{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T09:44:35Z","timestamp":1769161475013,"version":"3.49.0"},"reference-count":32,"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\/wacv45572.2020.9093548","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"1507-1515","source":"Crossref","is-referenced-by-count":24,"title":["MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding"],"prefix":"10.1109","author":[{"given":"Geondo","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chihye","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daeshik","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wonjun","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","article-title":"Dual-path convolutional image-text embedding","author":"zheng","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref30","article-title":"Univse: Robust visual semantic embeddings via structured semantic representations","author":"wu","year":"2019","journal-title":"CVPR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref12","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Skip-thought vectors","author":"kiros","year":"2015","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1477"},{"key":"ref16","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref17","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"ICLRE"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683869"},{"key":"ref19","article-title":"Learning natural language inference using bidirectional LSTM model and inner-attention","author":"liu","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00805"},{"key":"ref4","article-title":"VSE++: improved visual-semantic embeddings","author":"faghri","year":"2018","journal-title":"BMVC"},{"key":"ref27","article-title":"Learning two-branch neural networks for image-text matching tasks","author":"wang","year":"2018","journal-title":"TPAMI"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00419"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","article-title":"Look, imagine and match: Improving textual-visual cross-modal retrieval with generative models","author":"gu","year":"2017","journal-title":"CVPR"},{"key":"ref2","article-title":"Linking image and text with 2-way nets","author":"eisenschtat","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"ICLRE"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref21","article-title":"BAM: bottleneck attention module","author":"park","year":"2018","journal-title":"BMVC"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref23","article-title":"Weakly supervised memory networks","author":"sukhbaatar","year":"2015","journal-title":"NeurIPS"},{"key":"ref26","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2015","journal-title":"ICLRE"},{"key":"ref25","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"}],"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\/09093548.pdf?arnumber=9093548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:15:53Z","timestamp":1656602153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093548\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093548","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}