{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T11:29:18Z","timestamp":1748863758482},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682424","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"source":"Crossref","is-referenced-by-count":3,"title":["Multi-step Self-attention Network for Cross-modal Retrieval Based on a Limited Text Space"],"prefix":"10.1109","author":[{"given":"Zheng","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenmin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64689-3_24"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref12","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3078993"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/34.895972"},{"key":"ref19","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2017"},{"key":"ref4","article-title":"Dual-path convolutional image-text embedding","author":"zheng","year":"2017"},{"key":"ref3","article-title":"Deep captioning with multi-modal recurrent neural networks (m-rnn)","author":"mao","year":"2014"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref8","article-title":"Dual attention networks for multimodal reasoning and matching","author":"nam","year":"2016"},{"key":"ref7","article-title":"Instance-aware image and sentence matching with selective multi-modal lstm","author":"huang","year":"2016"},{"key":"ref2","article-title":"Word2visualvec: Cross-media retrieval by visual feature prediction","author":"dong","year":"2016"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref9","article-title":"Modality-specific cross-modal similarity measurement with recurrent attention network","author":"peng","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref21","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682424.pdf?arnumber=8682424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:14:54Z","timestamp":1657854894000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682424","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}