{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:40:05Z","timestamp":1769632805539,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T00:00:00Z","timestamp":1670544000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Jiangxi Natural Science Foundation","award":["20202BABL202014"],"award-info":[{"award-number":["20202BABL202014"]}]},{"name":"National Natural Science Foundation of China-Liaoning Joint Fundin part by the National Natural Science Foundation of China","award":["62261026"],"award-info":[{"award-number":["62261026"]}]},{"DOI":"10.13039\/100017052","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62061019"],"award-info":[{"award-number":["62061019"]}],"id":[{"id":"10.13039\/100017052","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangxi Education Department","award":["GJJ201107"],"award-info":[{"award-number":["GJJ201107"]}]},{"name":"System Control and Information Processing, Ministry of Education","award":["Scip202106"],"award-info":[{"award-number":["Scip202106"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,12,9]]},"DOI":"10.1145\/3577530.3577586","type":"proceedings-article","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T22:13:24Z","timestamp":1680214404000},"page":"94-99","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Attention-based Multi-scale ViT Fine-grained Visual Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8009-530X","authenticated-orcid":false,"given":"Rujia","family":"Li","sequence":"first","affiliation":[{"name":"Graduate School, Jiangxi Science and Technology Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6957-8607","authenticated-orcid":false,"given":"Junya","family":"Liu","sequence":"additional","affiliation":[{"name":"Foreign Languages College, Jiangxi Science and Technology Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0785-9382","authenticated-orcid":false,"given":"Zhen","family":"Yang","sequence":"additional","affiliation":[{"name":"Graduate School, Jiangxi Science and Technology Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5405-9890","authenticated-orcid":false,"given":"Xin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Graduate School, Jiangxi Science and Technology Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5683-802X","authenticated-orcid":false,"given":"Zhijian","family":"Yin","sequence":"additional","affiliation":[{"name":"Graduate School, Jiangxi Science and Technology Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,3,30]]},"reference":[{"issue":"4","key":"e_1_3_2_1_1_1","first-page":"640","volume":"39","author":"Long J","year":"2015","unstructured":"Long J , Shelhamer E , Darrell T . Fully Convolutional Networks for Semantic Segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015 , 39 ( 4 ): 640 - 651 . Long J , Shelhamer E , Darrell T . Fully Convolutional Networks for Semantic Segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(4):640-651.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2601099"},{"key":"e_1_3_2_1_3_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale[C]\/\/ International Conference on Learning Representations","author":"Dosovitskiy A","year":"2021","unstructured":"Dosovitskiy A , Beyer L , Kolesnikov A , An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale[C]\/\/ International Conference on Learning Representations . 2021 . Dosovitskiy A , Beyer L , Kolesnikov A , An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale[C]\/\/ International Conference on Learning Representations. 2021."},{"key":"e_1_3_2_1_4_1","volume-title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers[C]\/\/ Computer Vision and Pattern Recognition","author":"Zheng S","year":"2021","unstructured":"Zheng S , Lu J , Zhao H , Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers[C]\/\/ Computer Vision and Pattern Recognition . IEEE , 2021 . Zheng S , Lu J , Zhao H , Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers[C]\/\/ Computer Vision and Pattern Recognition. IEEE, 2021."},{"key":"e_1_3_2_1_5_1","volume-title":"The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification[J]","author":"Xiao T","year":"2014","unstructured":"Xiao T , Xu Y , Yang K , The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification[J] . IEEE , 2014 . Xiao T , Xu Y , Yang K , The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification[J]. IEEE, 2014."},{"key":"e_1_3_2_1_6_1","volume-title":"Advances in Neural Information Processing Systems 22:  23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held","author":"Wei C","year":"2009","unstructured":"Wei C , Liu T Y , Lan Y , Ranking Measures and Loss Functions in Learning to Rank[C]\/\/ Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009 , Vancouver, British Columbia, Canada. 2009. Wei C , Liu T Y , Lan Y , Ranking Measures and Loss Functions in Learning to Rank[C]\/\/ Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, Vancouver, British Columbia, Canada. 2009."},{"key":"e_1_3_2_1_7_1","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE","author":"Ding Y","year":"2019","unstructured":"Ding Y , Zhou Y , Zhu Y , Selective Sparse Sampling for Fine-Grained Image Recognition[C]\/\/ 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE , 2019 . Ding Y , Zhou Y , Zhu Y , Selective Sparse Sampling for Fine-Grained Image Recognition[C]\/\/ 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE, 2019."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"e_1_3_2_1_9_1","volume-title":"Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up[C]\/\/ IEEE Conference on Computer Vision & Pattern Recognition. arXiv","author":"Ge W","year":"2019","unstructured":"Ge W , Lin X , Yu Y . Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up[C]\/\/ IEEE Conference on Computer Vision & Pattern Recognition. arXiv , 2019 . Ge W , Lin X , Yu Y . Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up[C]\/\/ IEEE Conference on Computer Vision & Pattern Recognition. arXiv, 2019."},{"key":"e_1_3_2_1_10_1","first-page":"778","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Kaiming He","year":"2016","unstructured":"Kaiming He , Xiangyu Zhang, Shaoqing Ren , and Jian Sun. Deep residual learning for image recognition . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , pages 770\u2013 778 , 2016 . Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 770\u2013778, 2016."},{"key":"e_1_3_2_1_11_1","volume-title":"Computer Science","author":"Simonyan K","year":"2014","unstructured":"Simonyan K , Zisserman A . Very Deep Convolutional Networks for Large-Scale Image Recognition[J] . Computer Science , 2014 . Simonyan K , Zisserman A . Very Deep Convolutional Networks for Large-Scale Image Recognition[J]. Computer Science, 2014."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2929447"},{"key":"e_1_3_2_1_13_1","volume-title":"ImageNet Classification with Deep Convolutional Neural Networks[J]. Advances in neural information processing systems","author":"Krizhevsky A","year":"2012","unstructured":"Krizhevsky A , Sutskever I , Hinton G . ImageNet Classification with Deep Convolutional Neural Networks[J]. Advances in neural information processing systems , 2012 , 25(2). Krizhevsky A , Sutskever I , Hinton G . ImageNet Classification with Deep Convolutional Neural Networks[J]. Advances in neural information processing systems, 2012, 25(2)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_15_1","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society","author":"Lin T Y","year":"2017","unstructured":"Lin T Y , Dollar P , Girshick R , Feature Pyramid Networks for Object Detection[C]\/\/ 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society , 2017 . Lin T Y , Dollar P , Girshick R , Feature Pyramid Networks for Object Detection[C]\/\/ 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, 2017."},{"key":"e_1_3_2_1_16_1","volume-title":"Erhan D","author":"Liu W","year":"2015","unstructured":"Liu W , Anguelov D , Erhan D , SSD : Single Shot MultiBox Detector [J]. 2015 . Liu W , Anguelov D , Erhan D , SSD: Single Shot MultiBox Detector[J]. 2015."},{"key":"e_1_3_2_1_17_1","volume-title":"Bird Species Categorization Using Pose Normalized Deep Convolutional Nets[J]. Eprint Arxiv","author":"Branson S","year":"2014","unstructured":"Branson S , Horn G V , Belongie S , Bird Species Categorization Using Pose Normalized Deep Convolutional Nets[J]. Eprint Arxiv , 2014 . Branson S , Horn G V , Belongie S , Bird Species Categorization Using Pose Normalized Deep Convolutional Nets[J]. Eprint Arxiv, 2014."},{"key":"e_1_3_2_1_18_1","volume-title":"Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition[J]","author":"Wei X S","year":"2016","unstructured":"Wei X S , Xie C W , Wu J . Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition[J] . 2016 . Wei X S , Xie C W , Wu J . Mask-CNN: Localizing Parts and Selecting Descriptors for Fine-Grained Image Recognition[J]. 2016."},{"key":"e_1_3_2_1_19_1","volume-title":"Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition[J]","author":"Yang S","year":"2021","unstructured":"Yang S , Liu S , Yang C , Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition[J] . 2021 . Yang S , Liu S , Yang C , Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition[J]. 2021."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2648498"},{"key":"e_1_3_2_1_21_1","volume-title":"The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification[J]","author":"Xiao T","year":"2014","unstructured":"Xiao T , Xu Y , Yang K , The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification[J] . IEEE , 2014 . Xiao T , Xu Y , Yang K , The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification[J]. IEEE, 2014."},{"key":"e_1_3_2_1_22_1","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE","author":"Girdhar R","year":"2020","unstructured":"Girdhar R , Carreira J J , Doersch C , Video Action Transformer Network [C]\/\/ 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE , 2020 . Girdhar R , Carreira J J , Doersch C , Video Action Transformer Network[C]\/\/ 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_24_1","volume-title":"What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective[J]","author":"Wang Q","year":"2020","unstructured":"Wang Q , Zhang L , Wu B , What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective[J] . 2020 . Wang Q , Zhang L , Wu B , What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective[J]. 2020."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_26_1","volume-title":"FractalNet: Ultra-Deep Neural Networks without Residuals[C]\/\/","author":"Larsson G","year":"2016","unstructured":"Larsson G , Maire M , Shakhnarovich G . FractalNet: Ultra-Deep Neural Networks without Residuals[C]\/\/ 2016 . Larsson G , Maire M , Shakhnarovich G . FractalNet: Ultra-Deep Neural Networks without Residuals[C]\/\/ 2016."},{"key":"e_1_3_2_1_27_1","volume-title":"Shake-Shake regularization of 3-branch residual networks[C]\/\/ International Conference on Learning Representations","author":"Gastaldi X .","year":"2017","unstructured":"Gastaldi X . Shake-Shake regularization of 3-branch residual networks[C]\/\/ International Conference on Learning Representations . 2017 . Gastaldi X . Shake-Shake regularization of 3-branch residual networks[C]\/\/ International Conference on Learning Representations. 2017."},{"key":"e_1_3_2_1_28_1","volume-title":"ShakeDrop Regularization for Deep Residual Learning[J]","author":"Yamada Y","year":"2018","unstructured":"Yamada Y , Iwamura M , Akiba T , ShakeDrop Regularization for Deep Residual Learning[J] . 2018 . Yamada Y , Iwamura M , Akiba T , ShakeDrop Regularization for Deep Residual Learning[J]. 2018."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"}],"event":{"name":"CSAI 2022: 2022 6th International Conference on Computer Science and Artificial Intelligence","location":"Beijing China","acronym":"CSAI 2022"},"container-title":["Proceedings of the 2022 6th International Conference on Computer Science and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577530.3577586","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3577530.3577586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:35Z","timestamp":1750178855000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577530.3577586"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,9]]},"references-count":29,"alternative-id":["10.1145\/3577530.3577586","10.1145\/3577530"],"URL":"https:\/\/doi.org\/10.1145\/3577530.3577586","relation":{},"subject":[],"published":{"date-parts":[[2022,12,9]]},"assertion":[{"value":"2023-03-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}