{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T01:50:31Z","timestamp":1780105831076,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":53,"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":[{"name":"the National Science Foundation of China under Grant","award":["62076228"],"award-info":[{"award-number":["62076228"]}]},{"name":"the National Key R\\&D Program of China under Grant","award":["2020AAA0107100"],"award-info":[{"award-number":["2020AAA0107100"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612652","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"3550-3559","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["DPNET: Dynamic Poly-attention Network for Trustworthy Multi-modal Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4771-3836","authenticated-orcid":false,"given":"Xin","family":"Zou","sequence":"first","affiliation":[{"name":"China University of Geosciences, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6515-7696","authenticated-orcid":false,"given":"Chang","family":"Tang","sequence":"additional","affiliation":[{"name":"China University of Geosciences, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5146-4890","authenticated-orcid":false,"given":"Xiao","family":"Zheng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9151-3631","authenticated-orcid":false,"given":"Zhenglai","family":"Li","sequence":"additional","affiliation":[{"name":"China University of Geosciences, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5928-7083","authenticated-orcid":false,"given":"Xiao","family":"He","sequence":"additional","affiliation":[{"name":"China University of Geosciences, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7796-6952","authenticated-orcid":false,"given":"Shan","family":"An","sequence":"additional","affiliation":[{"name":"JD Health International Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9066-1475","authenticated-orcid":false,"given":"Xinwang","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.05.008"},{"key":"e_1_3_2_1_2_1","volume-title":"International conference on machine learning. PMLR, 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. PMLR, 1247--1255."},{"key":"e_1_3_2_1_3_1","volume-title":"Depth uncertainty in neural networks. Advances in neural information processing systems","author":"Antor\u00e1n Javier","year":"2020","unstructured":"Javier Antor\u00e1n, James Allingham, and Jos\u00e9 Miguel Hern\u00e1ndez-Lobato. 2020. Depth uncertainty in neural networks. Advances in neural information processing systems, Vol. 33 (2020), 10620--10634."},{"key":"e_1_3_2_1_4_1","volume-title":"Manuel Montes-y G\u00f3mez, and Fabio A Gonz\u00e1lez","author":"Arevalo John","year":"2017","unstructured":"John Arevalo, Thamar Solorio, Manuel Montes-y G\u00f3mez, and Fabio A Gonz\u00e1lez. 2017. Gated multimodal units for information fusion. arXiv preprint arXiv:1702.01992 (2017)."},{"key":"e_1_3_2_1_5_1","volume-title":"Multimodal machine learning: A survey and taxonomy","author":"Tadas Baltruvs","year":"2018","unstructured":"Tadas Baltruvs aitis, Chaitanya Ahuja, and Louis-Philippe Morency. 2018. Multimodal machine learning: A survey and taxonomy. IEEE transactions on pattern analysis and machine intelligence, Vol. 41, 2 (2018), 423--443."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-021-00408-3"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"e_1_3_2_1_8_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Du Yilun","year":"2018","unstructured":"Yilun Du, Zhijian Liu, Hector Basevi, Ales Leonardis, Bill Freeman, Josh Tenenbaum, and Jiajun Wu. 2018. Learning to exploit stability for 3d scene parsing. Advances in Neural Information Processing Systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"e_1_3_2_1_10_1","volume-title":"miR-378? mediates metabolic shift in breast cancer cells via the PGC-1\u03b2\/ERR\u03b3 transcriptional pathway. Cell metabolism","author":"Eichner Lillian J","year":"2010","unstructured":"Lillian J Eichner, Marie-Claude Perry, Catherine R Dufour, Nicholas Bertos, Morag Park, Julie St-Pierre, and Vincent Gigu\u00e8re. 2010. miR-378? mediates metabolic shift in breast cancer cells via the PGC-1\u03b2\/ERR\u03b3 transcriptional pathway. Cell metabolism, Vol. 12, 4 (2010), 352--361."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITB.2009.2037317"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16924"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2858933"},{"key":"e_1_3_2_1_14_1","first-page":"19251","article-title":"BayReL: Bayesian relational learning for multi-omics data integration","volume":"33","author":"Hajiramezanali Ehsan","year":"2020","unstructured":"Ehsan Hajiramezanali, Arman Hasanzadeh, Nick Duffield, Krishna Narayanan, and Xiaoning Qian. 2020. BayReL: Bayesian relational learning for multi-omics data integration. Advances in Neural Information Processing Systems, Vol. 33 (2020), 19251--19263.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02005"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3171983"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3016820"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683898"},{"key":"e_1_3_2_1_19_1","first-page":"10944","article-title":"What makes multi-modal learning better than single (provably)","volume":"34","author":"Huang Yu","year":"2021","unstructured":"Yu Huang, Chenzhuang Du, Zihui Xue, Xuanyao Chen, Hang Zhao, and Longbo Huang. 2021. What makes multi-modal learning better than single (provably). Advances in Neural Information Processing Systems, Vol. 34 (2021), 10944--10956.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","volume-title":"Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950","author":"Kiela Douwe","year":"2019","unstructured":"Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, Ethan Perez, and Davide Testuggine. 2019. Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950 (2019)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3081930"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475235"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2014.6946657"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20724"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Haojie Ma Wenzhong Li Xiao Zhang Songcheng Gao and Sanglu Lu. 2019. AttnSense: Multi-level attention mechanism for multimodal human activity recognition.. In IJCAI. 3109--3115.","DOI":"10.24963\/ijcai.2019\/431"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41388-019-0793-7"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00054"},{"key":"e_1_3_2_1_29_1","volume-title":"international conference on machine learning. PMLR, 7034--7044","author":"Moon Jooyoung","year":"2020","unstructured":"Jooyoung Moon, Jihyo Kim, Younghak Shin, and Sangheum Hwang. 2020. Confidence-aware learning for deep neural networks. In international conference on machine learning. PMLR, 7034--7044."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2106235118"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00029"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18632\/oncotarget.7437"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty1054"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70096-0_78"},{"key":"e_1_3_2_1_36_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_37_1","unstructured":"Petar Velickovic Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio Yoshua Bengio et al. 2017. Graph attention networks. stat Vol. 1050 20 (2017) 10-48550."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.23919\/ICIF.2017.8009768"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015281"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Siwei Wang Xinwang Liu En Zhu Chang Tang Jiyuan Liu Jingtao Hu Jingyuan Xia and Jianping Yin. 2019a. Multi-view Clustering via Late Fusion Alignment Maximization.. In IJCAI. 3778--3784.","DOI":"10.24963\/ijcai.2019\/524"},{"key":"e_1_3_2_1_42_1","volume-title":"MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification. Nature communications","author":"Wang Tongxin","year":"2021","unstructured":"Tongxin Wang, Wei Shao, Zhi Huang, Haixu Tang, Jie Zhang, Zhengming Ding, and Kun Huang. 2021. MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification. Nature communications, Vol. 12, 1 (2021), 3445."},{"key":"e_1_3_2_1_43_1","volume-title":"International conference on machine learning. PMLR, 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. PMLR, 1083--1092."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01285"},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the 28th international conference on machine learning (ICML-11)","author":"Welling Max","year":"2011","unstructured":"Max Welling and Yee W Teh. 2011. Bayesian learning via stochastic gradient Langevin dynamics. In Proceedings of the 28th international conference on machine learning (ICML-11). 681--688."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2933511"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17260"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106970"},{"key":"e_1_3_2_1_50_1","volume-title":"Multimodal skin lesion classification using deep learning. Experimental dermatology","author":"Yap Jordan","year":"2018","unstructured":"Jordan Yap, William Yolland, and Philipp Tschandl. 2018. Multimodal skin lesion classification using deep learning. Experimental dermatology, Vol. 27, 11 (2018), 1261--1267."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539388"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.312"},{"key":"e_1_3_2_1_53_1","unstructured":"Handong Zhao Hongfu Liu and Yun Fu. 2016. Incomplete multi-modal visual data grouping.. In IJCAI. 2392--2398."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612652","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612652","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:02:54Z","timestamp":1755820974000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612652"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":53,"alternative-id":["10.1145\/3581783.3612652","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612652","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"}}]}}