{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:26:05Z","timestamp":1783099565596,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":63,"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\/3664647.3680710","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"4387-4396","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Training-Free Feature Reconstruction with Sparse Optimization for Vision-Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5831-0170","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology & Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9687-6171","authenticated-orcid":false,"given":"Ke","family":"Yu","sequence":"additional","affiliation":[{"name":"University of California, San Diego, San Diego, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8878-0325","authenticated-orcid":false,"given":"Angelica I.","family":"Aviles-Rivero","sequence":"additional","affiliation":[{"name":"University of Cambridge, Cambridge, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0519-6280","authenticated-orcid":false,"given":"Jiyuan","family":"Jia","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8350-7637","authenticated-orcid":false,"given":"Yushun","family":"Tang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2647-8286","authenticated-orcid":false,"given":"Zhihai","family":"He","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, 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":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_1_2_1","volume-title":"International Conference on Learning Representations.","author":"Chen Guangyi","year":"2023","unstructured":"Guangyi Chen,Weiran Yao, Xiangchen Song, Xinyue Li, Yongming Rao, and Kun Zhang. 2023. PLOT: Prompt learning with optimal transport for vision-language models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00893"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_6_1","volume-title":"Rlprompt: Optimizing discrete text prompts with reinforcement learning. arXiv preprint arXiv:2205.12548","author":"Deng Mingkai","year":"2022","unstructured":"Mingkai Deng, JianyuWang, Cheng-Ping Hsieh, YihanWang, Han Guo, Tianmin Shu, Meng Song, Eric P Xing, and Zhiting Hu. 2022. Rlprompt: Optimizing discrete text prompts with reinforcement learning. arXiv preprint arXiv:2205.12548 (2022)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"e_1_3_2_1_8_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Doersch Carl","year":"2020","unstructured":"Carl Doersch, Ankush Gupta, and Andrew Zisserman. 2020. CrossTransformers: spatially-aware few-shot transfer. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6--12, 2020, virtual."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540094"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01520"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"e_1_3_2_1_12_1","volume-title":"Clip-adapter: Better vision-language models with feature adapters. arXiv preprint arXiv:2110.04544","author":"Gao Peng","year":"2021","unstructured":"Peng Gao, Shijie Geng, Renrui Zhang, Teli Ma, Rongyao Fang, Yongfeng Zhang, Hongsheng Li, and Yu Qiao. 2021. Clip-adapter: Better vision-language models with feature adapters. arXiv preprint arXiv:2110.04544 (2021)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.218"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25152"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"e_1_3_2_1_18_1","volume-title":"Cross Attention Network for Few-shot Classification. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Hou Ruibing","year":"2019","unstructured":"Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan, and Xilin Chen. 2019. Cross Attention Network for Few-shot Classification. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8--14, 2019, Vancouver, BC, Canada. 4005--4016."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548282"},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Machine Learning. 4904--4916","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 visionlanguage representation learning with noisy text supervision. In International Conference on Machine Learning. 4904--4916."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.483"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"e_1_3_2_1_27_1","volume-title":"Faster-Than-Nyquist Symbol-Level Precoding for Wideband Integrated Sensing and Communications. arXiv preprint arXiv:2306.14509","author":"Liao Zihan","year":"2023","unstructured":"Zihan Liao, Fan Liu, Ang Li, and Christos Masouros. 2023. Faster-Than-Nyquist Symbol-Level Precoding for Wideband Integrated Sensing and Communications. arXiv preprint arXiv:2306.14509 (2023)."},{"key":"e_1_3_2_1_28_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 55, 9 (2023), 1--35.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_1_29_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In Advances in Neural Information Processing Systems, Vol. 32."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"e_1_3_2_1_31_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, MatthewBlaschko, and Andrea Vedaldi. 2013. Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)."},{"key":"e_1_3_2_1_32_1","unstructured":"Shu Manli Nie Weili Huang De-An Yu Zhiding Goldstein Tom Anandkumar Anima and Xiao Chaowei. 2022. Test-Time Prompt Tuning for Zero-shot Generalization in Vision-Language Models. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_33_1","volume-title":"Splitting and alternating direction methods. Handbook of numerical analysis 1","author":"Marchuk Guri I","year":"1990","unstructured":"Guri I Marchuk. 1990. Splitting and alternating direction methods. Handbook of numerical analysis 1 (1990), 197--462."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"e_1_3_2_1_36_1","volume-title":"International Conference on Machine Learning.","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."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"e_1_3_2_1_38_1","volume-title":"International Conference on Machine Learning.","author":"Recht Benjamin","year":"2019","unstructured":"Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, and Vaishaal Shankar. 2019. Do imagenet classifiers generalize to imagenet?. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_10"},{"key":"e_1_3_2_1_40_1","volume-title":"Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis. arXiv preprint arXiv:2301.09515","author":"Sauer Axel","year":"2023","unstructured":"Axel Sauer, Tero Karras, Samuli Laine, Andreas Geiger, and Timo Aila. 2023. Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis. arXiv preprint arXiv:2301.09515 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298683"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680678"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222707"},{"key":"e_1_3_2_1_45_1","volume-title":"Neuro-modulated hebbian learning for fully test-time adaptation. arXiv preprint arXiv:2303.00914","author":"Tang Yushun","year":"2023","unstructured":"Yushun Tang, Ce Zhang, Heng Xu, Shuoshuo Chen, Jie Cheng, Luziwei Leng, Qinghai Guo, and Zhihai He. 2023. Neuro-modulated hebbian learning for fully test-time adaptation. arXiv preprint arXiv:2303.00914 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00257"},{"key":"e_1_3_2_1_47_1","volume-title":"Deep-LK for Efficient Adaptive Object Tracking. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018","author":"Wang Chaoyang","year":"2018","unstructured":"Chaoyang Wang, Hamed Kiani Galoogahi, Chen-Hsuan Lin, and Simon Lucey. 2018. Deep-LK for Efficient Adaptive Object Tracking. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia, May 21--25, 2018. 627--634."},{"key":"e_1_3_2_1_48_1","volume-title":"Learning to decompose visual features with latent textual prompts. arXiv preprint arXiv:2210.04287","author":"Wang Feng","year":"2022","unstructured":"Feng Wang, Manling Li, Xudong Lin, Hairong Lv, Alexander G Schwing, and Heng Ji. 2022. Learning to decompose visual features with latent textual prompts. arXiv preprint arXiv:2210.04287 (2022)."},{"key":"e_1_3_2_1_49_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Wang Haohan","year":"2019","unstructured":"Haohan Wang, Songwei Ge, Zachary Lipton, and Eric P Xing. 2019. Learning robust global representations by penalizing local predictive power. In Advances in Neural Information Processing Systems, Vol. 32."},{"key":"e_1_3_2_1_50_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 8012--8021","author":"Tang Luming","year":"2021","unstructured":"DavisWertheimer, Luming Tang, and Bharath Hariharan. 2021. Few-shot classification with feature map reconstruction networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 8012--8021."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"e_1_3_2_1_52_1","volume-title":"Cpt: Colorful prompt tuning for pre-trained vision-language models. arXiv preprint arXiv:2109.11797","author":"Yao Yuan","year":"2021","unstructured":"Yuan Yao, Ao Zhang, Zhengyan Zhang, Zhiyuan Liu, Tat-Seng Chua, and Maosong Sun. 2021. Cpt: Colorful prompt tuning for pre-trained vision-language models. arXiv preprint arXiv:2109.11797 (2021)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547935"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"e_1_3_2_1_57_1","unstructured":"Yi Zhang Ce Zhang Zihan Liao Yushun Tang and Zhihai He. 2023. BDCAdapter: Brownian Distance Covariance for Better Vision-Language Reasoning. In BMVC."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28568"},{"key":"e_1_3_2_1_59_1","volume-title":"A survey of sparse representation: algorithms and applications","author":"Zhang Zheng","year":"2015","unstructured":"Zheng Zhang, Yong Xu, Jian Yang, Xuelong Li, and David Zhang. 2015. A survey of sparse representation: algorithms and applications. IEEE access 3 (2015), 490-- 530."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_62_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16485--16494","author":"Zhou Mingyang","year":"2022","unstructured":"Mingyang Zhou, Licheng Yu, Amanpreet Singh, Mengjiao Wang, Zhou Yu, and Ning Zhang. 2022. Unsupervised vision-and-language pre-training via retrievalbased multi-granular alignment. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16485--16494."},{"key":"e_1_3_2_1_63_1","volume-title":"Not all features matter: Enhancing few-shot clip with adaptive prior refinement. arXiv preprint arXiv:2304.01195","author":"Zhu Xiangyang","year":"2023","unstructured":"Xiangyang Zhu, Renrui Zhang, Bowei He, Aojun Zhou, Dong Wang, Bin Zhao, and Peng Gao. 2023. Not all features matter: Enhancing few-shot clip with adaptive prior refinement. arXiv preprint arXiv:2304.01195 (2023)."}],"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\/3664647.3680710","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:23Z","timestamp":1750291583000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680710"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":63,"alternative-id":["10.1145\/3664647.3680710","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680710","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"}}]}}