{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:46Z","timestamp":1750309486052,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":41,"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:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680955","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"9360-9368","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Training Spatial-Frequency Visual Prompts and Probabilistic Clusters for Accurate Black-Box Transfer Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4547-734X","authenticated-orcid":false,"given":"Wonwoo","family":"Cho","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology & Letsur Inc., Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8940-656X","authenticated-orcid":false,"given":"Kangyeol","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science & Technology & Letsur Inc., Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5146-0997","authenticated-orcid":false,"given":"Saemee","family":"Choi","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science & Technology, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1071-4835","authenticated-orcid":false,"given":"Jaegul","family":"Choo","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology & Letsur Inc., Daejeon, Republic of Korea"}],"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":"International Conference on Machine Learning. PMLR, 528--539","author":"Bahng Hyojin","year":"2020","unstructured":"Hyojin Bahng, Sanghyuk Chun, Sangdoo Yun, Jaegul Choo, and Seong Joon Oh. 2020. Learning de-biased representations with biased representations. In International Conference on Machine Learning. PMLR, 528--539."},{"key":"e_1_3_2_1_2_1","volume-title":"Exploring visual prompts for adapting large-scale models. arXiv preprint arXiv:2203.17274","author":"Bahng Hyojin","year":"2022","unstructured":"Hyojin Bahng, Ali Jahanian, Swami Sankaranarayanan, and Phillip Isola. 2022. Exploring visual prompts for adapting large-scale models. arXiv preprint arXiv:2203.17274 (2022)."},{"key":"e_1_3_2_1_3_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_4_1","first-page":"10","article-title":"Finding Metric Structure in Information Theoretic Clustering","volume":"8","author":"Chaudhuri Kamalika","year":"2008","unstructured":"Kamalika Chaudhuri and Andrew McGregor. 2008. Finding Metric Structure in Information Theoretic Clustering.. In COLT, Vol. 8. 10.","journal-title":"COLT"},{"key":"e_1_3_2_1_5_1","volume-title":"ICASSP 2023--2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5.","author":"Chen Aochuan","year":"2023","unstructured":"Aochuan Chen, Peter Lorenz, Yuguang Yao, Pin-Yu Chen, and Sijia Liu. 2023. Vi- sual prompting for adversarial robustness. In ICASSP 2023--2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5."},{"key":"e_1_3_2_1_6_1","volume-title":"Low frequency adversarial perturbation. arXiv preprint arXiv:1809.08758","author":"Guo Chuan","year":"2018","unstructured":"Chuan Guo, Jared S Frank, and Kilian Q Weinberger. 2018. Low frequency adversarial perturbation. arXiv preprint arXiv:1809.08758 (2018)."},{"key":"e_1_3_2_1_7_1","volume-title":"Black-box tuning of vision-language models with effective gradient approximation. arXiv preprint arXiv:2312.15901","author":"Guo Zixian","year":"2023","unstructured":"Zixian Guo, Yuxiang Wei, Ming Liu, Zhilong Ji, Jinfeng Bai, Yiwen Guo, and Wangmeng Zuo. 2023. Black-box tuning of vision-language models with effective gradient approximation. arXiv preprint arXiv:2312.15901 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning. PMLR, 2790--2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790--2799."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00154"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01047"},{"key":"e_1_3_2_1_11_1","first-page":"33716","article-title":"Knowledge distillation from a stronger teacher","volume":"35","author":"Huang Tao","year":"2022","unstructured":"Tao Huang, Shan You, Fei Wang, Chen Qian, and Chang Xu. 2022. Knowledge distillation from a stronger teacher. Advances in Neural Information Processing Systems 35 (2022), 33716--33727.","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Euro- pean Conference on Computer Vision","author":"Jia Menglin","key":"e_1_3_2_1_12_1","unstructured":"Menglin Jia, Luming Tang, Bor-Chun Chen, Claire Cardie, Serge Belongie, Bharath Hariharan, and Ser-Nam Lim. 2022. Visual prompt tuning. In Euro- pean Conference on Computer Vision. Springer, 709--727."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00407"},{"key":"e_1_3_2_1_14_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In ICML.","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 ICML."},{"key":"e_1_3_2_1_16_1","volume-title":"Align before fuse: Vision and language repre- sentation 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 repre- sentation learning with momentum distillation. Advances in neural information processing systems 34 (2021), 9694--9705."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3003837"},{"key":"e_1_3_2_1_18_1","volume-title":"Explicit Visual Prompting for Universal Foreground Segmentations. arXiv preprint arXiv:2305.18476","author":"Liu Weihuang","year":"2023","unstructured":"Weihuang Liu, Xi Shen, Chi-Man Pun, and Xiaodong Cun. 2023. Explicit Visual Prompting for Universal Foreground Segmentations. arXiv preprint arXiv:2305.18476 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Doklady Akademii Nauk","volume":"269","author":"Nesterov Yurii","year":"1983","unstructured":"Yurii Evgen?evich Nesterov. 1983. A method of solving a convex programming problem with convergence rate ?? ( 1 ??2 ). In Doklady Akademii Nauk, Vol. 269. Russian Academy of Sciences, 543--547."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02320"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01424"},{"key":"e_1_3_2_1_22_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_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/9.119632"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings, Part XIV 16","author":"Tian Yonglong","year":"2020","unstructured":"Yonglong Tian, Yue Wang, Dilip Krishnan, Joshua B Tenenbaum, and Phillip Isola. 2020. Rethinking few-shot image classification: a good embedding is all you need?. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XIV 16. Springer, 266--282."},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Machine Learning. PMLR, 9614--9624","author":"Tsai Yun-Yun","year":"2020","unstructured":"Yun-Yun Tsai, Pin-Yu Chen, and Tsung-Yi Ho. 2020. Transfer learning without knowing: Reprogramming black-box machine learning models with scarce data and limited resources. In International Conference on Machine Learning. PMLR, 9614--9624."},{"key":"e_1_3_2_1_28_1","volume-title":"AutoVP: An Automated Visual Prompting Framework and Benchmark. arXiv preprint arXiv:2310.08381","author":"Tsao Hsi-Ai","year":"2023","unstructured":"Hsi-Ai Tsao, Lei Hsiung, Pin-Yu Chen, Sijia Liu, and Tsung-Yi Ho. 2023. AutoVP: An Automated Visual Prompting Framework and Benchmark. arXiv preprint arXiv:2310.08381 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"AutoVP: An Automated Visual Prompting Framework and Benchmark. arXiv preprint arXiv:2310.08381","author":"Tsao Hsi-Ai","year":"2023","unstructured":"Hsi-Ai Tsao, Lei Hsiung, Pin-Yu Chen, Sijia Liu, and Tsung-Yi Ho. 2023. AutoVP: An Automated Visual Prompting Framework and Benchmark. arXiv preprint arXiv:2310.08381 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation. arXiv preprint arXiv:2304.13672","author":"Wang Yan","year":"2023","unstructured":"Yan Wang, Jian Cheng, Yixin Chen, Shuai Shao, Lanyun Zhu, Zhenzhou Wu, Tao Liu, and Haogang Zhu. 2023. FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation. arXiv preprint arXiv:2304.13672 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation. arXiv preprint arXiv:2304.13672","author":"Wang Yan","year":"2023","unstructured":"Yan Wang, Jian Cheng, Yixin Chen, Shuai Shao, Lanyun Zhu, Zhenzhou Wu, Tao Liu, and Haogang Zhu. 2023. FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation. arXiv preprint arXiv:2304.13672 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"Unleashing the power of visual prompting at the pixel level. arXiv preprint arXiv:2212.10556","author":"Wu Junyang","year":"2022","unstructured":"Junyang Wu, Xianhang Li, Chen Wei, Huiyu Wang, Alan Yuille, Yuyin Zhou, and Cihang Xie. 2022. Unleashing the power of visual prompting at the pixel level. arXiv preprint arXiv:2212.10556 (2022)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01415"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00903"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00414"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Lang Yu Qin Chen Jiaju Lin and Liang He. 2023. Black-box Prompt Tuning for Vision-Language Model as a Service.. In IJCAI. 1686--1694.","DOI":"10.24963\/ijcai.2023\/187"},{"key":"e_1_3_2_1_37_1","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu Tianhe","year":"2020","unstructured":"Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, and Chelsea Finn. 2020. Gradient surgery for multi-task learning. Advances in Neural Information Processing Systems 33 (2020), 5824--5836.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","volume-title":"Unified vision and language prompt learning. arXiv preprint arXiv:2210.07225","author":"Zang Yuhang","year":"2022","unstructured":"Yuhang Zang, Wei Li, Kaiyang Zhou, Chen Huang, and Chen Change Loy. 2022. Unified vision and language prompt learning. arXiv preprint arXiv:2210.07225 (2022)."},{"key":"e_1_3_2_1_39_1","volume-title":"Tip-adapter: Training-free clip-adapter for better vision-language modeling. arXiv preprint arXiv:2111.03930","author":"Zhang Renrui","year":"2021","unstructured":"Renrui Zhang, Rongyao Fang, Wei Zhang, Peng Gao, Kunchang Li, Jifeng Dai, Yu Qiao, and Hongsheng Li. 2021. Tip-adapter: Training-free clip-adapter for better vision-language modeling. arXiv preprint arXiv:2111.03930 (2021)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"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 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680955","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:34Z","timestamp":1750295854000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680955"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":41,"alternative-id":["10.1145\/3664647.3680955","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680955","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"}}]}}