{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:06Z","timestamp":1750309506934,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,6]]},"DOI":"10.1145\/3709026.3709034","type":"proceedings-article","created":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T10:05:41Z","timestamp":1739613941000},"page":"105-111","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-level Attention-enhanced Learning for Fine-Grained Visual Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9687-6556","authenticated-orcid":false,"given":"Kaifeng","family":"Ding","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology(School of Artificial Intelligence), Zhejiang Normal University, Jinhua, ZheJiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2998-5101","authenticated-orcid":false,"given":"Caolin","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology(School of Artificial Intelligence), Zhejiang Normal University, Jinhua, ZheJiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6675-9074","authenticated-orcid":false,"given":"Chengzhuan","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology(School of Artificial Intelligence), Zhejiang Normal University, Jinhua, ZheJiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5271-9215","authenticated-orcid":false,"given":"Zhonglong","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology(School of Artificial Intelligence), Zhejiang Normal University, Jinhua, ZheJiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,2,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Steve Branson Grant Van\u00a0Horn Serge Belongie and Pietro Perona. 2014. Bird species categorization using pose normalized deep convolutional nets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1406.2952 (2014).","DOI":"10.5244\/C.28.87"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.47"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00232"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00432"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00315"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_3_1_13_2","unstructured":"Ranran Huang Yu Wang and Huazhong Yang. 2022. Cross-layer attention network for fine-grained visual categorization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.08784 (2022)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00066"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.132"},{"key":"e_1_3_3_1_16_2","unstructured":"Ruyi Ji Jiaying Li Libo Zhang Jing Liu and Yanjun Wu. 2023. Dual transformer with multi-grained assembly for fine-grained visual classification. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.743"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33676-9_5"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.145"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Hai Liu Cheng Zhang Yongjian Deng Bochen Xie Tingting Liu Zhaoli Zhang and You-Fu Li. 2023. TransIFC: invariant cues-aware feature concentration learning for efficient fine-grained bird image classification. IEEE Transactions on Multimedia (2023).","DOI":"10.1109\/TMM.2023.3238548"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_13"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Kangjun Liu Ke Chen and Kui Jia. 2022. Convolutional fine-grained classification with self-Supervised target relation regularization. IEEE Transactions on Image Processing 31 (2022) 5570\u20135584.","DOI":"10.1109\/TIP.2022.3197931"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Xinda Liu Lili Wang and Xiaoguang Han. 2022. Transformer with peak suppression and knowledge guidance for fine-grained image recognition. Neurocomputing 492 (2022) 137\u2013149.","DOI":"10.1016\/j.neucom.2022.04.037"},{"key":"e_1_3_3_1_28_2","unstructured":"Subhransu Maji Esa Rahtu Juho Kannala Matthew Blaschko and Andrea Vedaldi. 2013. Fine-grained visual classification of aircraft. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1306.5151 (2013)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et\u00a0al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision 115 (2015) 211\u2013252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_3_1_30_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1409.1556 (2014)."},{"key":"e_1_3_3_1_31_2","unstructured":"Yue Song Nicu Sebe and Wei Wang. 2022. On the eigenvalues of global covariance pooling for fine-grained visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 3 (2022) 3554\u20133566."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6882"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02273"},{"key":"e_1_3_3_1_34_2","volume-title":"The Caltech-UCSD birds-200-2011 dataset","author":"Wah C.","year":"2011","unstructured":"C. Wah, S. Branson, P. Welinder, P. Perona, and S. Belongie. 2011. The Caltech-UCSD birds-200-2011 dataset. Technical Report CNS-TR-2011-001. California Institute of Technology."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16384"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00977"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Xiu-Shen Wei Jian-Hao Luo Jianxin Wu and Zhi-Hua Zhou. 2017. Selective convolutional descriptor aggregation for fine-grained image retrieval. IEEE transactions on image processing 26 6 (2017) 2868\u20132881.","DOI":"10.1109\/TIP.2017.2688133"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.5555\/2586117.2587186"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Qin Xu Jiahui Wang Bo Jiang and Bin Luo. 2023. Fine-grained visual classification via internal ensemble learning transformer. IEEE Transactions on Multimedia (2023).","DOI":"10.1109\/TMM.2023.3244340"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00725"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_35"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67832-6_12"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00144"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Yifan Zhao Jia Li Xiaowu Chen and Yonghong Tian. 2021. Part-Guided Relational Transformers for Fine-Grained Visual Recognition. IEEE Transactions on Image Processing 30 (2021) 9470\u20139481.","DOI":"10.1109\/TIP.2021.3126490"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01483"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00156"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"}],"event":{"name":"CSAI 2024: 2024 8th International Conference on Computer Science and Artificial Intelligence (CSAI)","acronym":"CSAI 2024","location":"Beijing China"},"container-title":["Proceedings of the 2024 8th International Conference on Computer Science and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709026.3709034","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3709026.3709034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:55Z","timestamp":1750295875000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709026.3709034"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,6]]},"references-count":48,"alternative-id":["10.1145\/3709026.3709034","10.1145\/3709026"],"URL":"https:\/\/doi.org\/10.1145\/3709026.3709034","relation":{},"subject":[],"published":{"date-parts":[[2024,12,6]]},"assertion":[{"value":"2025-02-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}