{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:17:34Z","timestamp":1743085054976,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819722617"},{"type":"electronic","value":"9789819722594"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-2259-4_29","type":"book-chapter","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T09:02:31Z","timestamp":1713949351000},"page":"385-396","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MLT-Trans: Multi-level Token Transformer for\u00a0Hierarchical Image Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0643-2133","authenticated-orcid":false,"given":"Tanya","family":"Boone Sifuentes","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4955-9684","authenticated-orcid":false,"given":"Asef","family":"Nazari","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1807-430X","authenticated-orcid":false,"given":"Mohamed Reda","family":"Bouadjenek","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3930-6600","authenticated-orcid":false,"given":"Imran","family":"Razzak","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,25]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Mueller, R., Tertikas, K., Samangooei, S., Lord, N.A.: Making better mistakes: leveraging class hierarchies with deep networks. In: Proceedings of the IEEE\/CVF Conference, pp. 12506\u201312515 (2020)","DOI":"10.1109\/CVPR42600.2020.01252"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Boone-Sifuentes, T., Bouadjenek, M.R., Razzak, I., Hacid, H., Nazari, A.: A mask-based output layer for multi-level hierarchical classification. In: CIKM\u201922, pp. 3833\u20133837 (2022)","DOI":"10.1145\/3511808.3557534"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Boone-Sifuentes, T., et al.: Marine-tree: large-scale marine organisms dataset for hierarchical image classification. CIKM \u201922, New York, NY, USA (2022)","DOI":"10.1145\/3511808.3557634"},{"key":"29_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29"},{"key":"29_CR5","unstructured":"Chen, M., et al.: Coarse-to-fine vision transformer. arXiv preprint arXiv:2203.03821 (2022)"},{"key":"29_CR6","unstructured":"Chou, P.Y., Kao, Y.Y., Lin, C.H.: Fine-grained visual classification with high-temperature refinement and background suppression. arXiv preprint arXiv:2303.06442 (2023)"},{"key":"29_CR7","unstructured":"Diao, Q., Jiang, Y., Wen, B., Sun, J., Yuan, Z.: MetaFormer: a unified meta framework for fine-grained recognition. arXiv preprint arXiv:2203.02751 (2022)"},{"key":"29_CR8","doi-asserted-by":"publisher","unstructured":"Dong, B., Zhou, P., Yan, S., Zuo, W.: Towards class interpretable vision transformer with multi-class-tokens. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 609\u2013622. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-18913-5_47","DOI":"10.1007\/978-3-031-18913-5_47"},{"key":"29_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\,\\times \\,16$$ words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"29_CR10","unstructured":"Foret, P., Kleiner, A., Mobahi, H., Neyshabur, B.: Sharpness-aware minimization for efficiently improving generalization. arXiv preprint arXiv:2010.01412 (2020)"},{"key":"29_CR11","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Huo, Y., Lu, Y., Niu, Y., Lu, Z., Wen, J.R.: Coarse-to-fine grained classification. In: Proceedings of the ACM SIGIR Conference, pp. 1033\u20131036. SIGIR\u201919 (2019)","DOI":"10.1145\/3331184.3331336"},{"key":"29_CR13","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":"29_CR14","unstructured":"Kim, S., Nam, J., Ko, B.C.: ViT-NeT: interpretable vision transformers with neural tree decoder. In: International Conference on Machine Learning, pp. 11162\u201311172. PMLR (2022)"},{"issue":"3","key":"29_CR15","doi-asserted-by":"publisher","first-page":"820","DOI":"10.1007\/s10618-014-0382-x","volume":"29","author":"A Kosmopoulos","year":"2015","unstructured":"Kosmopoulos, A., Partalas, I., Gaussier, E., Paliouras, G., Androutsopoulos, I.: Evaluation measures for hierarchical classification: a unified view and novel approaches. Data Min. Knowl. Disc. 29(3), 820\u2013865 (2015)","journal-title":"Data Min. Knowl. Disc."},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y., Dou, Y., Jin, R., Qiao, P.: Visual tree convolutional neural network in image classification. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 758\u2013763. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8546126"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin Transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF Conference, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"29_CR18","unstructured":"Maji, S., Kannala, J., Rahtu, E., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. Tech. rep. (2013)"},{"key":"29_CR19","unstructured":"Parag, T., Wang, H.: Multilayer dense connections for hierarchical concept classification. arXiv preprint arXiv:2003.09015 (2020)"},{"key":"29_CR20","unstructured":"Schmid, F., Masoudian, S., Koutini, K., Widmer, G.: Knowledge distillation from transformers for low-complexity acoustic scene classification. In: Proceedings of the Detection and Classification of Acoustic Scenes and Events 2022 Workshop (2022)"},{"key":"29_CR21","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1016\/j.eswa.2018.09.022","volume":"116","author":"Y Seo","year":"2019","unstructured":"Seo, Y., Shin, K.S.: Hierarchical convolutional neural networks for fashion image classification. Expert Syst. Appl. 116, 328\u2013339 (2019)","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"29_CR22","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10618-010-0175-9","volume":"22","author":"CN Silla","year":"2011","unstructured":"Silla, C.N., Freitas, A.A.: A survey of hierarchical classification across different application domains. Data Min. Knowl. Disc. 22(1), 31\u201372 (2011)","journal-title":"Data Min. Knowl. Disc."},{"key":"29_CR23","unstructured":"Wood, L., Tan, Z., Stenbit, I., Bischof, J., Zhu, S., Chollet, F., et\u00a0al.: Kerascv. https:\/\/github.com\/keras-team\/keras-cv (2022)"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Xu, L., Ouyang, W., Bennamoun, M., Boussaid, F., Xu, D.: Multi-class token transformer for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference, pp. 4310\u20134319 (2022)","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Yan, Z., et al.: HD-CNN: hierarchical deep convolutional neural networks for large scale visual recognition. In: Proceedings of the IEEE ICCV Conference (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, H., Zhao, L., Chen, T., Arik, S.\u00d6., Pfister, T.: Nested hierarchical transformer: towards accurate, data-efficient and interpretable visual understanding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 3417\u20133425 (2022)","DOI":"10.1609\/aaai.v36i3.20252"},{"key":"29_CR27","unstructured":"Zhu, X., Bain, M.: B-CNN: branch convolutional neural network for hierarchical classification. arXiv preprint arXiv:1709.09890 (2017)"}],"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\/978-981-97-2259-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T23:19:56Z","timestamp":1714000796000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2259-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819722617","9789819722594"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2259-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"25 April 2024","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":"Taipei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","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":"7 May 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}