{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T08:01:31Z","timestamp":1777104091529,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":54,"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"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20389,62176139"],"award-info":[{"award-number":["U23A20389,62176139"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Scholars Program of Shandong University"},{"name":"Shandong Excellent Young Scientists Fund (Oversea?","award":["2024HWYQ-027"],"award-info":[{"award-number":["2024HWYQ-027"]}]},{"name":"Fundamental Research Funds of Shandong University"},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2023QF124"],"award-info":[{"award-number":["ZR2023QF124"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680589","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"8043-8052","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Hypergraph-guided Intra- and Inter-category Relation Modeling for Fine-grained Visual Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7485-6511","authenticated-orcid":false,"given":"Lu","family":"Chen","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan, Shandong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3707-1761","authenticated-orcid":false,"given":"Qiangchang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, Shandong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5094-2874","authenticated-orcid":false,"given":"Zhaohui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, Shandong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8465-1294","authenticated-orcid":false,"given":"Yilong","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, Shandong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Quantifying attention flow in transformers. arXiv preprint arXiv:2005.00928","author":"Abnar Samira","year":"2020","unstructured":"Samira Abnar and Willem Zuidema. 2020. Quantifying attention flow in transformers. arXiv preprint arXiv:2005.00928 (2020)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605776"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27834"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16176"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205215"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00432"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181492"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"e_1_3_2_1_10_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126668"},{"key":"e_1_3_2_1_13_1","volume-title":"Maximum-entropy fine grained classification. Advances in neural information processing systems 31","author":"Dubey Abhimanyu","year":"2018","unstructured":"Abhimanyu Dubey, Otkrist Gupta, Ramesh Raskar, and Nikhil Naik. 2018. Maximum-entropy fine grained classification. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00082"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00204"},{"key":"e_1_3_2_1_17_1","volume-title":"Inductive representation learning on large graphs. Advances in neural information processing systems 30","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01820"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475561"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Jianwen Jiang Yuxuan Wei Yifan Feng Jingxuan Cao and Yue Gao. 2019. Dynamic hypergraph neural networks.. In IJCAI. 2635--2641.","DOI":"10.24963\/ijcai.2019\/366"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28034"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 29th ACM International Conference on Multimedia. 5273--5280","author":"Li Guangjun","year":"2021","unstructured":"Guangjun Li, Yongxiong Wang, and Fengting Zhu. 2021. Multi-branch channelwise enhancement network for fine-grained visual recognition. In Proceedings of the 29th ACM International Conference on Multimedia. 5273--5280."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774041"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_4"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548308"},{"key":"e_1_3_2_1_31_1","volume-title":"Fixing the train-test resolution discrepancy. Advances in neural information processing systems 32","author":"Touvron Hugo","year":"2019","unstructured":"Hugo Touvron, Andrea Vedaldi, Matthijs Douze, and Herv\u00e9 J\u00e9gou. 2019. Fixing the train-test resolution discrepancy. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"e_1_3_2_1_34_1","unstructured":"Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The caltech-ucsd birds-200-2011 dataset. (2011)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612303"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01873-z"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00436"},{"key":"e_1_3_2_1_39_1","volume-title":"Jianxin Wu, Yuxin Peng, Jinhui Tang, Jian Yang, and Serge Belongie.","author":"Wei Xiu-Shen","year":"2021","unstructured":"Xiu-Shen Wei, Yi-Zhe Song, Oisin Mac Aodha, Jianxin Wu, Yuxin Peng, Jinhui Tang, Jian Yang, and Serge Belongie. 2021. Fine-grained image analysis with deep learning: A survey. IEEE transactions on pattern analysis and machine intelligence 44, 12 (2021), 8927--8948."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_33"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3244340"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_35"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3117064"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00842"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747591"},{"key":"e_1_3_2_1_47_1","volume-title":"Vit-fod: A vision transformer based fine-grained object discriminator. arXiv preprint arXiv:2203.12816","author":"Zhang Zi-Chao","year":"2022","unstructured":"Zi-Chao Zhang, Zhen-Duo Chen, Yongxin Wang, Xin Luo, and Xin-Shun Xu. 2022. Vit-fod: A vision transformer based fine-grained object discriminator. arXiv preprint arXiv:2203.12816 (2022)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612104"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3126490"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01483"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4692--4702","author":"Zhu Haowei","year":"2022","unstructured":"Haowei Zhu, Wenjing Ke, Dong Li, Ji Liu, Lu Tian, and Yi Shan. 2022. Dual cross-attention learning for fine-grained visual categorization and object reidentification. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4692--4702."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"}],"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\/3664647.3680589","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680589"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":54,"alternative-id":["10.1145\/3664647.3680589","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680589","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"}}]}}