{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T09:07:10Z","timestamp":1769504830365,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"U.S. Office of Naval Research Award","award":["N00014-24-1-2668"],"award-info":[{"award-number":["N00014-24-1-2668"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2316306"],"award-info":[{"award-number":["IIS-2316306"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2330215"],"award-info":[{"award-number":["CNS-2330215"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1145\/3716553.3750817","type":"proceedings-article","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:15:12Z","timestamp":1760188512000},"page":"663-672","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Few-shot Fine-grained Image Classification with Interpretable Prompt Learning through Distribution Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2856-4011","authenticated-orcid":false,"given":"Dongliang","family":"Guo","sequence":"first","affiliation":[{"name":"Data Science, University of Virginia, Charlottesville, Virginia, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3775-2954","authenticated-orcid":false,"given":"Handong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9758-0635","authenticated-orcid":false,"given":"Ryan","family":"Rossi","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3580-5290","authenticated-orcid":false,"given":"Sungchul","family":"Kim","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3779-7784","authenticated-orcid":false,"given":"Nedim","family":"Lipka","sequence":"additional","affiliation":[{"name":"Adobe Research, Adobe Systems, San Jose, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5991-2050","authenticated-orcid":false,"given":"Tong","family":"Yu","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1205-8632","authenticated-orcid":false,"given":"Sheng","family":"Li","sequence":"additional","affiliation":[{"name":"Data Science, University of Virginia, Charlottesville, Virginia, USA and Computer Science, University of Georgia, Athens, Georgia, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_3_1_3_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01834"},{"key":"e_1_3_3_1_5_2","unstructured":"Guangyi Chen Weiran Yao Xiangchen Song Xinyue Li Yongming Rao and Kun Zhang. 2022. Prompt learning with optimal transport for vision-language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.01253 (2022)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Peng Gao Shijie Geng Renrui Zhang Teli Ma Rongyao Fang Yongfeng Zhang Hongsheng Li and Yu Qiao. 2024. Clip-adapter: Better vision-language models with feature adapters. International Journal of Computer Vision 132 2 (2024) 581\u2013595.","DOI":"10.1007\/s11263-023-01891-x"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01067"},{"key":"e_1_3_3_1_11_2","unstructured":"Dongliang Guo Zhixuan Chu and Sheng Li. 2023. Fair Attribute Completion on Graph with Missing Attributes. arxiv:https:\/\/arXiv.org\/abs\/2302.12977\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2302.12977"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611978032.73"},{"key":"e_1_3_3_1_13_2","unstructured":"Dongliang Guo Mengxuan Hu Zihan Guan Junfeng Guo Thomas Hartvigsen and Sheng Li. 2024. Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing. arxiv:https:\/\/arXiv.org\/abs\/2410.18267\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2410.18267"},{"key":"e_1_3_3_1_14_2","unstructured":"Dongliang Guo Mengxuan Hu Zihan Guan Thomas Hartvigsen and Sheng Li. 2025. BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing. arxiv:https:\/\/arXiv.org\/abs\/2505.01343\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2505.01343"},{"key":"e_1_3_3_1_15_2","volume-title":"The IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Rui\u00a0Zhang Changsheng\u00a0Xu Hantao\u00a0Yao,","year":"2023","unstructured":"Changsheng\u00a0Xu Hantao\u00a0Yao, Rui\u00a0Zhang. 2023. Visual-Language Prompt Tuning with Knowledge-guided Context Optimization. In The IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Patrick Helber Benjamin Bischke Andreas Dengel and Damian Borth. 2019. Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 12 7 (2019) 2217\u20132226.","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"e_1_3_3_1_17_2","unstructured":"Mengxuan Hu Hongyi Wu Zihan Guan Ronghang Zhu Dongliang Guo Daiqing Qi and Sheng Li. 2024. No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs Even for Vigilant Users. arxiv:https:\/\/arXiv.org\/abs\/2410.07589\u00a0[cs.IR] https:\/\/arxiv.org\/abs\/2410.07589"},{"key":"e_1_3_3_1_18_2","first-page":"4904","volume-title":"International Conference on Machine Learning","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International Conference on Machine Learning. PMLR, 4904\u20134916."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"e_1_3_3_1_20_2","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:https:\/\/arXiv.org\/abs\/2301.12597 (2023)."},{"key":"e_1_3_3_1_21_2","first-page":"12888","volume-title":"International Conference on Machine Learning","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\u201312900."},{"key":"e_1_3_3_1_22_2","unstructured":"Shuo Li Fang Liu Licheng Jiac Lingling Li Puhua Chen Xu Liu and Wenping Ma. 2025. Prompt-Based Concept Learning for Few-Shot Class-Incremental Learning. IEEE Transactions on Circuits and Systems for Video Technology (2025)."},{"key":"e_1_3_3_1_23_2","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong\u00a0Jae Lee. 2023. Visual Instruction Tuning."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"e_1_3_3_1_25_2","unstructured":"Subhransu Maji Esa Rahtu Juho Kannala Matthew Blaschko and Andrea Vedaldi. 2013. Fine-grained visual classification of aircraft. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1306.5151 (2013)."},{"key":"e_1_3_3_1_26_2","unstructured":"Sachit Menon and Carl Vondrick. 2023. Visual Classification via Description from Large Language Models. ICLR (2023)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_3_1_28_2","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2303.08774\u00a0[cs.CL]"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"e_1_3_3_1_30_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_3_1_31_2","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et\u00a0al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_3_1_32_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et\u00a0al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_34_2","unstructured":"Shuvendu Roy and Ali Etemad. 2023. Consistency-guided prompt learning for vision-language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.01195 (2023)."},{"key":"e_1_3_3_1_35_2","unstructured":"Christoph Schuhmann Richard Vencu Romain Beaumont Robert Kaczmarczyk Clayton Mullis Aarush Katta Theo Coombes Jenia Jitsev and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2111.02114 (2021)."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Tongkai Shi Wei Feng Fanhua Shang Liang Wan et\u00a0al. 2025. Deep Correlated Prompting for Visual Recognition with Missing Modalities. Advances in Neural Information Processing Systems 37 (2025) 67446\u201367466.","DOI":"10.52202\/079017-2153"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01423"},{"key":"e_1_3_3_1_39_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et\u00a0al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.13971 (2023)."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00257"},{"key":"e_1_3_3_1_41_2","unstructured":"Dongsheng Wang Miaoge Li Xinyang Liu MingSheng Xu Bo Chen and Hanwang Zhang. 2023. Tuning Multi-mode Token-level Prompt Alignment across Modalities. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.13847 (2023)."},{"key":"e_1_3_3_1_42_2","unstructured":"Yizhou Wang Dongliang Guo Sheng Li Octavia Camps and Yun Fu. 2024. Explainable Anomaly Detection in Images and Videos: A Survey. arxiv:https:\/\/arXiv.org\/abs\/2302.06670\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2302.06670"},{"key":"e_1_3_3_1_43_2","first-page":"3032","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Wang Zhengbo","year":"2023","unstructured":"Zhengbo Wang, Jian Liang, Ran He, Nan Xu, Zilei Wang, and Tieniu Tan. 2023. Improving zero-shot generalization for clip with synthesized prompts. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 3032\u20133042."},{"key":"e_1_3_3_1_44_2","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Xiao Zehao","year":"2025","unstructured":"Zehao Xiao, Shilin Yan, Jack Hong, Jiayin Cai, Xiaolong Jiang, Yao Hu, Jiayi Shen, Cheems Wang, and Cees G.\u00a0M. Snoek. 2025. DynaPrompt: Dynamic Test-Time Prompt Tuning. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=EFZEdHB3Mp"},{"key":"e_1_3_3_1_45_2","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et\u00a0al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.15115 (2024)."},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Xi Yu Shinjae Yoo and Yuewei Lin. 2025. CLIPCEIL: Domain Generalization through CLIP via Channel rEfinement and Image-text aLignment. Advances in Neural Information Processing Systems 37 (2025) 4267\u20134294.","DOI":"10.52202\/079017-0139"},{"key":"e_1_3_3_1_47_2","unstructured":"Yuhang Zang Wei Li Kaiyang Zhou Chen Huang and Chen\u00a0Change Loy. 2022. Unified vision and language prompt learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.07225 (2022)."},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01228"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"crossref","unstructured":"Kaiyang Zhou Jingkang Yang Chen\u00a0Change Loy and Ziwei Liu. 2022. Learning to Prompt for Vision-Language Models. International Journal of Computer Vision (IJCV) (2022).","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","unstructured":"Beier Zhu Yulei Niu Yucheng Han Yue Wu and Hanwang Zhang. 2022. Prompt-aligned Gradient for Prompt Tuning. 10.48550\/ARXIV.2205.14865","DOI":"10.48550\/ARXIV.2205.14865"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","unstructured":"Ronghang Zhu Dongliang Guo Daiqing Qi Zhixuan Chu Xiang Yu and Sheng Li. 2024. A Survey of Trustworthy Representation Learning Across Domains. ACM Trans. Knowl. Discov. Data 18 7 Article 173 (June 2024) 53\u00a0pages. 10.1145\/3657301","DOI":"10.1145\/3657301"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"Xingyu Zhu Beier Zhu Yi Tan Shuo Wang Yanbin Hao and Hanwang Zhang. 2025. Enhancing zero-shot vision models by label-free prompt distribution learning and bias correcting. Advances in Neural Information Processing Systems 37 (2025) 2001\u20132025.","DOI":"10.52202\/079017-0064"}],"event":{"name":"ICMI '25: International Conference on Multimodal Interaction","location":"Canberra Australia","acronym":"ICMI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 27th International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3716553.3750817","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3716553.3750817","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3716553.3750817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T22:29:42Z","timestamp":1769466582000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716553.3750817"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":53,"alternative-id":["10.1145\/3716553.3750817","10.1145\/3716553"],"URL":"https:\/\/doi.org\/10.1145\/3716553.3750817","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"2025-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}