{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:10:24Z","timestamp":1755825024571,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","funder":[{"name":"the Key Program of the National Natural Science Foundation of China","award":["No.62237001"],"award-info":[{"award-number":["No.62237001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733355","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:29:43Z","timestamp":1750876183000},"page":"1479-1487","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HGAtt-ARN: A Novel Adversarial Reconstruction Network Based on Higher-order Gate Attention for Incomplete Multimodal Sentiment Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2182-8949","authenticated-orcid":false,"given":"Qingpeng","family":"Wen","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4479-8248","authenticated-orcid":false,"given":"Pengfei","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6086-4634","authenticated-orcid":false,"given":"Fan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3199-2631","authenticated-orcid":false,"given":"Qintai","family":"Hu","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology, Guangzhou, China and Guangdong Institute of Digital Education, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8596-8333","authenticated-orcid":false,"given":"Bi","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4450-597X","authenticated-orcid":false,"given":"Guang","family":"Feng","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology, Guangzhou, China and Guangdong Institute of Digital Education, Guangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01505"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55394-8"},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859836"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.132"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.94"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"e_1_3_2_1_9_1","volume-title":"Asian conference on computer vision. Springer, 213--228","author":"Hazirbas Caner","year":"2016","unstructured":"Caner Hazirbas, Lingni Ma, Csaba Domokos, and Daniel Cremers. 2016. Fusenet: Incorporating depth into semantic segmentation via fusion-based cnn architecture. In Asian conference on computer vision. Springer, 213--228."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"volume-title":"The 61st Annual Meeting Of The Association For Computational Linguistics.","author":"Hu Yuchen","key":"e_1_3_2_1_12_1","unstructured":"Yuchen Hu, Chen Chen, Ruizhe Li, Heqing Zou, and Eng Siong Chng. 2023. MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition. In The 61st Annual Meeting Of The Association For Computational Linguistics."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. 1. Minneapolis, Minnesota."},{"key":"e_1_3_2_1_14_1","volume-title":"Supervised contrastive learning. Advances in neural information processing systems","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems, Vol. 33 (2020), 18661--18673."},{"key":"e_1_3_2_1_15_1","volume-title":"CAAI International Conference on Artificial Intelligence. Springer, 189--200","author":"Lei Yuxuan","year":"2023","unstructured":"Yuxuan Lei, Dingkang Yang, Mingcheng Li, Shunli Wang, Jiawei Chen, and Lihua Zhang. 2023. Text-oriented modality reinforcement network for multimodal sentiment analysis from unaligned multimodal sequences. In CAAI International Conference on Artificial Intelligence. Springer, 189--200."},{"key":"e_1_3_2_1_16_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Li Mingcheng","year":"2024","unstructured":"Mingcheng Li, Dingkang Yang, Yang Liu, Shunli Wang, Jiawei Chen, Shuaibing Wang, Jinjie Wei, Yue Jiang, Qingyao Xu, Xiaolu Hou, et al. 2024. Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"e_1_3_2_1_18_1","volume-title":"SimCLS: A simple framework for contrastive learning of abstractive summarization. arXiv preprint arXiv:2106.01890","author":"Liu Yixin","year":"2021","unstructured":"Yixin Liu and Pengfei Liu. 2021. SimCLS: A simple framework for contrastive learning of abstractive summarization. arXiv preprint arXiv:2106.01890 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"e_1_3_2_1_21_1","first-page":"689","article-title":"Multimodal deep learning","volume":"11","author":"Ngiam Jiquan","year":"2011","unstructured":"Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, Andrew Y Ng, et al. 2011. Multimodal deep learning.. In ICML, Vol. 11. 689--696.","journal-title":"ICML"},{"key":"e_1_3_2_1_22_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29374"},{"key":"e_1_3_2_1_24_1","volume-title":"A review of affective computing: From unimodal analysis to multimodal fusion. Information fusion","author":"Poria Soujanya","year":"2017","unstructured":"Soujanya Poria, Erik Cambria, Rajiv Bajpai, and Amir Hussain. 2017. A review of affective computing: From unimodal analysis to multimodal fusion. Information fusion, Vol. 37 (2017), 98--125."},{"key":"e_1_3_2_1_25_1","volume-title":"Deep multimodal learning: A survey on recent advances and trends","author":"Ramachandram Dhanesh","year":"2017","unstructured":"Dhanesh Ramachandram and Graham W Taylor. 2017. Deep multimodal learning: A survey on recent advances and trends. IEEE signal processing magazine, Vol. 34, 6 (2017), 96--108."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3047978"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3097002"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1177\/0165551510388123"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the conference. Association for computational linguistics. Meeting","volume":"2019","author":"Hubert Tsai Yao-Hung","year":"2019","unstructured":"Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019. Multimodal transformer for unaligned multimodal language sequences. In Proceedings of the conference. Association for computational linguistics. Meeting, Vol. 2019. NIH Public Access, 6558."},{"key":"e_1_3_2_1_31_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2022EDP7116"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658097"},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Neural Information Processing. Springer, 42--54","author":"Wen Qingpeng","year":"2023","unstructured":"Qingpeng Wen, Bi Zeng, Pengfei Wei, and Huiting Hu. 2023. A Deep Joint Model of Multi-scale Intent-Slots Interaction with Second-Order Gate for SLU. In International Conference on Neural Information Processing. Springer, 42--54."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475585"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Chicago IL USA","acronym":"ICMR '25"},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:11:14Z","timestamp":1755749474000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733355"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":38,"alternative-id":["10.1145\/3731715.3733355","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733355","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}