{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:49:52Z","timestamp":1777654192744,"version":"3.51.4"},"reference-count":53,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"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":["61751209"],"award-info":[{"award-number":["61751209"]}],"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":["61836002"],"award-info":[{"award-number":["61836002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LR19F020006"],"award-info":[{"award-number":["LR19F020006"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joint Research Program of ZJU"},{"DOI":"10.13039\/501100012455","name":"China Knowledge Centre for Engineering Sciences and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012455","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tip.2020.2965987","type":"journal-article","created":{"date-parts":[[2020,1,17]],"date-time":"2020-01-17T21:11:19Z","timestamp":1579295479000},"page":"3750-3762","source":"Crossref","is-referenced-by-count":46,"title":["Moment Retrieval via Cross-Modal Interaction Networks With Query Reconstruction"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3461-8952","authenticated-orcid":false,"given":"Zhijie","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6121-0384","authenticated-orcid":false,"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8308-768X","authenticated-orcid":false,"given":"Zijian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deng","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298792"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.507"},{"key":"ref33","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc NIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00124"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref37","first-page":"2025","article-title":"Unsupervised alignment of actions in video with text descriptions","author":"song","year":"2016","journal-title":"Proc IJCAI"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.509"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646442"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00177"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref2","first-page":"6","article-title":"Jointly modeling deep video and compositional text to bridge vision and language in a unified framework","volume":"5","author":"xu","year":"2015","journal-title":"Proc AAAI"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.340"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.298"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1219044.1219075"},{"key":"ref53","first-page":"3294","article-title":"Skip-thought vectors","author":"kiros","year":"2015","journal-title":"Proc NIPS"},{"key":"ref52","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref11","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc ICLR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref12","article-title":"Graph attention networks","author":"velickovic","year":"2018","journal-title":"Proc ICLR"},{"key":"ref13","first-page":"684","article-title":"Exploring visual relationship for image captioning","author":"yao","year":"2018","journal-title":"Proc ECCV"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1159"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46604-0_46"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1168"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref46","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"Proc NIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/512"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref43","first-page":"534","article-title":"Semantic conditioned dynamic modulation for temporal sentence grounding in videos","author":"yuan","year":"2019","journal-title":"Proc NIPS"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/08962274.pdf?arnumber=8962274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:04Z","timestamp":1651070344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8962274\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.2965987","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}