{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T18:56:54Z","timestamp":1768071414048,"version":"3.49.0"},"reference-count":39,"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":["61966004"],"award-info":[{"award-number":["61966004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61663004"],"award-info":[{"award-number":["61663004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61762078"],"award-info":[{"award-number":["61762078"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61866004"],"award-info":[{"award-number":["61866004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004607","name":"Natural Science Foundation of Guangxi Province","doi-asserted-by":"publisher","award":["2019GXNSFDA245018"],"award-info":[{"award-number":["2019GXNSFDA245018"]}],"id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004607","name":"Natural Science Foundation of Guangxi Province","doi-asserted-by":"publisher","award":["2017GXNSFAA198365"],"award-info":[{"award-number":["2017GXNSFAA198365"]}],"id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004607","name":"Natural Science Foundation of Guangxi Province","doi-asserted-by":"publisher","award":["2018GXNSFDA281009"],"award-info":[{"award-number":["2018GXNSFDA281009"]}],"id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Fund of Guangxi Key Lab of Multisource Information Mining and Security","award":["16-A-03-02"],"award-info":[{"award-number":["16-A-03-02"]}]},{"name":"Research Fund of Guangxi Key Lab of Multisource Information Mining and Security","award":["MIMS18-08"],"award-info":[{"award-number":["MIMS18-08"]}]},{"name":"Research Fund of Guangxi Key Lab of Multisource Information Mining and Security","award":["MIMS19-02"],"award-info":[{"award-number":["MIMS19-02"]}]},{"name":"Guangxi Bagui Scholar Teams for Innovation and Research Project, Guangxi Collaborative Innovation Center of Multi-source Information Integration and Intelligent Processing"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2969808","type":"journal-article","created":{"date-parts":[[2020,1,27]],"date-time":"2020-01-27T20:41:25Z","timestamp":1580157685000},"page":"21847-21856","source":"Crossref","is-referenced-by-count":26,"title":["Combining Global and Local Similarity for Cross-Media Retrieval"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5313-6134","authenticated-orcid":false,"given":"Zhixin","family":"Li","sequence":"first","affiliation":[]},{"given":"Feng","family":"Ling","sequence":"additional","affiliation":[]},{"given":"Canlong","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5104-8982","authenticated-orcid":false,"given":"Huifang","family":"Ma","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Dual-path convolutional image-text embedding with instance loss","author":"zheng","year":"2017","journal-title":"arXiv 1711 05535"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-4764-0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852118"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref37","first-page":"649","article-title":"Character-level convolutional networks for text classification","author":"zhang","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"Self-attention generative adversarial networks","author":"zhang","year":"2018","journal-title":"arXiv 1805 08318"},{"key":"ref35","article-title":"Recurrent neural network regularization","author":"zaremba","year":"2014","journal-title":"arXiv 1409 2329"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/978-3-319-24261-3_7","article-title":"Deep metric learning using triplet network","author":"hoffer","year":"2015","journal-title":"Proc Int Workshops Similarity-Based Pattern Recognit"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref14","article-title":"Bidirectional LSTM-CRF models for sequence tagging","author":"huang","year":"2015","journal-title":"arXiv 1508 01991"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref17","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref28","article-title":"Order-embeddings of images and language","author":"vendrov","year":"2015","journal-title":"arXiv 1511 06361"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref27","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detectionwith region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","article-title":"Vse: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"2017","journal-title":"arXiv 1707 05612"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916887"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref8","first-page":"409","article-title":"Discriminant adaptive nearest neighbor classification and regression","author":"hastie","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref2","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref20","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref24","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2014","journal-title":"arXiv 1412 6632"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08970540.pdf?arnumber=8970540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:51:13Z","timestamp":1639770673000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8970540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2969808","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}