{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T17:58:31Z","timestamp":1793987911153,"version":"4.8.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754870","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"131-140","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Boosting Single-Domain Generalized Object Detection via Vision-Language Knowledge Interaction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8350-2828","authenticated-orcid":false,"given":"Xiaoran","family":"Xu","sequence":"first","affiliation":[{"name":"School of Advanced Interdisciplinary Sciences, University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0464-8336","authenticated-orcid":false,"given":"Jiangang","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7292-6573","authenticated-orcid":false,"given":"Wenyue","family":"Chong","sequence":"additional","affiliation":[{"name":"School of Advanced Interdisciplinary Sciences, University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1662-7151","authenticated-orcid":false,"given":"Wenhui","family":"Shi","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2782-9013","authenticated-orcid":false,"given":"Shichu","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Advanced Interdisciplinary Sciences, University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9607-3987","authenticated-orcid":false,"given":"Jing","family":"Xing","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8338-8749","authenticated-orcid":false,"given":"Jian","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01141"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01679"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"e_1_3_2_1_5_1","volume-title":"Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552","author":"DeVries Terrance","year":"2017","unstructured":"Terrance DeVries and Graham W Taylor. 2017. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01707"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.330"},{"key":"e_1_3_2_1_9_1","volume-title":"ImageNet-trained CNNs are biased towards texture","author":"Geirhos Robert","year":"1811","unstructured":"Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A Wichmann, and Wieland Brendel. 2018. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231 (2018)."},{"key":"e_1_3_2_1_10_1","volume-title":"Vehicle detection and tracking in adverse weather using a deep learning framework","author":"Hassaballah Mahmoud","year":"2020","unstructured":"Mahmoud Hassaballah, Mourad A Kenk, Khan Muhammad, and Shervin Minaee. 2020. Vehicle detection and tracking in adverse weather using a deep learning framework. IEEE transactions on intelligent transportation systems 22, 7 (2020), 4230--4242."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_12_1","volume-title":"Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261","author":"Hendrycks Dan","year":"2019","unstructured":"Dan Hendrycks and Thomas Dietterich. 2019. Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)."},{"key":"e_1_3_2_1_13_1","volume-title":"Benchmarking neural network robustness to common corruptions and surface variations. arXiv preprint arXiv:1807.01697","author":"Hendrycks Dan","year":"2018","unstructured":"Dan Hendrycks and Thomas G Dietterich. 2018. Benchmarking neural network robustness to common corruptions and surface variations. arXiv preprint arXiv:1807.01697 (2018)."},{"key":"e_1_3_2_1_14_1","volume-title":"Augmix: A simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781","author":"Hendrycks Dan","year":"2019","unstructured":"Dan Hendrycks, Norman Mu, Ekin D Cubuk, Barret Zoph, Justin Gilmer, and Balaji Lakshminarayanan. 2019. Augmix: A simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781 (2019)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00501"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the Asian Conference on Computer Vision. 4223--4244","author":"H\u00fcmmer Christoph","year":"2024","unstructured":"Christoph H\u00fcmmer, Manuel Schwonberg, Liangwei Zhou, Hu Cao, Alois Knoll, and Hanno Gottschalk. 2024. Strong but Simple: A Baseline for Domain Generalized Dense Perception by CLIP-Based Transfer Learning. In Proceedings of the Asian Conference on Computer Vision. 4223--4244."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_18_1","volume-title":"Supervised contrastive learning. Advances in neural information processing systems 33","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, ChenWang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems 33 (2020), 18661--18673."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28076"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01667"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02724"},{"key":"e_1_3_2_1_23_1","volume-title":"Benchmarking robustness in object detection: Autonomous driving when winter is coming. arXiv preprint arXiv:1907.07484","author":"Michaelis Claudio","year":"2019","unstructured":"Claudio Michaelis, Benjamin Mitzkus, Robert Geirhos, Evgenia Rusak, Oliver Bringmann, Alexander S Ecker, Matthias Bethge, and Wieland Brendel. 2019. Benchmarking robustness in object detection: Autonomous driving when winter is coming. arXiv preprint arXiv:1907.07484 (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_36"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00195"},{"key":"e_1_3_2_1_27_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_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"e_1_3_2_1_29_1","first-page":"29935","article-title":"Data augmentation can improve robustness","volume":"34","author":"Rebuffi Sylvestre-Alvise","year":"2021","unstructured":"Sylvestre-Alvise Rebuffi, Sven Gowal, Dan Andrei Calian, Florian Stimberg, Olivia Wiles, and Timothy A Mann. 2021. Data augmentation can improve robustness. Advances in Neural Information Processing Systems 34 (2021), 29935--29948.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_31_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01900"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00727"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01682"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00314"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00901"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916669237"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00092"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Gao Jinling","year":"2024","unstructured":"FanWu, Jinling Gao, Lanqing Hong, XinbingWang, Chenghu Zhou, and Nanyang Ye. 2024. G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 5958--5966."},{"key":"e_1_3_2_1_42_1","volume-title":"PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection. arXiv preprint arXiv:2412.11807","author":"Xu Xiaoran","year":"2024","unstructured":"Xiaoran Xu, Jiangang Yang, Wenhui Shi, Siyuan Ding, Luqing Luo, and Jian Liu. 2024. PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection. arXiv preprint arXiv:2412.11807 (2024)."},{"key":"e_1_3_2_1_43_1","first-page":"9125","article-title":"Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume":"35","author":"Yao Lewei","year":"2022","unstructured":"Lewei Yao, Jianhua Han, Youpeng Wen, Xiaodan Liang, Dan Xu, Wei Zhang, Zhenguo Li, Chunjing Xu, and Hang Xu. 2022. Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection. Advances in Neural Information Processing Systems 35 (2022), 9125--9138.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"e_1_3_2_1_45_1","volume-title":"mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412","author":"Zhang Hongyi","year":"2017","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)."},{"key":"e_1_3_2_1_46_1","first-page":"14435","article-title":"Maximum-entropy adversarial data augmentation for improved generalization and robustness","volume":"33","author":"Zhao Long","year":"2020","unstructured":"Long Zhao, Ting Liu, Xi Peng, and Dimitris Metaxas. 2020. Maximum-entropy adversarial data augmentation for improved generalization and robustness. Advances in Neural Information Processing Systems 33 (2020), 14435--14447.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_31"},{"key":"e_1_3_2_1_48_1","first-page":"4396","article-title":"Domain generalization: A survey","volume":"45","author":"Zhou Kaiyang","year":"2022","unstructured":"Kaiyang Zhou, Ziwei Liu, Yu Qiao, Tao Xiang, and Chen Change Loy. 2022. Domain generalization: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 4 (2022), 4396--4415.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings, Part XXVII 16","author":"Zoph Barret","year":"2020","unstructured":"Barret Zoph, Ekin D Cubuk, Golnaz Ghiasi, Tsung-Yi Lin, Jonathon Shlens, and Quoc V Le. 2020. Learning data augmentation strategies for object detection. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXVII 16. Springer, 566--583."}],"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\/3746027.3754870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:01:20Z","timestamp":1765339280000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754870"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":51,"alternative-id":["10.1145\/3746027.3754870","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754870","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"}}]}}