{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T04:48:21Z","timestamp":1749703701334,"version":"3.37.3"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61671385","61571354"],"award-info":[{"award-number":["61671385","61571354"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010877","name":"Science, Technology, and Innovation Commission of Shenzhen Municipality","doi-asserted-by":"publisher","award":["JCYJ20190806160210899"],"award-info":[{"award-number":["JCYJ20190806160210899"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2992187","type":"journal-article","created":{"date-parts":[[2020,5,5]],"date-time":"2020-05-05T00:00:54Z","timestamp":1588636854000},"page":"84642-84651","source":"Crossref","is-referenced-by-count":7,"title":["Boosting Cross-Modal Retrieval With MVSE++ and Reciprocal Neighbors"],"prefix":"10.1109","volume":"8","author":[{"given":"Wei","family":"Wei","sequence":"first","affiliation":[]},{"given":"Mengmeng","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Xiangnan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Heng","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3217-0368","authenticated-orcid":false,"given":"Chunna","family":"Tian","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"3013","article-title":"Object retrieval and localization with spatially-constrained similarity measure and k-NN re-ranking","author":"shen","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995373"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref32","article-title":"Multiple object recognition with visual attention","volume":"abs 1412 7755","author":"ba","year":"2015","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751140"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.382970"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019549"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240535"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2813971"},{"key":"ref28","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00628"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00177"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.374"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2097"},{"key":"ref1","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst Meeting Held"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref22","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","volume":"abs 1412 6632","author":"mao","year":"2015","journal-title":"CoRR"},{"key":"ref21","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"2014","journal-title":"Proc ICML"},{"key":"ref24","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"2764","article-title":"Wsabie: Scaling up to large vocabulary image annotation","volume":"11","author":"weston","year":"2011","journal-title":"Proc IJCAI"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.386"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.104"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref51","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref55","article-title":"Linking image and text with 2-way nets","author":"eisenschtat","year":"2016","journal-title":"arXiv 1608 07973"},{"key":"ref54","first-page":"1","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2015","journal-title":"Proc ICLR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2616298"},{"key":"ref11","first-page":"2222","article-title":"Multimodal learning with deep Boltzmann machines","author":"srivastava","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.441"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2375793"},{"key":"ref16","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"},{"key":"ref17","article-title":"VSE: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2017","journal-title":"arXiv 1707 05612"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.452"},{"key":"ref4","article-title":"The impact of frequency on summarization","volume":"101","author":"nenkova","year":"2005"},{"key":"ref3","first-page":"359","article-title":"Collective generation of natural image descriptions","author":"kuznetsova","year":"2012","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482228"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref49","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"ref9","first-page":"1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn (ICML)"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref45","first-page":"18","article-title":"ImageNet: Crowdsourcing, benchmarking & other cool things","volume":"16","author":"fei-fei","year":"2010","journal-title":"CMU VASC Seminar"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2605058"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408891"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.389"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248018"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09085386.pdf?arnumber=9085386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:51:50Z","timestamp":1639770710000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9085386\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2992187","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}