{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T23:48:44Z","timestamp":1778802524402,"version":"3.51.4"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/wacv45572.2020.9093373","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"2939-2948","source":"Crossref","is-referenced-by-count":25,"title":["Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features"],"prefix":"10.1109","author":[{"given":"Andres","family":"Mafla","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sounak","family":"Dey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali Furkan","family":"Biten","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lluis","family":"Gomez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimosthenis","family":"Karatzas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref38","article-title":"Learning deep representations for word spotting under weak supervision","author":"sudholt","year":"2017","journal-title":"arXiv preprint arXiv 1712 00250"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298778"},{"key":"ref30","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref37","first-page":"2222","article-title":"Multimodal learning with deep boltzmann machines","author":"srivastava","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref28","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"d maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref27","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"liu","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref29","article-title":"Fine-grained visual classification of aircraft","author":"maji","year":"2013","journal-title":"arXiv preprint arXiv 1306 5151"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2878899"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2339814"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref22","article-title":"Pvanet: deep but lightweight neural networks for real-time object detection","author":"kim","year":"2016","journal-title":"arXiv preprint arXiv 1608 08021"},{"key":"ref21","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2016","journal-title":"arXiv preprint arXiv 1610 09756"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2825107"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref26","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"2019","journal-title":"arXiv preprint arXiv 1908 00310"},{"key":"ref25","first-page":"4161","article-title":"Textboxes: A fast text detector with a single deep neural network","author":"liao","year":"2017","journal-title":"AAAI"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-015-4488-0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00228"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_43"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2642781"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2307\/2528680"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00527"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2638622"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502197"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref5","author":"biten","year":"2019","journal-title":"Scene text visual question answering"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","first-page":"127","article-title":"E2e-mlt-an unconstrained? end-to-end method for multi-language scene text","author":"busta","year":"2018","journal-title":"Asian Conference on Computer Vision"},{"key":"ref49","article-title":"Lookahead optimizer: k steps forward, 1 step back","author":"zhang","year":"2019","journal-title":"arXiv preprint arXiv 1907 09977"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.81"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref42","first-page":"842","article-title":"The application of two-level attention models in deep convolutional neural network for fine-grained image classification","author":"xiao","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref41","article-title":"Coco-text: Dataset and benchmark for text detection and recognition in natural images","author":"veit","year":"2016","journal-title":"arXiv preprint arXiv 1601 07409"},{"key":"ref44","first-page":"3122","article-title":"Unsupervised template learning for fine-grained object recognition","author":"yang","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/145"}],"event":{"name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","location":"Snowmass Village, CO, USA","start":{"date-parts":[[2020,3,1]]},"end":{"date-parts":[[2020,3,5]]}},"container-title":["2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9087828\/9093261\/09093373.pdf?arnumber=9093373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:17:13Z","timestamp":1656602233000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093373","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}