{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:40:23Z","timestamp":1730230823603,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054758","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"4452-4456","source":"Crossref","is-referenced-by-count":3,"title":["Exploring Entity-Level Spatial Relationships for Image-Text Matching"],"prefix":"10.1109","author":[{"given":"Yaxian","family":"Xia","sequence":"first","affiliation":[]},{"given":"Lun","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Wenmin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiao-Yong","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"1564","article-title":"Bilinear attention networks","volume":"31","author":"kim","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.576"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref16","article-title":"Learning deep structure-preserving image-text embeddings","author":"wang","year":"2015","journal-title":"CoRR"},{"key":"ref17","article-title":"Vse++: Improved visual-semantic embeddings","author":"faghri","year":"2017","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref19","first-page":"2017","article-title":"Learning semantic concepts and order for image and sentence matching","author":"yan","year":"0","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref3","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.386"},{"key":"ref7","first-page":"2018","article-title":"Universal transformers","author":"dehghani","year":"0","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref1","first-page":"2014","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"0","journal-title":"CoRR"},{"key":"ref9","article-title":"Stacked cross attention for imagetext matching","author":"lee","year":"2018","journal-title":"the European Conference on Computer Vision (ECCV)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref23","first-page":"2015","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"CoRR"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054758.pdf?arnumber=9054758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:15:47Z","timestamp":1656360947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054758","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}