{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T12:09:41Z","timestamp":1790251781872,"version":"4.1.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/cbmi.2018.8516480","type":"proceedings-article","created":{"date-parts":[[2018,11,19]],"date-time":"2018-11-19T20:53:35Z","timestamp":1542660815000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Embedding Images and Sentences in a Common Space with a Recurrent Capsule Network"],"prefix":"10.1109","author":[{"given":"Danny","family":"Francis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benoit","family":"Huet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernard","family":"Merialdo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","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":"ref11","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref13","author":"kiros","year":"2014","journal-title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref15","first-page":"833","article-title":"Rnn fisher vectors for action recognition and image annotation","author":"lev","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref16","author":"vendrov","year":"2015","journal-title":"Order-embeddings of images and language"},{"key":"ref17","author":"eisenschtat","year":"2017","journal-title":"Linking image and text with 2-way nets"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref19","author":"nam","year":"2016","journal-title":"Dual Attention Networks for Multimodal Reasoning and Matching"},{"key":"ref4","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2017.34"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"hochreiter","year":"1997","journal-title":"Long Short-term Memory Neural Computation"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","first-page":"3859","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","author":"cho","year":"2014","journal-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref9","first-page":"44","author":"hinton","year":"2011","journal-title":"Transforming auto-encoders In International Conference on Artificial Neural Networks"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref20","author":"faghri","year":"2017","journal-title":"VSE++ Improving Visual-Semantic Em-beddings with Hard Negatives"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref21","author":"gu","year":"2017","journal-title":"Look Imagine and Match Improving Textual-Visual Cross-Modal Retrieval with Generative Models"},{"key":"ref24","first-page":"321","author":"hotelling","year":"1936","journal-title":"Relations between two sets of variates Biometrika 28(3\/4)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref26","first-page":"265","volume":"16","author":"abadi","year":"2016","journal-title":"Tensorflow A system for large-scale machine learning"},{"key":"ref25","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"}],"event":{"name":"2018 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"La Rochelle","start":{"date-parts":[[2018,9,4]]},"end":{"date-parts":[[2018,9,6]]}},"container-title":["2018 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8491725\/8516270\/08516480.pdf?arnumber=8516480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,15]],"date-time":"2020-11-15T10:19:57Z","timestamp":1605435597000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8516480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/cbmi.2018.8516480","relation":{},"subject":[],"published":{"date-parts":[[2018,9]]}}}