{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:41:44Z","timestamp":1777653704644,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M762480"],"award-info":[{"award-number":["2024M762480"]}],"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":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730108","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:38:52Z","timestamp":1752457132000},"page":"864-873","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Unified Category and Style Generalization for Instance-Level Sketch Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6834-6137","authenticated-orcid":false,"given":"Zechao","family":"Hu","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8190-1438","authenticated-orcid":false,"given":"Zhengwei","family":"Yang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1758-5936","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2125-9041","authenticated-orcid":false,"given":"Yixiong","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6776-2040","authenticated-orcid":false,"given":"Fengbin","family":"Zhu","sequence":"additional","affiliation":[{"name":"NExT++ School of Computing, National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3846-9157","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00423"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00107"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_10"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00980"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00228"},{"key":"e_1_3_2_2_7_1","volume-title":"Int. Conf. Learn. Represent.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Int. Conf. Learn. Represent."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00523"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01637"},{"key":"e_1_3_2_2_10_1","volume-title":"Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 43-54","author":"Ghita Alexandru","year":"2024","unstructured":"Alexandru Ghita, and Radu Tudor Ionescu. 2024. A New Loss for Image Retrieval: Class Anchor Margin. In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 43-54."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080681"},{"key":"e_1_3_2_2_12_1","first-page":"22479","article-title":"Variational interaction information maximization for cross-domain disentanglement","volume":"33","author":"Hwang HyeongJoo","year":"2020","unstructured":"HyeongJoo Hwang, Geon-Hyeong Kim, Seunghoon Hong, and Kee-Eung Kim. 2020. Variational interaction information maximization for cross-domain disentanglement. Advances in Neural Information Processing Systems, Vol. 33 (2020), 22479-22491.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_2_14_1","volume-title":"Jamie Ryan Kiros.","author":"Geoffrey","year":"2016","unstructured":"Geoffrey E. Hinton Jimmy Lei Ba, Jamie Ryan Kiros. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01595"},{"key":"e_1_3_2_2_16_1","volume-title":"Int. Conf. Learn. Represent.","author":"Kumar Ananya","year":"2022","unstructured":"Ananya Kumar, Aditi Raghunathan, Robbie Jones, Tengyu Ma, and Percy Liang. 2022. Fine-tuning can distort pretrained features and underperform out-of-distribution. In Int. Conf. Learn. Represent."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02236"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.247"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00376"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681233"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00555"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00077"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.46"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01036"},{"key":"e_1_3_2_2_26_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. In 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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning. PMLR, 8748-8763."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00271"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00664"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00731"},{"key":"e_1_3_2_2_30_1","volume-title":"Yongxin Yang, Tao Xiang, and Yi-Zhe Song.","author":"Sain Aneeshan","year":"2020","unstructured":"Aneeshan Sain, Ayan Kumar Bhunia, Yongxin Yang, Tao Xiang, and Yi-Zhe Song. 2020. Cross-modal hierarchical modelling for fine-grained sketch based image retrieval. arXiv preprint arXiv:2007.15103 (2020)."},{"key":"e_1_3_2_2_31_1","volume-title":"StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval. In IEEE Conf. Comput. Vis. Pattern Recog., 8504-8513","author":"Sain Aneeshan","year":"2021","unstructured":"Aneeshan Sain, Ayan Kumar Bhunia, Yongxin Yang, Tao Xiang, and Yi-Zhe Song. 2021. StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval. In IEEE Conf. Comput. Vis. Pattern Recog., 8504-8513."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925954"},{"key":"e_1_3_2_2_33_1","volume-title":"Generalizing across domains via cross-gradient training. arXiv preprint arXiv:1804.10745","author":"Shankar Shiv","year":"2018","unstructured":"Shiv Shankar, Vihari Piratla, Soumen Chakrabarti, Siddhartha Chaudhuri, Preethi Jyothi, and Sunita Sarawagi. 2018. Generalizing across domains via cross-gradient training. arXiv preprint arXiv:1804.10745 (2018)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.592"},{"key":"e_1_3_2_2_35_1","volume-title":"How do we generalize? Neurons, behavior, data analysis and theory","author":"Taylor Jessica Elizabeth","year":"2021","unstructured":"Jessica Elizabeth Taylor, Aurelio Cortese, Helen C Barron, Xiaochuan Pan, Masamichi Sakagami, and Dagmar Zeithamova. 2021. How do we generalize? Neurons, behavior, data analysis and theory, Vol. 1 (2021)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20136"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3123315"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548382"},{"key":"e_1_3_2_2_39_1","volume-title":"Domain-smoothing network for zero-shot sketch-based image retrieval. arXiv preprint arXiv:2106.11841","author":"Wang Zhipeng","year":"2021","unstructured":"Zhipeng Wang, Hao Wang, Jiexi Yan, Aming Wu, and Cheng Deng. 2021b. Domain-smoothing network for zero-shot sketch-based image retrieval. arXiv preprint arXiv:2106.11841 (2021)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.31234\/osf.io\/6uz9q"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_19"},{"key":"e_1_3_2_2_42_1","volume-title":"Sketch Me That Shoe. In IEEE Conf. Comput. Vis. Pattern Recog., 799-807","author":"Yu Qian","year":"2016","unstructured":"Qian Yu, Feng Liu, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, and Chen Change Loy. 2016. Sketch Me That Shoe. In IEEE Conf. Comput. Vis. Pattern Recog., 799-807."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6993"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:06:49Z","timestamp":1755864409000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730108"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":45,"alternative-id":["10.1145\/3726302.3730108","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730108","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}