{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T07:40:06Z","timestamp":1743061206888,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031278174"},{"type":"electronic","value":"9783031278181"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-27818-1_11","type":"book-chapter","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:20:17Z","timestamp":1680171617000},"page":"127-138","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Recombining Vision Transformer Architecture for\u00a0Fine-Grained Visual Categorization"],"prefix":"10.1007","author":[{"given":"Xuran","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanbin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiying","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,31]]},"reference":[{"key":"11_CR1","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD birds-200-2011 dataset (2011)"},{"key":"11_CR2","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.F.: Novel dataset for fine-grained image categorization: Stanford dogs. In: Proceedings of CVPR Workshop on Fine-Grained Visual Categorization (FGVC), vol. 2. Citeseer (2011)"},{"key":"11_CR3","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":"11_CR4","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CNN: towards real-time object detection with region proposal networks. In: 28th Proceedings Conference on Advances in Neural Information Processing Systems (2015)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Cai, S., Zuo, W., Zhang, L.: Higher-order integration of hierarchical convolutional activations for fine-grained visual categorization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 511\u2013520 (2017)","DOI":"10.1109\/ICCV.2017.63"},{"key":"11_CR6","unstructured":"Zheng, H., Fu, J., Zha, Z.J., Luo, J.: Learning deep bilinear transformation for fine-grained image representation. In: 32nd Proceedings of the Conference on Advances in Neural Information Processing Systems (2019)"},{"key":"11_CR7","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":"11_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"11_CR9","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"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: A free lunch from VIT: adaptive attention multi-scale fusion transformer for fine-grained visual recognition. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 3234\u20133238. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747591"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Fu, J., Zheng, H., Mei, T.: Look closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4438\u20134446 (2017)","DOI":"10.1109\/CVPR.2017.476"},{"key":"11_CR14","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1016\/j.patcog.2017.10.002","volume":"76","author":"XS Wei","year":"2018","unstructured":"Wei, X.S., Xie, C.W., Wu, J., Shen, C.: Mask-CNN: localizing parts and selecting descriptors for fine-grained bird species categorization. Pattern Recogn. 76, 704\u2013714 (2018)","journal-title":"Pattern Recogn."},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Mei, T., Luo, J.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5209\u20135217 (2017)","DOI":"10.1109\/ICCV.2017.557"},{"key":"11_CR17","unstructured":"He, J., et al.: A transformer architecture for fine-grained recognition. arXiv preprint arXiv:2103.07976 (2021)"},{"key":"11_CR18","unstructured":"Wang, J., Yu, X., Gao, Y.: Feature fusion vision transformer for fine-grained visual categorization. arXiv preprint arXiv:2107.02341 (2021)"},{"key":"11_CR19","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"11_CR20","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":"11_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. arXiv preprint arXiv:2203.16527 (2022)","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"11_CR22","unstructured":"Ali, A., et al.: XCIT: cross-covariance image transformers. In: 34th Proceedings of the Conference on Advances in Neural Information Processing Systems (2021)"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Ding, M., Xiao, B., Codella, N., Luo, P., Wang, J., Yuan, L.: Davit: dual attention vision transformer. arXiv preprint arXiv:2204.03645 (2022)","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 113\u2013123 (2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Wang, Y., Morariu, V.I., Davis, L.S.: Learning a discriminative filter bank within a CNN for fine-grained recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4148\u20134157 (2018)","DOI":"10.1109\/CVPR.2018.00436"},{"key":"11_CR26","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. 34, pp. 11555\u201311562 (2020)","DOI":"10.1609\/aaai.v34i07.6822"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27818-1_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:23:19Z","timestamp":1680171799000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27818-1_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031278174","9783031278181"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27818-1_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"31 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bergen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"267","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"86","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}