{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:17:52Z","timestamp":1757618272146,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819681792"},{"type":"electronic","value":"9789819681808"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-8180-8_37","type":"book-chapter","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T09:16:05Z","timestamp":1750324565000},"page":"468-479","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Gate-ViT: Gated Vision Transformer for\u00a0Fine-Grained Visual Classification"],"prefix":"10.1007","author":[{"given":"Xiaowei","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kanqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., Van\u00a0Gool, L.: Food-101\u2013mining discriminative components with random forests. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, 6\u201312 September 2014, Proceedings, Part VI 13, pp. 446\u2013461. Springer (2014)","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"37_CR3","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"37_CR4","doi-asserted-by":"crossref","unstructured":"Fang, Z., Jiang, X., Tang, H., Li, Z.: Learning contrastive self-distillation for ultra-fine-grained visual categorization targeting limited samples. arXiv preprint arXiv:2311.06056 (2023)","DOI":"10.1109\/TCSVT.2024.3370731"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Fang, Z., Jiang, X., Tang, H., Li, Z.: Learning contrastive self-distillation for ultra-fine-grained visual categorization targeting limited samples. IEEE Trans. Circuits Syst. Video Technol. (2024)","DOI":"10.1109\/TCSVT.2024.3370731"},{"key":"37_CR6","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.\u00a036, pp. 852\u2013860 (2022)","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"37_CR7","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":"37_CR8","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, 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":"37_CR9","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.F.: Novel dataset for fine-grained image categorization: Stanford dogs. In: Proceedings of the CVPR Workshop on Fine-Grained Visual Categorization (FGVC), vol.\u00a02. Citeseer (2011)"},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"Lambert, J., Sener, O., Savarese, S.: Deep learning under privileged information using heteroscedastic dropout. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8886\u20138895 (2018)","DOI":"10.1109\/CVPR.2018.00926"},{"key":"37_CR11","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"},{"issue":"5","key":"37_CR12","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1136\/amiajnl-2011-000464","volume":"18","author":"PM Nadkarni","year":"2011","unstructured":"Nadkarni, P.M., Ohno-Machado, L., Chapman, W.W.: Natural language processing: an introduction. J. Am. Med. Inform. Assoc. 18(5), 544\u2013551 (2011)","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez, A.C., D\u2019Aronco, S., Schindler, K., Wegner, J.D.: Fine-grained species recognition with privileged pooling: better sample efficiency through supervised attention. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3316718"},{"key":"37_CR14","unstructured":"Salehinejad, H., Sankar, S., Barfett, J., Colak, E., Valaee, S.: Recent advances in recurrent neural networks. arXiv preprint arXiv:1801.01078 (2017)"},{"issue":"5","key":"37_CR15","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1109\/TNNLS.2014.2330900","volume":"26","author":"L Shao","year":"2014","unstructured":"Shao, L., Zhu, F., Li, X.: Transfer learning for visual categorization: a survey. IEEE Trans. Neural Netw. Learn. Syst. 26(5), 1019\u20131034 (2014)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., Schl\u00fcter, R., Ney, H.: LSTM neural networks for language modeling. In: Thirteenth Annual Conference of the International Speech Communication Association (2012)","DOI":"10.21437\/Interspeech.2012-65"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Voulodimos, A., Doulamis, N., Doulamis, A., Protopapadakis, E., et\u00a0al.: Deep learning for computer vision: a brief review. Comput. Intell. Neurosci. 2018 (2018)","DOI":"10.1155\/2018\/7068349"},{"key":"37_CR18","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 dataset (2011)"},{"key":"37_CR19","doi-asserted-by":"publisher","first-page":"109547","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":"37_CR20","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1016\/j.jvcir.2018.12.049","volume":"59","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Wang, Z.: A survey of recent work on fine-grained image classification techniques. J. Vis. Commun. Image Represent. 59, 210\u2013214 (2019)","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"12","key":"37_CR21","doi-asserted-by":"publisher","first-page":"8927","DOI":"10.1109\/TPAMI.2021.3126648","volume":"44","author":"XS Wei","year":"2021","unstructured":"Wei, X.S., et al.: Fine-grained image analysis with deep learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 8927\u20138948 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR22","unstructured":"Wei, X.S., Wu, J., Cui, Q.: Deep learning for fine-grained image analysis: a survey. arXiv preprint arXiv:1907.03069 (2019)"},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"Wu, X., Zhan, C., Lai, Y.K., Cheng, M.M., Yang, J.: IP102: a large-scale benchmark dataset for insect pest recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8787\u20138796 (2019)","DOI":"10.1109\/CVPR.2019.00899"},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Yang, H., Tianyi\u00a0Zhou, J., Cai, J., Soon\u00a0Ong, Y.: MIML-FCN+: multi-instance multi-label learning via fully convolutional networks with privileged information. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1577\u20131585 (2017)","DOI":"10.1109\/CVPR.2017.635"},{"key":"37_CR25","doi-asserted-by":"crossref","unstructured":"Yu, X., Pan, Z., Zhao, Y., Gao, Y.: Self-supervised lie algebra representation learning via optimal canonical metric. IEEE Trans. Neural Netw. Learn. Syst. (2024)","DOI":"10.1109\/TNNLS.2024.3355492"},{"key":"37_CR26","doi-asserted-by":"publisher","first-page":"109131","DOI":"10.1016\/j.patcog.2022.109131","volume":"135","author":"X Yu","year":"2023","unstructured":"Yu, X., Wang, J., Zhao, Y., Gao, Y.: Mix-ViT: mixing attentive vision transformer for ultra-fine-grained visual categorization. Pattern Recogn. 135, 109131 (2023)","journal-title":"Pattern Recogn."},{"key":"37_CR27","doi-asserted-by":"publisher","first-page":"109979","DOI":"10.1016\/j.patcog.2023.109979","volume":"145","author":"ZC Zhang","year":"2024","unstructured":"Zhang, Z.C., Chen, Z.D., Wang, Y., Luo, X., Xu, X.S.: A vision transformer for fine-grained classification by reducing noise and enhancing discriminative information. Pattern Recogn. 145, 109979 (2024)","journal-title":"Pattern Recogn."},{"key":"37_CR28","doi-asserted-by":"crossref","unstructured":"Zhu, L., Chen, T., Yin, J., See, S., Liu, J.: Learning gabor texture features for fine-grained recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1621\u20131631 (2023)","DOI":"10.1109\/ICCV51070.2023.00156"},{"key":"37_CR29","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.\u00a034, pp. 13130\u201313137 (2020)","DOI":"10.1609\/aaai.v34i07.7016"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8180-8_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T20:31:19Z","timestamp":1757190679000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8180-8_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819681792","9789819681808"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8180-8_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"20 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","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":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}