{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:48:51Z","timestamp":1777873731746,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2232048, CNS-2204445"],"award-info":[{"award-number":["CNS-2232048, CNS-2204445"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3736911","type":"proceedings-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T13:30:13Z","timestamp":1754055013000},"page":"37-46","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["DiSa: Directional Saliency-Aware Prompt Learning for Generalizable Vision-Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6881-3671","authenticated-orcid":false,"given":"Niloufar","family":"Alipour Talemi","sequence":"first","affiliation":[{"name":"Clemson University, Clemson, SC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8338-9987","authenticated-orcid":false,"given":"Hossein","family":"Kashiani","sequence":"additional","affiliation":[{"name":"Clemson University, Clemson, SC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1847-400X","authenticated-orcid":false,"given":"Hossein R.","family":"Nowdeh","sequence":"additional","affiliation":[{"name":"Clemson University, Clemson, SC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2315-1173","authenticated-orcid":false,"given":"Fatemeh","family":"Afghah","sequence":"additional","affiliation":[{"name":"Clemson University, Clemson, SC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_14"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02225"},{"key":"e_1_3_2_2_4_1","volume-title":"PLOT: Prompt learning with optimal transport for vision-language models. arXiv preprint arXiv:2210.01253(2022).","author":"Chen Guangyi","year":"2022","unstructured":"Guangyi Chen, Weiran Yao, Xiangchen Song, Xinyue Li, Yongming Rao, and Kun Zhang. 2022. PLOT: Prompt learning with optimal transport for vision-language models. arXiv preprint arXiv:2210.01253(2022)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1034"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01398"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01078"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"e_1_3_2_2_17_1","first-page":"29262","article-title":"Patching open-vocabulary models by interpolating weights","volume":"35","author":"Ilharco Gabriel","year":"2022","unstructured":"Gabriel Ilharco, Mitchell Wortsman, Samir Yitzhak Gadre, Shuran Song, Hannaneh Hajishirzi, Simon Kornblith, Ali Farhadi, and Ludwig Schmidt. 2022. Patching open-vocabulary models by interpolating weights. Advances in Neural Information Processing Systems, Vol. 35 (2022), 29262-29277.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_18_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_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"e_1_3_2_2_21_1","unstructured":"Konwoo Kim Michael Laskin Igor Mordatch and Deepak Pathak. 2021. How to adapt your large-scale vision-and-language model. (2021)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_2_23_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101(2017)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"e_1_3_2_2_25_1","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_26_1","first-page":"12283","article-title":"I2DFormer: Learning image to document attention for zero-shot image classification","volume":"35","author":"Naeem Muhammad Ferjad","year":"2022","unstructured":"Muhammad Ferjad Naeem, Yongqin Xian, Luc V Gool, and Federico Tombari. 2022. I2DFormer: Learning image to document attention for zero-shot image classification. Advances in Neural Information Processing Systems, Vol. 35 (2022), 12283-12294.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"e_1_3_2_2_29_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_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"e_1_3_2_2_32_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_2_33_1","unstructured":"Shuvendu Roy and Ali Etemad. 2023. Consistency-guided prompt learning for vision-language models. arXiv preprint arXiv:2306.01195(2023)."},{"key":"e_1_3_2_2_34_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_2_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_2_36_1","volume-title":"Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Models. In 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision. IEEE, 6207-6216","author":"Talemi Niloufar Alipour","year":"2025","unstructured":"Niloufar Alipour Talemi, Hossein Kashiani, and Fatemeh Afghah. 2025. Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Models. In 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision. IEEE, 6207-6216."},{"key":"e_1_3_2_2_37_1","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli Maria","year":"2021","unstructured":"Maria Tsimpoukelli, Jacob L Menick, Serkan Cabi, SM Eslami, Oriol Vinyals, and Felix Hill. 2021. Multimodal few-shot learning with frozen language models. Advances in Neural Information Processing Systems, Vol. 34 (2021), 200-212.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_38_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. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02249"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Yongjin Yang Jongwoo Ko and Se-Young Yun. 2023. Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language Models. arXiv preprint arXiv:2311.15569(2023).","DOI":"10.18653\/v1\/2024.emnlp-main.124"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02212"},{"key":"e_1_3_2_2_43_1","volume-title":"Filip: Fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783(2021).","author":"Yao Lewei","year":"2021","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. 2021. Filip: Fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783(2021)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3248583"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3736911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:17:28Z","timestamp":1777573048000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3736911"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":46,"alternative-id":["10.1145\/3711896.3736911","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3736911","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}