{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T02:13:45Z","timestamp":1743128025205,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819601219"},{"type":"electronic","value":"9789819601226"}],"license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"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\/978-981-96-0122-6_5","type":"book-chapter","created":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T18:23:23Z","timestamp":1731781403000},"page":"41-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MMAT: Multi-scale Multi-attention Transformer for\u00a0Fine-Grained Wild Fungi Visual Classification"],"prefix":"10.1007","author":[{"given":"Qinyan","family":"Dai","sequence":"first","affiliation":[]},{"given":"Yuxiang","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Chunlin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Hongtao","family":"Lu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"key":"5_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"5_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Hu, H., Wu, H., Jiang, Y., Wang, C.: Learning the best pooling strategy for visual semantic embedding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15789\u201315798 (2021)","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"5_CR4","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"5_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/978-3-030-58565-5_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Du","year":"2020","unstructured":"Du, R., et al.: Fine-grained visual classification via progressive multi-granularity training of jigsaw patches. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 153\u2013168. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_10"},{"key":"5_CR6","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":"5_CR7","doi-asserted-by":"crossref","unstructured":"Ge, W., Lin, X., Yu, Y.: Weakly supervised complementary parts models for fine-grained image classification from the bottom up. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3034\u20133043 (2019)","DOI":"10.1109\/CVPR.2019.00315"},{"key":"5_CR8","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":"5_CR9","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: RAMS-Trans: recurrent attention multi-scale transformer for fine-grained image recognition. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 4239\u20134248 (2021)","DOI":"10.1145\/3474085.3475561"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1449\u20131457 (2015)","DOI":"10.1109\/ICCV.2015.170"},{"key":"5_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":"5_CR13","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":"5_CR14","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":"5_CR15","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 dataset (2011)"},{"issue":"12","key":"5_CR16","doi-asserted-by":"publisher","first-page":"2860","DOI":"10.11834\/jig.200426","volume":"26","author":"Z Xun","year":"2021","unstructured":"Xun, Z., Jiabao, W., Yang, L., Yapeng, W., Zhuang, M.: Complemented attention method for fine-grained image classification. Chin. J. Image Graph. 26(12), 2860\u20132869 (2021)","journal-title":"Chin. J. Image Graph."},{"key":"5_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/978-3-030-01264-9_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Z Yang","year":"2018","unstructured":"Yang, Z., Luo, T., Wang, D., Hu, Z., Gao, J., Wang, L.: Learning to navigate for fine-grained classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 438\u2013454. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_26"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cao, X., Wang, R.: Audio visual attribute discovery for fine-grained object recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12295"},{"key":"5_CR19","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 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3234\u20133238. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747591"},{"key":"5_CR20","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":"5_CR21","unstructured":"Zheng, H., Fu, J., Zha, Z.J., Luo, J.: Learning deep bilinear transformation for fine-grained image representation. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"5_CR22","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","PRICAI 2024: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0122-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T19:17:47Z","timestamp":1731784667000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0122-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"ISBN":["9789819601219","9789819601226"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0122-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"12 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}