{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:20:14Z","timestamp":1767183614371,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/icpr.2018.8545452","type":"proceedings-article","created":{"date-parts":[[2018,11,30]],"date-time":"2018-11-30T00:17:38Z","timestamp":1543537058000},"page":"916-921","source":"Crossref","is-referenced-by-count":18,"title":["Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch"],"prefix":"10.1109","author":[{"given":"Sounak","family":"Dey","sequence":"first","affiliation":[]},{"given":"Anjan","family":"Dutta","sequence":"additional","affiliation":[]},{"given":"Suman K.","family":"Ghosh","sequence":"additional","affiliation":[]},{"given":"Ernest","family":"Valveny","sequence":"additional","affiliation":[]},{"given":"Josep","family":"Llados","sequence":"additional","affiliation":[]},{"given":"Umapada","family":"Pal","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.247"},{"key":"ref32","article-title":"Sketch-a-net that beats humans","author":"yu","year":"2015","journal-title":"CoRR"},{"key":"ref31","volume":"absi1412 6980","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref30","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref10","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.93"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2010.07.002"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477615"},{"key":"ref14","first-page":"730","article-title":"Improving semantic embedding consistency by metric learning for zero-shot classiffication","author":"bucher","year":"2016","journal-title":"ECCV"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2699668"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref28","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"absi1409 1556","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.560"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532801"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref29","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"ICLRE"},{"journal-title":"A comprehensive survey on cross-modal retrieval","year":"2016","author":"wang","key":"ref5"},{"key":"ref8","first-page":"790","article-title":"A performance evaluation of gradient field hog descriptor for sketch based image retrieval","volume":"117","author":"hu","year":"2013","journal-title":"CVIU"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1145\/2897824.2925954","article-title":"The sketchy database: Learning to retrieve badly drawn bunnies","author":"sangkloy","year":"2016","journal-title":"ACM SIGGRAPH"},{"key":"ref9","first-page":"7","article-title":"Sketch based image retrieval using learned keyshapes (lks)","volume":"1","author":"saavedra","year":"2015","journal-title":"BMVC"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025606"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref22","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"NIPS"},{"key":"ref21","first-page":"2764","article-title":"Wsabie: Scaling up to large vocabulary image annotation","volume":"11","author":"weston","year":"2011","journal-title":"IJCAI"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref26","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"abs 1502 3044","author":"xu","year":"2015","journal-title":"CoRR"},{"key":"ref25","article-title":"Neural machine translation by jointly learning to align and translate","volume":"absi1409 473","author":"bahdanau","year":"2014","journal-title":"CoRR"}],"event":{"name":"2018 24th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2018,8,20]]},"location":"Beijing","end":{"date-parts":[[2018,8,24]]}},"container-title":["2018 24th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8527858\/8545020\/08545452.pdf?arnumber=8545452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T16:39:49Z","timestamp":1643301589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8545452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icpr.2018.8545452","relation":{},"subject":[],"published":{"date-parts":[[2018,8]]}}}