":false,"given":"Cai","family":"Xu","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6305-0828","authenticated-orcid":false,"given":"Zehui","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2413-4698","authenticated-orcid":false,"given":"Ziyu","family":"Guan","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9767-1323","authenticated-orcid":false,"given":"Wei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5550-6354","authenticated-orcid":false,"given":"Xiangyu","family":"Song","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3459-5079","authenticated-orcid":false,"given":"Yue","family":"Wu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9059-330X","authenticated-orcid":false,"given":"Jianxin","family":"Li","sequence":"additional","affiliation":[{"name":"Deakin University, Geelong, Australia"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of The 27th Conference on Learning Theory","volume":"35","author":"Agarwal Alekh","year":"2014","unstructured":"Alekh Agarwal, Animashree Anandkumar, Prateek Jain, Praneeth Netrapalli, and Rashish Tandon. 2014. Learning Sparsely Used Overcomplete Dictionaries. In Proceedings of The 27th Conference on Learning Theory, Vol. 35. 123--137."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881199"},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Machine Learning. 1247--1255","author":"Andrew Galen","year":"2013","unstructured":"Galen Andrew, Raman Arora, Jeff Bilmes, and Karen Livescu. 2013. Deep canonical correlation analysis. In International Conference on Machine Learning. 1247--1255."},{"key":"e_1_3_2_1_4_1","volume-title":"Graph regularized nonnegative matrix factorization for data representation","author":"Cai Deng","year":"2010","unstructured":"Deng Cai, Xiaofei He, Jiawei Han, and Thomas S Huang. 2010. Graph regularized nonnegative matrix factorization for data representation. IEEE transactions on Pattern Analysis and Machine Intelligence, Vol. 33, 8 (2010), 1548--1560."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3242473"},{"key":"e_1_3_2_1_7_1","volume-title":"Sparse overcomplete word vector representations. arXiv preprint arXiv:1506.02004","author":"Faruqui Manaal","year":"2015","unstructured":"Manaal Faruqui, Yulia Tsvetkov, Dani Yogatama, Chris Dyer, and Noah Smith. 2015. Sparse overcomplete word vector representations. arXiv preprint arXiv:1506.02004 (2015)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16924"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"e_1_3_2_1_10_1","volume-title":"Dsd: Dense-sparse-dense training for deep neural networks. arXiv preprint arXiv:1607.04381","author":"Han Song","year":"2016","unstructured":"Song Han, Jeff Pool, Sharan Narang, Huizi Mao, Enhao Gong, Shijian Tang, Erich Elsen, Peter Vajda, Manohar Paluri, John Tran, et al. 2016. Dsd: Dense-sparse-dense training for deep neural networks. arXiv preprint arXiv:1607.04381 (2016)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3171983"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20652"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3083072"},{"key":"e_1_3_2_1_14_1","volume-title":"Dictionary learning algorithms for sparse representation. Neural computation","author":"Kreutz-Delgado Kenneth","year":"2003","unstructured":"Kenneth Kreutz-Delgado, Joseph F Murray, Bhaskar D Rao, Kjersti Engan, Te-Won Lee, and Terrence J Sejnowski. 2003. Dictionary learning algorithms for sparse representation. Neural computation, Vol. 15, 2 (2003), 349--396."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/404"},{"key":"e_1_3_2_1_16_1","volume-title":"DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification. arXiv preprint arXiv:2303.08358","author":"Liu Chengliang","year":"2023","unstructured":"Chengliang Liu, Jie Wen, Xiaoling Luo, Chao Huang, Zhihao Wu, and Yong Xu. 2023. DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification. arXiv preprint arXiv:2303.08358 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Late fusion incomplete multi-view clustering","author":"Liu Xinwang","year":"2018","unstructured":"Xinwang Liu, Xinzhong Zhu, Miaomiao Li, Lei Wang, Chang Tang, Jianping Yin, Dinggang Shen, Huaimin Wang, and Wen Gao. 2018. Late fusion incomplete multi-view clustering. IEEE transactions on Pattern Analysis and Machine Intelligence, Vol. 41, 10 (2018), 2410--2423."},{"key":"e_1_3_2_1_18_1","volume-title":"Self-supervised correlation learning for cross-modal retrieval","author":"Liu Yaxin","year":"2022","unstructured":"Yaxin Liu, Jianlong Wu, Leigang Qu, Tian Gan, Jianhua Yin, and Liqiang Nie. 2022. Self-supervised correlation learning for cross-modal retrieval. IEEE Transactions on Multimedia (2022)."},{"key":"e_1_3_2_1_19_1","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume":"34","author":"Nagrani Arsha","year":"2021","unstructured":"Arsha Nagrani, Shan Yang, Anurag Arnab, Aren Jansen, Cordelia Schmid, and Chen Sun. 2021. Attention bottlenecks for multimodal fusion. Advances in Neural Information Processing Systems, Vol. 34 (2021), 14200--14213.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01538"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0090-4295(96)00611-5"},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Machine Learning. 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. 8748--8763."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/127"},{"key":"e_1_3_2_1_24_1","volume-title":"Asian conference on machine learning. 113--128","author":"Tao Hong","year":"2017","unstructured":"Hong Tao, Chenping Hou, Jubo Zhu, and Dongyun Yi. 2017. Multi-view clustering with adaptively learned graph. In Asian conference on machine learning. 113--128."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428184"},{"key":"e_1_3_2_1_26_1","volume-title":"International conference on machine learning. 1083--1092","author":"Wang Weiran","year":"2015","unstructured":"Weiran Wang, Raman Arora, Karen Livescu, and Jeff Bilmes. 2015. On deep multi-view representation learning. In International conference on machine learning. 1083--1092."},{"key":"e_1_3_2_1_27_1","first-page":"4835","article-title":"Deep multimodal fusion by channel exchanging","volume":"33","author":"Wang Yikai","year":"2020","unstructured":"Yikai Wang, Wenbing Huang, Fuchun Sun, Tingyang Xu, Yu Rong, and Junzhou Huang. 2020. Deep multimodal fusion by channel exchanging. Advances in Neural Information Processing Systems, Vol. 33 (2020), 4835--4845.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","volume-title":"A survey on incomplete multiview clustering","author":"Wen Jie","year":"2022","unstructured":"Jie Wen, Zheng Zhang, Lunke Fei, Bob Zhang, Yong Xu, Zhao Zhang, and Jinxing Li. 2022. A survey on incomplete multiview clustering. IEEE Transactions on Systems, Man, and Cybernetics: Systems (2022)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413807"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17231"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101766"},{"key":"e_1_3_2_1_32_1","volume-title":"Adversarial incomplete multiview subspace clustering networks","author":"Xu Cai","year":"2021","unstructured":"Cai Xu, Hongmin Liu, Ziyu Guan, Xunlian Wu, Jiale Tan, and Beilei Ling. 2021. Adversarial incomplete multiview subspace clustering networks. IEEE Transactions on Cybernetics (2021)."},{"key":"e_1_3_2_1_33_1","volume-title":"Progressive Deep Multi-view Comprehensive Representation Learning. In Thirty-Seventh AAAI Conference on Artificial Intelligence.","author":"Xu Cai","year":"2023","unstructured":"Cai Xu, wei Zhao, Jinglong Zhao, Ziyu Guan, Yaming Yang, Long Chen, and Xiangyu Song. 2023. Progressive Deep Multi-view Comprehensive Representation Learning. In Thirty-Seventh AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806315"},{"key":"e_1_3_2_1_35_1","volume-title":"International Conference on Machine Learning. 3958--3966","author":"Yoon Jaehong","year":"2017","unstructured":"Jaehong Yoon and Sung Ju Hwang. 2017. Combined group and exclusive sparsity for deep neural networks. In International Conference on Machine Learning. 3958--3966."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00631"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062692"},{"key":"e_1_3_2_1_38_1","first-page":"2402","article-title":"Deep Partial Multi-View Learning","volume":"44","author":"Zhang Changqing","year":"2022","unstructured":"Changqing Zhang, Yajie Cui, Zongbo Han, Joey Tianyi Zhou, Huazhu Fu, and Qinghua Hu. 2022a. Deep Partial Multi-View Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 5 (2022), 2402--2415.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2627806"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3189239"},{"key":"e_1_3_2_1_41_1","volume-title":"Joey Tianyi Zhou, and Qinghua Hu. 2023 b. Calibrating Multimodal Learning. arXiv preprint arXiv:2306.01265","author":"Qingyang Zhang Huan Ma","year":"2023","unstructured":"Huan Ma Qingyang Zhang, Changqing Zhang, Bingzhe Wu, Huazhu Fu, Joey Tianyi Zhou, and Qinghua Hu. 2023 b. Calibrating Multimodal Learning. arXiv preprint arXiv:2306.01265 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"Joey Tianyi Zhou, and Xi Peng. 2023 a. Provable Dynamic Fusion for Low-Quality Multimodal Data. arXiv preprint arXiv:2306.02050","author":"Zhang Qingyang","year":"2023","unstructured":"Qingyang Zhang, Haitao Wu, Changqing Zhang, Qinghua Hu, Huazhu Fu, Joey Tianyi Zhou, and Xi Peng. 2023 a. Provable Dynamic Fusion for Low-Quality Multimodal Data. arXiv preprint arXiv:2306.02050 (2023)."},{"key":"e_1_3_2_1_43_1","volume-title":"Graph-guided Unsupervised Multi-view Representation Learning","author":"Zheng Qinghai","year":"2022","unstructured":"Qinghai Zheng, Jihua Zhu, Zhongyu Li, and Haoyu Tang. 2022. Graph-guided Unsupervised Multi-view Representation Learning. IEEE Transactions on Circuits and Systems for Video Technology (2022)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.115"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2974065"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612527","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:57:24Z","timestamp":1755820644000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612527"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":45,"alternative-id":["10.1145\/3581783.3612527","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612527","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}