{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:05:12Z","timestamp":1765310712980,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant No. 62366036"],"award-info":[{"award-number":["Grant No. 62366036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Education Science Planning Project","award":["Grant No. BIX230343"],"award-info":[{"award-number":["Grant No. BIX230343"]}]},{"name":"The Central Government Fund for Promoting Local Scientiffc and Technological Development","award":["Grant No. 2022ZY0198"],"award-info":[{"award-number":["Grant No. 2022ZY0198"]}]},{"name":"Program for Young Talents of Science and Technology in Universities of Inner Mongolia Autonomous Region","award":["Grant No. NJYT24033"],"award-info":[{"award-number":["Grant No. NJYT24033"]}]},{"name":"Inner Mongolia Autonomous Region Science and Technology Planning Project","award":["Grant No. 2023YFSH0017"],"award-info":[{"award-number":["Grant No. 2023YFSH0017"]}]},{"name":"Hohhot Science and Technology Project","award":["Grant No. 2023-Zhan-Zhong-1"],"award-info":[{"award-number":["Grant No. 2023-Zhan-Zhong-1"]}]},{"name":"Science and Technology Program of the Joint Fund of Scientific Research for the Public Hospitals of Inner Mongolia Academy of Medical Sciences","award":["Grant No.2023GLLH0035"],"award-info":[{"award-number":["Grant No.2023GLLH0035"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755129","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"3605-3614","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Fourier Self-Adaptation for Transferring General Pretrained Models to Specific Domains"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0962-724X","authenticated-orcid":false,"given":"Lei","family":"Liu","sequence":"first","affiliation":[{"name":"Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8061-1474","authenticated-orcid":false,"given":"Xiangdong","family":"Su","sequence":"additional","affiliation":[{"name":"Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5513-1192","authenticated-orcid":false,"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[{"name":"Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-023-01049-7"},{"key":"e_1_3_2_1_3_1","volume-title":"Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254","author":"Bao Hangbo","year":"2021","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2021. Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"e_1_3_2_1_6_1","volume-title":"Domain adaptation for visual applications: A comprehensive survey. arXiv preprint arXiv:1702.05374","author":"Csurka Gabriela","year":"2017","unstructured":"Gabriela Csurka. 2017. Domain adaptation for visual applications: A comprehensive survey. arXiv preprint arXiv:1702.05374 (2017)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"e_1_3_2_1_8_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arXiv:2305.06500 [cs.CV]"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_7"},{"key":"e_1_3_2_1_10_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_11_1","volume-title":"Does clip benefit visual question answering in the medical domain as much as it does in the general domain? arXiv preprint arXiv:2112.13906","author":"Eslami Sedigheh","year":"2021","unstructured":"Sedigheh Eslami, Gerard de Melo, and Christoph Meinel. 2021. Does clip benefit visual question answering in the medical domain as much as it does in the general domain? arXiv preprint arXiv:2112.13906 (2021)."},{"key":"e_1_3_2_1_12_1","volume-title":"Efficient and robust automated machine learning. Advances in neural information processing systems","author":"Feurer Matthias","year":"2015","unstructured":"Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Springenberg, Manuel Blum, and Frank Hutter. 2015. Efficient and robust automated machine learning. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66096-3_8"},{"key":"e_1_3_2_1_14_1","unstructured":"Google Cloud. 2021. Google AutoML Vision. https:\/\/cloud.google.com\/vision\/automl\/docs."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_17_1","volume-title":"Pathvqa: 30000 questions for medical visual question answering. arXiv preprint arXiv:2003.10286","author":"He Xuehai","year":"2020","unstructured":"Xuehai He, Yichen Zhang, Luntian Mou, Eric Xing, and Pengtao Xie. 2020. Pathvqa: 30000 questions for medical visual question answering. arXiv preprint arXiv:2003.10286 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531724"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"e_1_3_2_1_20_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Kim Jin-Hwa","year":"2018","unstructured":"Jin-Hwa Kim, Jaehyun Jun, and Byoung-Tak Zhang. 2018. Bilinear attention networks. Advances in Neural Information Processing Systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_21_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_22_1","volume-title":"International Conference on Machine Learning. PMLR, 17931-17952","author":"Kulinski Sean","year":"2023","unstructured":"Sean Kulinski and David I Inouye. 2023. Towards explaining distribution shifts. In International Conference on Machine Learning. PMLR, 17931-17952."},{"key":"e_1_3_2_1_23_1","volume-title":"Asma Ben Abacha, and Dina Demner-Fushman","author":"Lau Jason J","year":"2018","unstructured":"Jason J Lau, Soumya Gayen, Asma Ben Abacha, and Dina Demner-Fushman. 2018. A dataset of clinically generated visual questions and answers about radiology images. Scientific data, Vol. 5, 1 (2018), 1-10."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148307"},{"key":"e_1_3_2_1_25_1","volume-title":"Domain generalization for medical imaging classification with linear-dependency regularization. Advances in neural information processing systems","author":"Li Haoliang","year":"2020","unstructured":"Haoliang Li, YuFei Wang, Renjie Wan, Shiqi Wang, Tie-Qiang Li, and Alex Kot. 2020. Domain generalization for medical imaging classification with linear-dependency regularization. Advances in neural information processing systems, Vol. 33 (2020), 3118-3129."},{"key":"e_1_3_2_1_26_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43993-3_51"},{"volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Liu Bo","key":"e_1_3_2_1_28_1","unstructured":"Bo Liu, Li-Ming Zhan, and Xiao-Ming Wu. 2021c. Contrastive Pre-training and Representation Distillation for Medical Visual Question Answering Based on Radiology Images. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 210-220."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM55620.2022.9995347"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM62325.2024.10821918"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956469"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00107"},{"key":"e_1_3_2_1_34_1","volume-title":"MS-Net: multi-site network for improving prostate segmentation with heterogeneous MRI data","author":"Liu Quande","year":"2020","unstructured":"Quande Liu, Qi Dou, Lequan Yu, and Pheng Ann Heng. 2020. MS-Net: multi-site network for improving prostate segmentation with heterogeneous MRI data. IEEE transactions on medical imaging, Vol. 39, 9 (2020), 2713-2724."},{"key":"e_1_3_2_1_35_1","volume-title":"Task-customized masked autoencoder via mixture of cluster-conditional experts. arXiv preprint arXiv:2402.05382","author":"Liu Zhili","year":"2024","unstructured":"Zhili Liu, Kai Chen, Jianhua Han, Lanqing Hong, Hang Xu, Zhenguo Li, and James T Kwok. 2024a. Task-customized masked autoencoder via mixture of cluster-conditional experts. arXiv preprint arXiv:2402.05382 (2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3390\/app7100992"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"volume-title":"The fast Fourier transform","author":"Nussbaumer Henri J","key":"e_1_3_2_1_39_1","unstructured":"Henri J Nussbaumer and Henri J Nussbaumer. 1982. The fast Fourier transform. Springer."},{"key":"e_1_3_2_1_40_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_41_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_42_1","unstructured":"unum-cloud. 2023. Pocket-Sized Multimodal AI For Content Understanding and Generation. https:\/\/github.com\/unum-cloud\/uform."},{"key":"e_1_3_2_1_43_1","volume-title":"Git: A generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100","author":"Wang Jianfeng","year":"2022","unstructured":"Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu, Linjie Li, Kevin Lin, Zhe Gan, Zicheng Liu, Ce Liu, and Lijuan Wang. 2022. Git: A generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100 (2022)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28357"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01155"},{"key":"e_1_3_2_1_46_1","volume-title":"A fine-grained analysis on distribution shift. arXiv preprint arXiv:2110.11328","author":"Wiles Olivia","year":"2021","unstructured":"Olivia Wiles, Sven Gowal, Florian Stimberg, Sylvestre Alvise-Rebuffi, Ira Ktena, Krishnamurthy Dvijotham, and Taylan Cemgil. 2021. A fine-grained analysis on distribution shift. arXiv preprint arXiv:2110.11328 (2021)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01415"},{"key":"e_1_3_2_1_49_1","volume-title":"MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis. In IEEE 18th International Symposium on Biomedical Imaging (ISBI). 191-195","author":"Yang Jiancheng","year":"2021","unstructured":"Jiancheng Yang, Rui Shi, and Bingbing Ni. 2021a. MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis. In IEEE 18th International Symposium on Biomedical Imaging (ISBI). 191-195."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00885"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00414"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"e_1_3_2_1_54_1","volume-title":"Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"},{"key":"e_1_3_2_1_56_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. 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"e_1_3_2_1_58_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_59_1","first-page":"1","article-title":"Mutual attention inception network for remote sensing visual question answering","volume":"60","author":"Zheng Xiangtao","year":"2021","unstructured":"Xiangtao Zheng, Binqiang Wang, Xingqian Du, and Xiaoqiang Lu. 2021. Mutual attention inception network for remote sensing visual question answering. IEEE Transactions on Geoscience and Remote Sensing, Vol. 60 (2021), 1-14.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_60_1","volume-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417","author":"Zhu Lianghui","year":"2024","unstructured":"Lianghui Zhu, Bencheng Liao, Qian Zhang, Xinlong Wang, Wenyu Liu, and Xinggang Wang. 2024. Vision mamba: Efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417 (2024)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00697"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:00:06Z","timestamp":1765310406000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755129"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":61,"alternative-id":["10.1145\/3746027.3755129","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755129","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}