{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T01:37:38Z","timestamp":1772674658807,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2016YFB0800404"],"award-info":[{"award-number":["2016YFB0800404"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1936212"],"award-info":[{"award-number":["U1936212"]}],"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":["61532005"],"award-info":[{"award-number":["61532005"]}],"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":["61972022"],"award-info":[{"award-number":["61972022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201807095006"],"award-info":[{"award-number":["201807095006"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2018JBZ001"],"award-info":[{"award-number":["2018JBZ001"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2018YJS028"],"award-info":[{"award-number":["2018YJS028"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1109\/tmm.2019.2957948","type":"journal-article","created":{"date-parts":[[2019,12,12]],"date-time":"2019-12-12T20:44:46Z","timestamp":1576183486000},"page":"2354-2365","source":"Crossref","is-referenced-by-count":20,"title":["Rich Features Embedding for Cross-Modal Retrieval: A Simple Baseline"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6212-6499","authenticated-orcid":false,"given":"Xin","family":"Fu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2812-8781","authenticated-orcid":false,"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yufeng","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3803-9763","authenticated-orcid":false,"given":"Shikui","family":"Wei","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019356"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_36"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2890144"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00446"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref36","first-page":"817","article-title":"Grounding of textual phrases in images by reconstruction","author":"rohrbach","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2775109"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.483"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2610969"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.348"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2018.112142537"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_17"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.170"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref21","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"0","journal-title":"Proc Brit Mach Vision Conf"},{"key":"ref24","article-title":"Stacked cross attention for image-text matching","author":"lee","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00805"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.267"},{"key":"ref50","first-page":"3294","article-title":"Skip-thought vectors","author":"kiros","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref59","first-page":"686","article-title":"Deep cross-modal projection learning for image-text matching","author":"zhang","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref56","article-title":"Order-embeddings of images and language","author":"vendrov","year":"0","journal-title":"Proc"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref54","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","author":"mao","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2014.2313866"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2606648"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240535"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2535864"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2646219"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247923"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"ref18","first-page":"1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.201"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref3","article-title":"Dual-path convolutional image-text embedding","author":"zheng","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2742704"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref8","first-page":"53","article-title":"Exploiting local features from deep networks for image retrieval","author":"yue-hei ng","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recognit"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683898"},{"key":"ref49","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2519449"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.389"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2852503"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1109\/TKDE.2018.2842190","article-title":"Hierarchical multi-clue modelling for POI popularity prediction with heterogeneous tourist information","volume":"31","author":"yang","year":"2019","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9173579\/08931635.pdf?arnumber=8931635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:57:39Z","timestamp":1651075059000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8931635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9]]},"references-count":59,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2957948","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9]]}}}