{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T07:08:46Z","timestamp":1743059326913,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781650"},{"type":"electronic","value":"9783031781667"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-78166-7_3","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T21:34:51Z","timestamp":1733088891000},"page":"35-49","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DualViT: A Hierarchical Vision Transformer for\u00a0Broad and\u00a0Fine Class Embeddings"],"prefix":"10.1007","author":[{"given":"Ankita","family":"Chatterjee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sandip","family":"Dutta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jayanta","family":"Mukhopadhyay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Partha Pratim","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","first-page":"14410","DOI":"10.1109\/ACCESS.2018.2807385","volume":"6","author":"N Akhtar","year":"2018","unstructured":"Akhtar, N., Mian, A.: Threat of adversarial attacks on deep learning in computer vision: a survey. IEEE Access 6, 14410\u201314430 (2018)","journal-title":"IEEE Access"},{"key":"3_CR2","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 on Computer Vision and Pattern Recognition, pp. 12506\u201312515 (2020)","DOI":"10.1109\/CVPR42600.2020.01252"},{"key":"3_CR3","doi-asserted-by":"publisher","first-page":"1718","DOI":"10.1109\/TAI.2023.3297086","volume":"5","author":"A Chatterjee","year":"2023","unstructured":"Chatterjee, A., Mukherjee, J., Das, P.P.: ImageNet classification using wordnet hierarchy. IEEE Trans. Artif. Intell. 5, 1718\u20131727 (2023)","journal-title":"IEEE Trans. Artif. Intell."},{"key":"3_CR4","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1007\/s12559-019-09656-w","volume":"13","author":"H Chen","year":"2021","unstructured":"Chen, H., Ding, G., Lin, Z., Guo, Y., Shan, C., Han, J.: Image captioning with memorized knowledge. Cogn. Comput. 13, 807\u2013820 (2021)","journal-title":"Cogn. Comput."},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Berg, A.C., Fei-Fei, L.: Hierarchical semantic indexing for large scale image retrieval. In: CVPR 2011, pp. 785\u2013792. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995516"},{"key":"3_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-642-15555-0_6","volume-title":"Computer Vision \u2013 ECCV 2010","author":"J Deng","year":"2010","unstructured":"Deng, J., Berg, A.C., Li, K., Fei-Fei, L.: What does classifying more than 10,000 image categories tell us? In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6315, pp. 71\u201384. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15555-0_6"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3_CR8","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1007\/978-3-031-19812-0_16","volume-title":"ECCV 2022","author":"Y Deng","year":"2022","unstructured":"Deng, Y., et al.: Hierarchical memory learning for fine-grained scene graph generation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 266\u2013283. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_16"},{"key":"3_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"3_CR10","unstructured":"Hou, L., Yu, C.P., Samaras, D.: Squared earth mover\u2019s distance-based loss for training deep neural networks. arXiv preprint arXiv:1611.05916 (2016)"},{"key":"3_CR11","unstructured":"Karthik, S., Prabhu, A., Dokania, P.K., Gandhi, V.: No cost likelihood manipulation at test time for making better mistakes in deep networks. In: International Conference on Learning Representations (2020)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Khrulkov, V., Mirvakhabova, L., Ustinova, E., Oseledets, I., Lempitsky, V.: Hyperbolic image embeddings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6418\u20136428 (2020)","DOI":"10.1109\/CVPR42600.2020.00645"},{"key":"3_CR13","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"3_CR14","unstructured":"Landrieu, L., Garnot, V.S.F.: Leveraging class hierarchies with metric-guided prototype learning. In: British Machine Vision Conference (BMVC) (2021)"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Lee, J., Lee, M., Lee, D., Lee, S.: Hierarchically decomposed graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10444\u201310453 (2023)","DOI":"10.1109\/ICCV51070.2023.00958"},{"issue":"04","key":"3_CR16","doi-asserted-by":"publisher","first-page":"1750017","DOI":"10.1142\/S0219720017500172","volume":"15","author":"W Li","year":"2017","unstructured":"Li, W., Cerise, J.E., Yang, Y., Han, H.: Application of t-SNE to human genetic data. J. Bioinform. Comput. Biol. 15(04), 1750017 (2017)","journal-title":"J. Bioinform. Comput. Biol."},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Liu, S., Chen, J., Pan, L., Ngo, C.W., Chua, T.S., Jiang, Y.G.: Hyperbolic visual embedding learning for zero-shot recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9273\u20139281 (2020)","DOI":"10.1109\/CVPR42600.2020.00929"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Long, T., Mettes, P., Shen, H.T., Snoek, C.G.: Searching for actions on the hyperbole. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1141\u20131150 (2020)","DOI":"10.1109\/CVPR42600.2020.00122"},{"issue":"11","key":"3_CR19","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"issue":"11","key":"3_CR20","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"3_CR21","unstructured":"Nickel, M., Kiela, D.: Poincar\u00e9 embeddings for learning hierarchical representations. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"3_CR23","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.neunet.2019.09.010","volume":"121","author":"D Roy","year":"2020","unstructured":"Roy, D., Panda, P., Roy, K.: Tree-CNN: a hierarchical deep convolutional neural network for incremental learning. Neural Netw. 121, 148\u2013160 (2020)","journal-title":"Neural Netw."},{"key":"3_CR24","unstructured":"Sala, F., De\u00a0Sa, C., Gu, A., R\u00e9, C.: Representation tradeoffs for hyperbolic embeddings. In: International Conference on Machine Learning, pp. 4460\u20134469. PMLR (2018)"},{"issue":"8","key":"3_CR25","doi-asserted-by":"publisher","first-page":"1958","DOI":"10.1109\/TPAMI.2012.269","volume":"35","author":"R Salakhutdinov","year":"2012","unstructured":"Salakhutdinov, R., Tenenbaum, J.B., Torralba, A.: Learning with hierarchical-deep models. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1958\u20131971 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR26","unstructured":"Schlag, I., Smolensky, P., Fernandez, R., Jojic, N., Schmidhuber, J., Gao, J.: Enhancing the transformer with explicit relational encoding for math problem solving. arXiv preprint arXiv:1910.06611 (2019)"},{"key":"3_CR27","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, 31\u201372 (2011)","journal-title":"Data Min. Knowl. Disc."},{"key":"3_CR28","unstructured":"Srivastava, N., Salakhutdinov, R.R.: Discriminative transfer learning with tree-based priors. Adv. Neural Inf. Process. Syst. 26 (2013)"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Verma, N., Mahajan, D., Sellamanickam, S., Nair, V.: Learning hierarchical similarity metrics. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2280\u20132287. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247938"},{"key":"3_CR30","unstructured":"Wang, W., Sun, Y., Li, W., Yang, Y.: TransHP: image classification with hierarchical prompting. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, S., Xu, R., Xiong, C., Ramaiah, C.: Use all the labels: a hierarchical multi-label contrastive learning framework. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16660\u201316669 (2022)","DOI":"10.1109\/CVPR52688.2022.01616"},{"key":"3_CR32","unstructured":"Zhao, B., Li, F., Xing, E.: Large-scale category structure aware image categorization. Adv. Neural Inf. Process. Syst. 24 (2011)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78166-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:36:08Z","timestamp":1733096168000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78166-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031781650","9783031781667"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78166-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}