{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:08:36Z","timestamp":1765357716204,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076195, 62376070, 62206271"],"award-info":[{"award-number":["62076195, 62376070, 62206271"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["AUGA5710011522"],"award-info":[{"award-number":["AUGA5710011522"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3689092.3689399","type":"proceedings-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T18:33:17Z","timestamp":1729708397000},"page":"88-92","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Multimodal Blockwise Transformer for Robust Sentiment Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6144-5396","authenticated-orcid":false,"given":"Zhengqin","family":"Lai","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology & Pengcheng Laboratory, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0611-0636","authenticated-orcid":false,"given":"Xiaopeng","family":"Hong","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology & Pengcheng Laboratory, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2931-572X","authenticated-orcid":false,"given":"Yabin","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems 33","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems 33 (2020), 12449--12460."},{"key":"e_1_3_2_1_2_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023. Qwen Technical Report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_3_1","first-page":"32897","article-title":"Vlmo: Unified visionlanguage pre-training with mixture-of-modality-experts","volume":"35","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais Khan Mohammed, Kriti Aggarwal, Subhojit Som, Songhao Piao, and FuruWei. 2022. Vlmo: Unified visionlanguage pre-training with mixture-of-modality-experts. Advances in Neural Information Processing Systems 35 (2022), 32897--32912.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.189"},{"key":"e_1_3_2_1_5_1","volume-title":"Revisiting pre-trained models for Chinese natural language processing. arXiv preprint arXiv:2004.13922","author":"Cui Yiming","year":"2020","unstructured":"Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, and Guoping Hu. 2020. Revisiting pre-trained models for Chinese natural language processing. arXiv preprint arXiv:2004.13922 (2020)."},{"key":"e_1_3_2_1_6_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830596"},{"key":"e_1_3_2_1_8_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2017. Vse: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_1_9_1","unstructured":"Pengcheng Guo and Shixing Liu. 2022. chinese speech pretrain. https:\/\/github. com\/TencentGameMate\/chinese_speech_pretrain"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3337985"},{"key":"e_1_3_2_1_13_1","volume-title":"Kushal Lakhotia","author":"Hsu Wei-Ning","year":"2021","unstructured":"Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, and Abdelrahman Mohamed. 2021. Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM transactions on audio, speech, and language processing 29 (2021), 3451--3460."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0195-2"},{"key":"e_1_3_2_1_15_1","volume-title":"International conference on machine learning. PMLR, 5583--5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. Vilt: Vision-and-language transformer without convolution or region supervision. In International conference on machine learning. PMLR, 5583--5594."},{"key":"e_1_3_2_1_16_1","volume-title":"Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection. arXiv preprint arXiv:2402.19091","author":"Koutlis Christos","year":"2024","unstructured":"Christos Koutlis and Symeon Papadopoulos. 2024. Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection. arXiv preprint arXiv:2402.19091 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems 34","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems 34 (2021), 9694--9705."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551876.3554809"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612836"},{"key":"e_1_3_2_1_20_1","volume-title":"MER 2024: Semi- Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition. arXiv preprint arXiv:2404","author":"Lian Zheng","year":"2024","unstructured":"Zheng Lian, Haiyang Sun, Licai Sun, Zhuofan Wen, Siyuan Zhang, Shun Chen, Hao Gu, Jinming Zhao, Ziyang Ma, Xie Chen, et al. 2024. MER 2024: Semi- Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition. arXiv preprint arXiv:2404.17113 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"International conference on machine learning. PMLR, 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. PMLR, 8748--8763."},{"key":"e_1_3_2_1_22_1","volume-title":"Musan: A music, speech, and noise corpus. arXiv preprint arXiv:1510.08484","author":"Snyder David","year":"2015","unstructured":"David Snyder, Guoguo Chen, and Daniel Povey. 2015. Musan: A music, speech, and noise corpus. arXiv preprint arXiv:1510.08484 (2015)."},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on machine learning. PMLR, 10347--10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347--10357."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01494"},{"key":"e_1_3_2_1_25_1","volume-title":"Recent trends in deep learning based natural language processing. ieee Computational intelligenCe magazine 13, 3","author":"Young Tom","year":"2018","unstructured":"Tom Young, Devamanyu Hazarika, Soujanya Poria, and Erik Cambria. 2018. Recent trends in deep learning based natural language processing. ieee Computational intelligenCe magazine 13, 3 (2018), 55--75."},{"key":"e_1_3_2_1_26_1","volume-title":"IEEE International Conference on Automatic Face and Gesture Recognition.","author":"Zadeh Amir","year":"2018","unstructured":"Amir Zadeh, Yao Chong Lim, and Louis-Philippe Morency. 2018. OpenFace 2.0: Facial behavior analysis toolkit tadas baltru?aitis. In IEEE International Conference on Automatic Face and Gesture Recognition."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"e_1_3_2_1_28_1","volume-title":"More Productive End-to-End Speech Recognition Toolkit. arXiv preprint arXiv:2203.15455","author":"Zhang Binbin","year":"2022","unstructured":"Binbin Zhang, Di Wu, Zhendong Peng, Xingchen Song, Zhuoyuan Yao, Hang Lv, Lei Xie, Chao Yang, Fuping Pan, and Jianwei Niu. 2022. WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit. arXiv preprint arXiv:2203.15455 (2022)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3213509"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Sicheng Zhao Xiaopeng Hong Jufeng Yang Yanyan Zhao and Guiguang Ding. 2023. Toward Label-Efficient Emotion and Sentiment Analysis This article introduces label-efficient emotion and sentiment analysis from the computational perspective focusing on state-of-the-art methodologies promising applications and potential outlooks. Proc. IEEE (2023).","DOI":"10.1109\/JPROC.2023.3309299"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689092.3689399","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689092.3689399","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:59:21Z","timestamp":1755914361000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689092.3689399"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":30,"alternative-id":["10.1145\/3689092.3689399","10.1145\/3689092"],"URL":"https:\/\/doi.org\/10.1145\/3689092.3689399","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}