{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T17:18:21Z","timestamp":1790961501666,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":31,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681485","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"8672-8680","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Adaptive Multi-Modality Prompt Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4687-3475","authenticated-orcid":false,"given":"Zongqian","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9229-5188","authenticated-orcid":false,"given":"Yujing","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangxi Key Lab of Multisource Information Mining and Security, Guangxi Normal University, Guilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8815-5542","authenticated-orcid":false,"given":"Mengmeng","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3121-9852","authenticated-orcid":false,"given":"Ping","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6840-0578","authenticated-orcid":false,"given":"Xiaofeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China & Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_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_2_2_1","doi-asserted-by":"crossref","unstructured":"Lukas Bossard Matthieu Guillaumin and Luc Van Gool. 2014. Food-101--mining discriminative components with random forests. In ECCV. 446--461.","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings of the 29th conference on Information communications. 1181--1189","author":"Cheng Siyao","year":"2010","unstructured":"Siyao Cheng, Jianzhong Li, Qianqian Ren, and Lei Yu. 2010. Bernoulli sampling based (varepsilon, \u03b4)-approximate aggregation in large-scale sensor networks. In Proceedings of the 29th conference on Information communications. 1181--1189."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Mircea Cimpoi Subhransu Maji Iasonas Kokkinos Sammy Mohamed and Andrea Vedaldi. 2014. Describing textures in the wild. In CVPR. 3606--3613.","DOI":"10.1109\/CVPR.2014.461"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-842X.1991.tb00424.x"},{"key":"e_1_3_2_2_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_2_7_1","volume-title":"Dropmessage: Unifying random dropping for graph neural networks. In AAAI. 4267--4275.","author":"Fang Taoran","year":"2023","unstructured":"Taoran Fang, Zhiqing Xiao, Chunping Wang, Jiarong Xu, Xuan Yang, and Yang Yang. 2023. Dropmessage: Unifying random dropping for graph neural networks. In AAAI. 4267--4275."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1931.10503148"},{"key":"e_1_3_2_2_10_1","unstructured":"Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Doll\u00e1r and Ross Girshick. 2022. Masked autoencoders are scalable vision learners. In CVPR. 16000--16009."},{"key":"e_1_3_2_2_11_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Menglin Jia Luming Tang Bor-Chun Chen Claire Cardie Serge Belongie Bharath Hariharan and Ser-Nam Lim. 2022. Visual prompt tuning. In ECCV. 709--727.","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Muhammad Uzair khattak Hanoona Rasheed Muhammad Maaz Salman Khan and Fahad Shahbaz Khan. 2023. MaPLe: Multi-modal Prompt Learning. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"e_1_3_2_2_15_1","volume-title":"Few-shot Adaptation of Multi-modal Foundation Models: A Survey. arXiv preprint arXiv:2401.01736","author":"Liu Fan","year":"2024","unstructured":"Fan Liu, Tianshu Zhang, Wenwen Dai, Wenwen Cai, Xiaocong Zhou, and Delong Chen. 2024. Few-shot Adaptation of Multi-modal Foundation Models: A Survey. arXiv preprint arXiv:2401.01736 (2024)."},{"key":"e_1_3_2_2_16_1","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu Pengfei","year":"2023","unstructured":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surveys, Vol. 55, 9 (2023), 1--35.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_2_17_1","volume-title":"Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151","author":"Maji Subhransu","year":"2013","unstructured":"Subhransu Maji, Esa Rahtu, Juho Kannala, Matthew Blaschko, and Andrea Vedaldi. 2013. Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Omkar M Parkhi Andrea Vedaldi Andrew Zisserman and CV Jawahar. 2012. Cats and dogs. In CVPR. 3498--3505.","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"e_1_3_2_2_20_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","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 ICML. 8748--8763."},{"key":"e_1_3_2_2_21_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. A dataset of 101 human action classes from videos in the wild. Center for Research in Computer Vision, Vol. 2, 11 (2012)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28311"},{"key":"e_1_3_2_2_23_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NeurIPS."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"Yongqin Xian Bernt Schiele and Zeynep Akata. 2017. Zero-shot learning-the good the bad and the ugly. In CVPR. 4582--4591.","DOI":"10.1109\/CVPR.2017.328"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Jianxiong Xiao James Hays Krista A Ehinger Aude Oliva and Antonio Torralba. 2010. Sun database: Large-scale scene recognition from abbey to zoo. In CVPR. 3485--3492.","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"e_1_3_2_2_26_1","volume-title":"Dual modality prompt tuning for vision-language pre-trained model","author":"Xing Yinghui","year":"2023","unstructured":"Yinghui Xing, Qirui Wu, De Cheng, Shizhou Zhang, Guoqiang Liang, Peng Wang, and Yanning Zhang. 2023. Dual modality prompt tuning for vision-language pre-trained model. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Jiawei Yao Qi Qian and Juhua Hu. 2024. Multi-modal proxy learning towards personalized visual multiple clustering. In CVPR. 14066--14075.","DOI":"10.1109\/CVPR52733.2024.01334"},{"key":"e_1_3_2_2_28_1","volume-title":"Vision-language models for vision tasks: A survey. arXiv preprint arXiv:2304.00685","author":"Zhang Jingyi","year":"2023","unstructured":"Jingyi Zhang, Jiaxing Huang, Sheng Jin, and Shijian Lu. 2023. Vision-language models for vision tasks: A survey. arXiv preprint arXiv:2304.00685 (2023)."},{"key":"e_1_3_2_2_29_1","volume-title":"Chen Change Loy, and Ziwei Liu","author":"Zhou Kaiyang","year":"2022","unstructured":"Kaiyang Zhou, Jingkang Yang, Chen Change Loy, and Ziwei Liu. 2022. Conditional Prompt Learning for Vision-Language Models. In CVPR."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_2_31_1","volume-title":"Chen Change Loy, and Ziwei Liu","author":"Zhou Kaiyang","year":"2022","unstructured":"Kaiyang Zhou, Jingkang Yang, Chen Change Loy, and Ziwei Liu. 2022. Learning to Prompt for Vision-Language Models. International Journal of Computer Vision (2022)."}],"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\/3664647.3681485","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:47Z","timestamp":1750294667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681485"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":31,"alternative-id":["10.1145\/3664647.3681485","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681485","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"}}]}}