{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:26:44Z","timestamp":1770917204996,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1701600"],"award-info":[{"award-number":["2018YFB1701600"]}],"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":["U20B2069"],"award-info":[{"award-number":["U20B2069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859880","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"1-6","source":"Crossref","is-referenced-by-count":51,"title":["Visual Grounding with Transformers"],"prefix":"10.1109","author":[{"given":"Ye","family":"Du","sequence":"first","affiliation":[{"name":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehua","family":"Fu","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingjie","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2973983"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"ICLRE"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref35","article-title":"Convolutional lstm network: A machine learning approach for precipitation now-castine","author":"xingjian","year":"0","journal-title":"NIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"ref14","article-title":"Ref-nms: Breaking proposal bottlenecks in two-stage referring expression grounding","author":"chen","year":"0","journal-title":"AAAI"},{"key":"ref15","article-title":"Yolov3: An incremental improvement","author":"redmon","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042066"},{"key":"ref18","article-title":"Attention is all you need","author":"ashish","year":"0","journal-title":"NIPS"},{"key":"ref19","article-title":"End-to-end object detection with transformers","author":"carion","year":"0","journal-title":"ECCV"},{"key":"ref28","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"0","journal-title":"ECCV"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref27","article-title":"Generation and comprehension of unambiguous object descriptions","author":"junhua","year":"0","journal-title":"CVPR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/558"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref7","article-title":"Real-time referring expression comprehension by single-stage grounding network","author":"chen","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2803"},{"key":"ref20","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"zhu","year":"0","journal-title":"ICLRE"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref26","article-title":"Modeling context in referring expressions","author":"licheng","year":"0","journal-title":"ECCV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","location":"Taipei, Taiwan","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859880.pdf?arnumber=9859880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:24:48Z","timestamp":1663619088000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859880\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859880","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}