{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:17:11Z","timestamp":1750220231146,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China (NSFC)","award":["61922015, 61773071, U19B2036"],"award-info":[{"award-number":["61922015, 61773071, U19B2036"]}]},{"name":"National Key R&D Program of China","award":["2019YFF0303300,Subject II No. 2019YFF0303302, and 2020AAA0105200"],"award-info":[{"award-number":["2019YFF0303300,Subject II No. 2019YFF0303302, and 2020AAA0105200"]}]},{"name":"Beijing Natural Science Foundation Project","award":["Z200002"],"award-info":[{"award-number":["Z200002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1145\/3469877.3490579","type":"proceedings-article","created":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T18:24:29Z","timestamp":1641839069000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-layer Navigation Convolutional Neural Network for Fine-grained Visual Classification"],"prefix":"10.1145","author":[{"given":"Chenyu","family":"Guo","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyang","family":"Xie","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kongming","family":"Liang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian","family":"Sun","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China and Beijing Academy of Artificial Intelligence, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,1,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.47"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2020.2973812"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01131"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Dongliang Chang Yixiao Zheng Zhanyu Ma Ruoyi Du and Kongming Liang. 2021. Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features. arXiv preprint arXiv:2102.00367(2021).  Dongliang Chang Yixiao Zheng Zhanyu Ma Ruoyi Du and Kongming Liang. 2021. Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features. arXiv preprint arXiv:2102.00367(2021).","DOI":"10.1109\/ICME51207.2021.9428148"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"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\/tip.2021.3055617"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6712"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.132"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5842"},{"key":"e_1_3_2_1_15_1","unstructured":"Max Jaderberg Karen Simonyan Andrew Zisserman and Koray Kavukcuoglu. 2015. Spatial transformer networks. arXiv preprint arXiv:1506.02025(2015).  Max Jaderberg Karen Simonyan Andrew Zisserman and Koray Kavukcuoglu. 2015. Spatial transformer networks. arXiv preprint arXiv:1506.02025(2015)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2899972"},{"key":"e_1_3_2_1_21_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).  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_1_22_1","volume-title":"Bam: Bottleneck attention module. arXiv preprint arXiv:1807.06514(2018).","author":"Park Jongchan","year":"2018","unstructured":"Jongchan Park , Sanghyun Woo , Joon-Young Lee , and In\u00a0So Kweon . 2018 . Bam: Bottleneck attention module. arXiv preprint arXiv:1807.06514(2018). Jongchan Park, Sanghyun Woo, Joon-Young Lee, and In\u00a0So Kweon. 2018. Bam: Bottleneck attention module. arXiv preprint arXiv:1807.06514(2018)."},{"key":"e_1_3_2_1_23_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703(2019).","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke , Sam Gross , Francisco Massa , Adam Lerer , James Bradbury , Gregory Chanan , Trevor Killeen , Zeming Lin , Natalia Gimelshein , Luca Antiga , 2019 . Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703(2019). Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703(2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_49"},{"key":"e_1_3_2_1_25_1","unstructured":"Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The caltech-ucsd birds-200-2011 dataset. (2011).  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_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00436"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-7538-0"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 842\u2013850","author":"Xiao Tianjun","year":"2015","unstructured":"Tianjun Xiao , Yichong Xu , Kuiyuan Yang , Jiaxing Zhang , Yuxin Peng , and Zheng Zhang . 2015 . The application of two-level attention models in deep convolutional neural network for fine-grained image classification . In Proceedings of the IEEE conference on computer vision and pattern recognition. 842\u2013850 . Tianjun Xiao, Yichong Xu, Kuiyuan Yang, Jiaxing Zhang, Yuxin Peng, and Zheng Zhang. 2015. The application of two-level attention models in deep convolutional neural network for fine-grained image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition. 842\u2013850."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Tian Zhang Dongliang Chang Zhanyu Ma and Jun Guo. 2021. Progressive Co-Attention Network for Fine-grained Visual Classification. arXiv preprint arXiv:2101.08527(2021).  Tian Zhang Dongliang Chang Zhanyu Ma and Jun Guo. 2021. Progressive Co-Attention Network for Fine-grained Visual Classification. arXiv preprint arXiv:2101.08527(2021).","DOI":"10.1109\/VCIP53242.2021.9675376"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2531289"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.557"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"}],"event":{"name":"MMAsia '21: ACM Multimedia Asia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Gold Coast Australia","acronym":"MMAsia '21"},"container-title":["ACM Multimedia Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469877.3490579","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3469877.3490579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:16Z","timestamp":1750188616000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469877.3490579"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":34,"alternative-id":["10.1145\/3469877.3490579","10.1145\/3469877"],"URL":"https:\/\/doi.org\/10.1145\/3469877.3490579","relation":{},"subject":[],"published":{"date-parts":[[2021,12]]},"assertion":[{"value":"2022-01-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}