{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T18:19:02Z","timestamp":1786040342613,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":46,"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":[{"name":"National Natural Science Young Foundation of China","award":["No. 62102242"],"award-info":[{"award-number":["No. 62102242"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681292","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"8992-9000","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["MB2C: Multimodal Bidirectional Cycle Consistency for Learning Robust Visual Neural Representations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2132-976X","authenticated-orcid":false,"given":"Yayun","family":"Wei","sequence":"first","affiliation":[{"name":"College of Information Engineering, Shanghai Maritime University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8427-4548","authenticated-orcid":false,"given":"Lei","family":"Cao","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Shanghai Maritime University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3377-6706","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Shanghai Maritime University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4441-3355","authenticated-orcid":false,"given":"Yilin","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Shanghai Maritime University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cortex.2017.07.006"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/282403a0"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2207746"},{"key":"e_1_3_2_1_4_1","volume-title":"Combining features from erp components in single-trial eeg for discriminating four-category visual objects. Journal of neural engineering, 9(5):056013","author":"Xiong Shi","year":"2012","unstructured":"ChangmingWang, Shi Xiong, Xiaoping Hu, Li Yao, and Jiacai Zhang. Combining features from erp components in single-trial eeg for discriminating four-category visual objects. Journal of neural engineering, 9(5):056013, 2012."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263181"},{"key":"e_1_3_2_1_6_1","volume-title":"Decoding natural images from eeg for object recognition. arXiv preprint arXiv:2308.13234","author":"Song Yonghao","year":"2023","unstructured":"Yonghao Song, Bingchuan Liu, Xiang Li, Nanlin Shi, Yijun Wang, and Xiaorong Gao. Decoding natural images from eeg for object recognition. arXiv preprint arXiv:2308.13234 , 2023."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00738"},{"key":"e_1_3_2_1_8_1","first-page":"36","article-title":"Connecting multi-modal contrastive representations","author":"Zhao Yang","year":"2024","unstructured":"ZehanWang, Yang Zhao, Haifeng Huang, Jiageng Liu, Aoxiong Yin, Li Tang, Linjun Li, YongqiWang, Ziang Zhang, and Zhou Zhao. Connecting multi-modal contrastive representations. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_9_1","volume-title":"Unsupervised natural language inference via decoupled multimodal contrastive learning. arXiv preprint arXiv:2010.08200","author":"Cui Wanyun","year":"2020","unstructured":"Wanyun Cui, Guangyu Zheng, and Wei Wang. Unsupervised natural language inference via decoupled multimodal contrastive learning. arXiv preprint arXiv:2010.08200, 2020."},{"key":"e_1_3_2_1_10_1","volume-title":"mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412","author":"Zhang Hongyi","year":"2017","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412, 2017."},{"key":"e_1_3_2_1_11_1","first-page":"6438","volume-title":"International conference on machine learning","author":"Verma Vikas","year":"2019","unstructured":"Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez-Paz, and Yoshua Bengio. Manifold mixup: Better representations by interpolating hidden states. In International conference on machine learning, pages 6438--6447. PMLR, 2019."},{"key":"e_1_3_2_1_12_1","first-page":"36","article-title":"Discrete encoding of eeg waves for eeg to text translation","author":"Duan Yiqun","year":"2024","unstructured":"Yiqun Duan, Charles Chau, Zhen Wang, Yu-Kai Wang, and Chin-teng Lin. Dewave: Discrete encoding of eeg waves for eeg to text translation. Advances in Neural Information Processing Systems, 36, 2024.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110837"},{"key":"e_1_3_2_1_14_1","volume-title":"A penny for your (visual) thoughts: Self-supervised reconstruction of natural movies from brain activity. arXiv preprint arXiv:2206.03544","author":"Kupershmidt Ganit","year":"2022","unstructured":"Ganit Kupershmidt, Roman Beliy, Guy Gaziv, and Michal Irani. A penny for your (visual) thoughts: Self-supervised reconstruction of natural movies from brain activity. arXiv preprint arXiv:2206.03544, 2022."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00804"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01389"},{"key":"e_1_3_2_1_17_1","volume-title":"Xi-Zhao Wang, and QM Jonathan Wu. A review of generalized zero-shot learning methods","author":"Pourpanah Farhad","year":"2022","unstructured":"Farhad Pourpanah, Moloud Abdar, Yuxuan Luo, Xinlei Zhou, Ran Wang, Chee Peng Lim, Xi-Zhao Wang, and QM Jonathan Wu. A review of generalized zero-shot learning methods. IEEE transactions on pattern analysis and machine intelligence, 45(4):4051--4070, 2022."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00986"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00379"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2964429"},{"key":"e_1_3_2_1_21_1","first-page":"479","volume-title":"Proceedings, Part XXII 16","author":"Narayan Sanath","year":"2020","unstructured":"Sanath Narayan, Akshita Gupta, Fahad Shahbaz Khan, Cees GM Snoek, and Ling Shao. Latent embedding feedback and discriminative features for zero-shot classification. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXII 16, pages 479--495. Springer, 2020."},{"key":"e_1_3_2_1_22_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems, 27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. Advances in neural information processing systems, 27, 2014."},{"key":"e_1_3_2_1_23_1","volume-title":"Robin Tibor Schirrmeister, and Tonio Ball. Eeg-gan: Generative adversarial networks for electroencephalograhic (eeg) brain signals. arXiv preprint arXiv:1806.01875","author":"Hartmann Kay Gregor","year":"2018","unstructured":"Kay Gregor Hartmann, Robin Tibor Schirrmeister, and Tonio Ball. Eeg-gan: Generative adversarial networks for electroencephalograhic (eeg) brain signals. arXiv preprint arXiv:1806.01875, 2018."},{"key":"e_1_3_2_1_24_1","first-page":"1","volume-title":"ICASSP 2023--2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Singh Prajwal","year":"2023","unstructured":"Prajwal Singh, Pankaj Pandey, Krishna Miyapuram, and Shanmuganathan Raman. Eeg2image: image reconstruction from eeg brain signals. In ICASSP 2023--2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1--5. IEEE, 2023."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.479"},{"key":"e_1_3_2_1_26_1","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, JongWook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748--8763. PMLR, 2021."},{"key":"e_1_3_2_1_27_1","volume-title":"Dreamdiffusion: Generating high-quality images from brain eeg signals. arXiv preprint arXiv:2306.16934","author":"Bai Yunpeng","year":"2023","unstructured":"Yunpeng Bai, Xintao Wang, Yan-pei Cao, Yixiao Ge, Chun Yuan, and Ying Shan. Dreamdiffusion: Generating high-quality images from brain eeg signals. arXiv preprint arXiv:2306.16934, 2023."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02175"},{"key":"e_1_3_2_1_29_1","volume-title":"Brain decoding: toward real-time reconstruction of visual perception. arXiv preprint arXiv:2310.19812","author":"Benchetrit Yohann","year":"2023","unstructured":"Yohann Benchetrit, Hubert Banville, and Jean-R\u00e9mi King. Brain decoding: toward real-time reconstruction of visual perception. arXiv preprint arXiv:2310.19812, 2023."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.328"},{"key":"e_1_3_2_1_31_1","volume-title":"See what you see: Selfsupervised cross-modal retrieval of visual stimuli from brain activity. arXiv preprint arXiv:2208.03666","author":"Ye Zesheng","year":"2022","unstructured":"Zesheng Ye, Lina Yao, Yu Zhang, and Sylvia Gustin. See what you see: Selfsupervised cross-modal retrieval of visual stimuli from brain activity. arXiv preprint arXiv:2208.03666, 2022."},{"key":"e_1_3_2_1_32_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. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748, 2018."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00581"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.64"},{"key":"e_1_3_2_1_35_1","first-page":"2642","volume-title":"International conference on machine learning","author":"Odena Augustus","year":"2017","unstructured":"Augustus Odena, Christopher Olah, and Jonathon Shlens. Conditional image synthesis with auxiliary classifier gans. In International conference on machine learning, pages 2642--2651. PMLR, 2017."},{"key":"e_1_3_2_1_36_1","volume-title":"Wasserstein gan","author":"Arjovsky Martin","year":"2017","unstructured":"Martin Arjovsky, Soumith Chintala, and L\u00e9on Bottou. Wasserstein gan, 2017."},{"key":"e_1_3_2_1_37_1","volume-title":"Improved training of wasserstein gans. Advances in neural information processing systems, 30","author":"Gulrajani Ishaan","year":"2017","unstructured":"Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, and Aaron C Courville. Improved training of wasserstein gans. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127907"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2022.119754"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2995909"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2019.101730"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413858"},{"key":"e_1_3_2_1_44_1","volume-title":"Seeing through the brain: image reconstruction of visual perception from human brain signals. arXiv preprint arXiv:2308.02510","author":"Lan Yu-Ting","year":"2023","unstructured":"Yu-Ting Lan, Kan Ren, Yansen Wang, Wei-Long Zheng, Dongsheng Li, Bao-Liang Lu, and Lili Qiu. Seeing through the brain: image reconstruction of visual perception from human brain signals. arXiv preprint arXiv:2308.02510, 2023."},{"key":"e_1_3_2_1_45_1","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952, 2023."},{"key":"e_1_3_2_1_46_1","volume-title":"Visualizing data using t-sne. Journal of machine learning research, 9(11)","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681292","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:43Z","timestamp":1750295863000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681292"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":46,"alternative-id":["10.1145\/3664647.3681292","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681292","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"}}]}}