{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T17:02:50Z","timestamp":1774112570811,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Project of China","award":["2018AAA0101900"],"award-info":[{"award-number":["2018AAA0101900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876177"],"award-info":[{"award-number":["61876177"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4202034"],"award-info":[{"award-number":["4202034"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2020B1515020048"],"award-info":[{"award-number":["2020B1515020048"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities, Zhejiang Lab","doi-asserted-by":"publisher","award":["2019KD0AB04"],"award-info":[{"award-number":["2019KD0AB04"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tcsvt.2021.3085907","type":"journal-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T00:54:06Z","timestamp":1622768046000},"page":"8238-8249","source":"Crossref","is-referenced-by-count":80,"title":["Human-Centric Spatio-Temporal Video Grounding With Visual Transformers"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9903-802X","authenticated-orcid":false,"given":"Zongheng","family":"Tang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"given":"Yue","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9180-2935","authenticated-orcid":false,"given":"Si","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"given":"Xiaojie","family":"Jin","sequence":"additional","affiliation":[{"name":"ByteDance AI Lab, Beijing, China"}]},{"given":"Hongxu","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"given":"Qian","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2775-9730","authenticated-orcid":false,"given":"Dong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1518"},{"key":"ref38","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref36","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325056"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref12","article-title":"A real-time cross-modality correlation filtering method for referring expression comprehension","author":"liao","year":"2019","journal-title":"arXiv 1909 07072"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1183"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1219"},{"key":"ref15","first-page":"104","article-title":"Uniter: Universal image-text representation learning","author":"chen","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref17","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"harold li","year":"2019","journal-title":"arXiv 1908 03557"},{"key":"ref18","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"su","year":"2019","journal-title":"arXiv 1908 08530"},{"key":"ref19","first-page":"13","article-title":"VILBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350985"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref29","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016","journal-title":"arXiv 1609 02907"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3013142"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref45","article-title":"Learning 2D temporal adjacent networks for moment localization with natural language","author":"zhang","year":"2019","journal-title":"arXiv 1912 03590"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.375"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref41","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018175"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.162"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9973795\/09446308.pdf?arnumber=9446308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:11:29Z","timestamp":1672081889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9446308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":46,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2021.3085907","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}