{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:16:55Z","timestamp":1792790215272,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","funder":[{"name":"Natural Science Foundation of China","award":["62306241"],"award-info":[{"award-number":["62306241"]}]},{"name":"Innovation Foundation for Doctor Dissertation of Northwestern Polytechnical University","award":["CX2025109"],"award-info":[{"award-number":["CX2025109"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755008","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:47:42Z","timestamp":1761371262000},"page":"3212-3221","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["KAID: Knowledge-Aware Interactive Distillation for Vision-Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9248-2941","authenticated-orcid":false,"given":"Da","family":"Zhang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China and Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5261-4418","authenticated-orcid":false,"given":"Feiyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China and Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6444-0453","authenticated-orcid":false,"given":"Bingyu","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, He Fei, China and Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7666-4020","authenticated-orcid":false,"given":"Zhiyuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6000-8168","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0019-4197","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, China, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"80396","article-title":"Align your prompts: Test-time prompting with distribution alignment for zero-shot generalization","volume":"36","author":"Samadh Jameel Abdul","year":"2023","unstructured":"Jameel Abdul Samadh, Mohammad Hanan Gani, Noor Hussein, Muhammad Uzair Khattak, Muhammad Muzammal Naseer, Fahad Shahbaz Khan, and Salman H Khan. 2023. Align your prompts: Test-time prompting with distribution alignment for zero-shot generalization. Advances in Neural Information Processing Systems, Vol. 36 (2023), 80396-80413.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00505"},{"key":"e_1_3_2_1_3_1","first-page":"446","volume-title":"Switzerland","author":"Bossard Lukas","year":"2014","unstructured":"Lukas Bossard, Matthieu Guillaumin, and Luc Van Gool. 2014. Food-101-mining discriminative components with random forests. In Computer vision-ECCV 2014: 13th European conference, zurich, Switzerland, September 6-12, 2014, proceedings, part VI 13. Springer, 446-461."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"e_1_3_2_1_5_1","volume-title":"European Conference on Computer Vision. Springer, 19-35","author":"Chen Liang","year":"2024","unstructured":"Liang Chen, Haozhe Zhao, Tianyu Liu, Shuai Bai, Junyang Lin, Chang Zhou, and Baobao Chang. 2024b. An image is worth 1\/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models. In European Conference on Computer Vision. Springer, 19-35."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"e_1_3_2_1_7_1","volume-title":"From captions to rewards (carevl): Leveraging large language model experts for enhanced reward modeling in large vision-language models. arXiv preprint arXiv:2503.06260","author":"Dai Muzhi","year":"2025","unstructured":"Muzhi Dai, Jiashuo Sun, Zhiyuan Zhao, Shixuan Liu, Rui Li, Junyu Gao, and Xuelong Li. 2025. From captions to rewards (carevl): Leveraging large language model experts for enhanced reward modeling in large vision-language models. arXiv preprint arXiv:2503.06260 (2025)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00146"},{"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","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"e_1_3_2_1_16_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29153"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00635"},{"key":"e_1_3_2_1_19_1","volume-title":"International conference on machine learning. PMLR, 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 vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904-4916."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_1_23_1","volume-title":"European Conference on Computer Vision. Springer, 143-160","author":"Lan Mengcheng","year":"2024","unstructured":"Mengcheng Lan, Chaofeng Chen, Yiping Ke, Xinjiang Wang, Litong Feng, and Wayne Zhang. 2024. Clearclip: Decomposing clip representations for dense vision-language inference. In European Conference on Computer Vision. Springer, 143-160."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01083"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3350695"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01184"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25236"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680665"},{"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, Matthew Blaschko, and Andrea Vedaldi. 2013. Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01820"},{"key":"e_1_3_2_1_36_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_37_1","volume-title":"International conference on machine learning. PMLR, 5389-5400","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. PMLR, 5389-5400."},{"key":"e_1_3_2_1_38_1","first-page":"14274","article-title":"Test-time prompt tuning for zero-shot generalization in vision-language models","volume":"35","author":"Shu Manli","year":"2022","unstructured":"Manli Shu, Weili Nie, De-An Huang, Zhiding Yu, Tom Goldstein, Anima Anandkumar, and Chaowei Xiao. 2022. Test-time prompt tuning for zero-shot generalization in vision-language models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 14274-14289.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_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_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"e_1_3_2_1_41_1","volume-title":"Learning robust global representations by penalizing local predictive power. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00173"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28347"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2924811"},{"key":"e_1_3_2_1_46_1","volume-title":"European Conference on Computer Vision. Springer, 304-321","author":"Wu Ge","year":"2024","unstructured":"Ge Wu, Xin Zhang, Zheng Li, Zhaowei Chen, Jiajun Liang, Jian Yang, and Xiang Li. 2024. Cascade prompt learning for vision-language model adaptation. In European Conference on Computer Vision. Springer, 304-321."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02008"},{"key":"e_1_3_2_1_48_1","first-page":"3485","article-title":"Sun database: Large-scale scene recognition from abbey to zoo. In 2010 IEEE computer society conference on computer vision and pattern recognition","author":"Xiao Jianxiong","year":"2010","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 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, 3485-3492.","journal-title":"IEEE"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20211"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01510"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_31"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3257878"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3483775"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02592"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21431"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:18:24Z","timestamp":1765307904000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":59,"alternative-id":["10.1145\/3746027.3755008","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755008","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"}}]}}