{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:59:07Z","timestamp":1777489147616,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["61972192, 62172208, 61906085, 41972111"],"award-info":[{"award-number":["61972192, 62172208, 61906085, 41972111"]}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583258","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T23:30:51Z","timestamp":1682551851000},"page":"1510-1518","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Learning Robust Multi-Modal Representation for Multi-Label Emotion Recognition via Adversarial Masking and Perturbation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9198-5324","authenticated-orcid":false,"given":"Shiping","family":"Ge","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5243-4992","authenticated-orcid":false,"given":"Zhiwei","family":"Jiang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8486-2614","authenticated-orcid":false,"given":"Zifeng","family":"Cheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0916-7803","authenticated-orcid":false,"given":"Cong","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9497-6244","authenticated-orcid":false,"given":"Yafeng","family":"Yin","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1112-790X","authenticated-orcid":false,"given":"Qing","family":"Gu","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, China"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Multimodal machine learning: A survey and taxonomy","author":"Baltru\u0161aitis Tadas","year":"2018","unstructured":"Tadas Baltru\u0161aitis, Chaitanya Ahuja, and Louis-Philippe Morency. 2018. Multimodal machine learning: A survey and taxonomy. IEEE transactions on pattern analysis and machine intelligence 41, 2 (2018), 423\u2013443."},{"key":"e_1_3_2_1_2_1","volume-title":"Optimized pre-processing for discrimination prevention. Advances in neural information processing systems 30","author":"Calmon Flavio","year":"2017","unstructured":"Flavio Calmon, Dennis Wei, Bhanukiran Vinzamuri, Karthikeyan Natesan\u00a0Ramamurthy, and Kush\u00a0R Varshney. 2017. Optimized pre-processing for discrimination prevention. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_3_1","volume-title":"Adversarial attacks and defences: A survey. arXiv preprint arXiv:1810.00069","author":"Chakraborty Anirban","year":"2018","unstructured":"Anirban Chakraborty, Manaar Alam, Vishal Dey, Anupam Chattopadhyay, and Debdeep Mukhopadhyay. 2018. Adversarial attacks and defences: A survey. arXiv preprint arXiv:1810.00069 (2018)."},{"key":"e_1_3_2_1_4_1","volume-title":"Journal of Physics: Conference Series, Vol.\u00a02161","author":"Chandra Shravan","year":"2049","unstructured":"Shravan Chandra and Bhaskarjyoti Das. 2022. An approach framework of transfer learning, adversarial training and hierarchical multi-task learning-a case study of disinformation detection with offensive text. In Journal of Physics: Conference Series, Vol.\u00a02161. IOP Publishing, 012049."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1566"},{"key":"e_1_3_2_1_6_1","volume-title":"COVAREP\u2014A collaborative voice analysis repository for speech technologies. In 2014 ieee international conference on acoustics, speech and signal processing (icassp)","author":"Degottex Gilles","unstructured":"Gilles Degottex, John Kane, Thomas Drugman, Tuomo Raitio, and Stefan Scherer. 2014. COVAREP\u2014A collaborative voice analysis repository for speech technologies. In 2014 ieee international conference on acoustics, speech and signal processing (icassp). IEEE, 960\u2013964."},{"key":"e_1_3_2_1_7_1","first-page":"3197","article-title":"Removing bias in multi-modal classifiers: Regularization by maximizing functional entropies","volume":"33","author":"Gat Itai","year":"2020","unstructured":"Itai Gat, Idan Schwartz, Alexander Schwing, and Tamir Hazan. 2020. Removing bias in multi-modal classifiers: Regularization by maximizing functional entropies. Advances in Neural Information Processing Systems 33 (2020), 3197\u20133208.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_8_1","volume-title":"Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572","author":"Goodfellow J","year":"2014","unstructured":"Ian\u00a0J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11296"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_12_1","volume-title":"Data augmentation for deep learning-based radio modulation classification","author":"Huang Liang","year":"2019","unstructured":"Liang Huang, Weijian Pan, You Zhang, Liping Qian, Nan Gao, and Yuan Wu. 2019. Data augmentation for deep learning-based radio modulation classification. IEEE access 8 (2019), 1498\u20131506."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413577"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_3"},{"key":"e_1_3_2_1_15_1","volume-title":"Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236","author":"Kurakin Alexey","year":"2016","unstructured":"Alexey Kurakin, Ian Goodfellow, and Samy Bengio. 2016. Adversarial machine learning at scale. arXiv preprint arXiv:1611.01236 (2016)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547969"},{"key":"e_1_3_2_1_17_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_18_1","volume-title":"Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083","author":"Madry Aleksander","year":"2017","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2017. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)."},{"key":"e_1_3_2_1_19_1","volume-title":"Adversarial training methods for semi-supervised text classification. arXiv preprint arXiv:1605.07725","author":"Miyato Takeru","year":"2016","unstructured":"Takeru Miyato, Andrew\u00a0M Dai, and Ian Goodfellow. 2016. Adversarial training methods for semi-supervised text classification. arXiv preprint arXiv:1605.07725 (2016)."},{"key":"e_1_3_2_1_20_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_22_1","volume-title":"Adversarial training for free!Advances in Neural Information Processing Systems 32","author":"Shafahi Ali","year":"2019","unstructured":"Ali Shafahi, Mahyar Najibi, Mohammad\u00a0Amin Ghiasi, Zheng Xu, John Dickerson, Christoph Studer, Larry\u00a0S Davis, Gavin Taylor, and Tom Goldstein. 2019. Adversarial training for free!Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings, Part III 16","author":"Tian Yapeng","year":"2020","unstructured":"Yapeng Tian, Dingzeyu Li, and Chenliang Xu. 2020. Unified multisensory perception: Weakly-supervised audio-visual video parsing. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part III 16. Springer, 436\u2013454."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"e_1_3_2_1_26_1","volume-title":"On modality bias in the TVQA dataset. arXiv preprint arXiv:2012.10210","author":"Winterbottom Thomas","year":"2020","unstructured":"Thomas Winterbottom, Sarah Xiao, Alistair McLean, and Noura\u00a0Al Moubayed. 2020. On modality bias in the TVQA dataset. arXiv preprint arXiv:2012.10210 (2020)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1187"},{"key":"e_1_3_2_1_28_1","first-page":"20520","article-title":"Differentiable top-k with optimal transport","volume":"33","author":"Xie Yujia","year":"2020","unstructured":"Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, and Tomas Pfister. 2020. Differentiable top-k with optimal transport. Advances in Neural Information Processing Systems 33 (2020), 20520\u201320531.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","volume-title":"Adversarial examples: Attacks and defenses for deep learning","author":"Yuan Xiaoyong","year":"2019","unstructured":"Xiaoyong Yuan, Pan He, Qile Zhu, and Xiaolin Li. 2019. Adversarial examples: Attacks and defenses for deep learning. IEEE transactions on neural networks and learning systems 30, 9 (2019), 2805\u20132824."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.291"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17686"},{"key":"e_1_3_2_1_33_1","volume-title":"Tailor versatile multi-modal learning for multi-label emotion recognition. arXiv preprint arXiv:2201.05834","author":"Zhang Yi","year":"2022","unstructured":"Yi Zhang, Mingyuan Chen, Jundong Shen, and Chongjun Wang. 2022. Tailor versatile multi-modal learning for multi-label emotion recognition. arXiv preprint arXiv:2201.05834 (2022)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5364"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583258","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:22Z","timestamp":1750178242000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583258"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":35,"alternative-id":["10.1145\/3543507.3583258","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583258","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}