{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:19:37Z","timestamp":1783556377649,"version":"3.55.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032222633","type":"print"},{"value":"9783032222640","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-22264-0_23","type":"book-chapter","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:08:50Z","timestamp":1783555730000},"page":"288-299","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Vision Transformer for\u00a0Fine-Grained Visual Classification with\u00a0Selective Attention Aggregation and\u00a0Multi-Head Noise Suppression"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8844-2466","authenticated-orcid":false,"given":"TianRong","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JuanDong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"YaoSen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,2]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. arXiv: Learning, arXiv: Learning (2020)","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Bai, Y., Zhang, W., Mei, T.: Destruction and construction learning for fine-grained image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5157\u20135166 (2019)","DOI":"10.1109\/CVPR.2019.00530"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Ding, Y., Zhou, Y., Zhu, Y., Ye, Q., Jiao, J.: Selective sparse sampling for fine-grained image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6599\u20136608 (2019)","DOI":"10.1109\/ICCV.2019.00670"},{"key":"23_CR4","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: transformers for image recognition at scale (2020). arXiv:2010.11929 arXiv preprint"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Du, R., et al.: Fine-grained visual classification via progressive multi-granularity training of jigsaw patches. In: European Conference on Computer Vision, pp. 153\u2013168. Springer (2020)","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Gao, Y., Han, X., Wang, X., Huang, W., Scott, M.: Channel interaction networks for fine-grained image categorization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10818\u201310825 (2020)","DOI":"10.1609\/aaai.v34i07.6712"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"He, J., et al.: Transfg: a transformer architecture for fine-grained recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 852\u2013860 (2022)","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Huang, Z., Li, Y.: Interpretable and accurate fine-grained recognition via region grouping. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8662\u20138672 (2020)","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Ji, R., et al.: Attention convolutional binary neural tree for fine-grained visual categorization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10468\u201310477 (2020)","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"23_CR10","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.F.: Novel dataset for fine-grained image categorization: stanford dogs. In: Proceedings CVPR workshop on fine-grained visual categorization (FGVC), vol. 2, (2011)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Liu, C., Xie, H., Zha, Z.J., Ma, L., Yu, L., Zhang, Y.: Filtration and distillation: enhancing region attention for fine-grained visual categorization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11555\u201311562 (2020)","DOI":"10.1609\/aaai.v34i07.6822"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Luo, W., et al.: Cross-x learning for fine-grained visual categorization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8242\u20138251 (2019)","DOI":"10.1109\/ICCV.2019.00833"},{"key":"23_CR15","doi-asserted-by":"publisher","first-page":"4996","DOI":"10.1109\/TIP.2020.2977457","volume":"29","author":"S Min","year":"2020","unstructured":"Min, S., Yao, H., Xie, H., Zha, Z.J., Zhang, Y.: Multi-objective matrix normalization for fine-grained visual recognition. IEEE Trans. Image Process. 29, 4996\u20135009 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR16","doi-asserted-by":"publisher","unstructured":"Serrano, S., Smith, N.A.: Is attention interpretable? In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/p19-1282, http:\/\/dx.doi.org\/10.18653\/v1\/p19-1282","DOI":"10.18653\/v1\/p19-1282"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Sun, H., He, X., Peng, Y.: Sim-trans: structure information modeling transformer for fine-grained visual categorization. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5853\u20135861 (2022)","DOI":"10.1145\/3503161.3548308"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Sun, M., Yuan, Y., Zhou, F., Ding, E.: Multi-attention multi-class constraint for fine-grained image recognition. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 805\u2013821 (2018)","DOI":"10.1007\/978-3-030-01270-0_49"},{"key":"23_CR19","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"23_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. Neural Information Processing Systems, Neural Information Processing Systems (2017)"},{"key":"23_CR21","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Wang, J., Yu, X., Gao, Y.: Feature fusion vision transformer for fine-grained visual categorization. arXiv preprint arXiv:2107.02341 (2021)","DOI":"10.5244\/C.35.192"},{"key":"23_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109547","volume":"140","author":"Q Wang","year":"2023","unstructured":"Wang, Q., Wang, J., Deng, H., Wu, X., Wang, Y., Hao, G.: Aa-trans: Core attention aggregating transformer with information entropy selector for fine-grained visual classification. Pattern Recogn. 140, 109547 (2023)","journal-title":"Pattern Recogn."},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, S., Yang, S., Li, H., Li, J., Li, Z.: Weakly supervised fine-grained image classification via guassian mixture model oriented discriminative learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9749\u20139758 (2020)","DOI":"10.1109\/CVPR42600.2020.00977"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, S., Li, H., Dou, Z., Li, J.: Graph-propagation based correlation learning for weakly supervised fine-grained image classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 12289\u201312296 (2020)","DOI":"10.1609\/aaai.v34i07.6912"},{"key":"23_CR26","doi-asserted-by":"publisher","first-page":"9015","DOI":"10.1109\/TMM.2023.3244340","volume":"25","author":"Q Xu","year":"2023","unstructured":"Xu, Q., Wang, J., Jiang, B., Luo, B.: Fine-grained visual classification via internal ensemble learning transformer. IEEE Trans. Multimedia 25, 9015\u20139028 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, L., Huang, S., Liu, W., Tao, D.: Learning a mixture of granularity-specific experts for fine-grained categorization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8331\u20138340 (2019)","DOI":"10.1109\/ICCV.2019.00842"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Zha, Z.J., Luo, J.: Looking for the devil in the details: learning trilinear attention sampling network for fine-grained image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5012\u20135021 (2019)","DOI":"10.1109\/CVPR.2019.00515"},{"key":"23_CR29","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1109\/TIP.2019.2921876","volume":"29","author":"H Zheng","year":"2019","unstructured":"Zheng, H., Fu, J., Zha, Z.J., Luo, J., Mei, T.: Learning rich part hierarchies with progressive attention networks for fine-grained image recognition. IEEE Trans. Image Process. 29, 476\u2013488 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Zhuang, P., Wang, Y., Qiao, Y.: Learning attentive pairwise interaction for fine-grained classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13130\u201313137 (2020)","DOI":"10.1609\/aaai.v34i07.7016"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-22264-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:08:54Z","timestamp":1783555734000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-22264-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032222633","9783032222640"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-22264-0_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"42","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cgs-network.org\/cgi25","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}