{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:22:36Z","timestamp":1772907756459,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62176139"],"award-info":[{"award-number":["62176139"]}],"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":["62106128"],"award-info":[{"award-number":["62106128"]}],"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":["62176141"],"award-info":[{"award-number":["62176141"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major basic research project of Shandong Natural Science Foundation","award":["ZR2021ZD15"],"award-info":[{"award-number":["ZR2021ZD15"]}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2021QF001"],"award-info":[{"award-number":["ZR2021QF001"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2021QNRC001"],"award-info":[{"award-number":["2021QNRC001"]}]},{"name":"Shandong Provincial Natural Science Foundation for Distinguished Young Scholars","award":["ZR2021JQ26"],"award-info":[{"award-number":["ZR2021JQ26"]}]},{"name":"Shandong Province Science and Technology Small and Medium-sized Enterprise Innovation Capacity Enhancement Project","award":["2023TSGC0115"],"award-info":[{"award-number":["2023TSGC0115"]}]},{"name":"Shandong Province Higher Education Institutions Youth Entrepreneurship and Technology Support Program","award":["2023KJ027"],"award-info":[{"award-number":["2023KJ027"]}]},{"DOI":"10.13039\/501100010040","name":"Taishan Scholar Project of Shandong Province","doi-asserted-by":"publisher","award":["tsqn202103088"],"award-info":[{"award-number":["tsqn202103088"]}],"id":[{"id":"10.13039\/501100010040","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Project Programme of the State Key Laboratory of Internet of Things for Smart City","award":["SKL-IoTSC(UM)-2021-2023\/ORP\/GA05\/2022)"],"award-info":[{"award-number":["SKL-IoTSC(UM)-2021-2023\/ORP\/GA05\/2022)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3387696","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T17:35:25Z","timestamp":1713375325000},"page":"9268-9279","source":"Crossref","is-referenced-by-count":6,"title":["Learning Feature Semantic Matching for Spatio-Temporal Video Grounding"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8163-3050","authenticated-orcid":false,"given":"Tong","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8846-8294","authenticated-orcid":false,"given":"Hao","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2725-6458","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8554-7827","authenticated-orcid":false,"given":"Jialin","family":"Gao","sequence":"additional","affiliation":[{"name":"AI Singapore, National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9543-6960","authenticated-orcid":false,"given":"Xiankai","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9644-9723","authenticated-orcid":false,"given":"Xiushan","family":"Nie","sequence":"additional","affiliation":[{"name":"Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Company, Ltd., Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8465-1294","authenticated-orcid":false,"given":"Yilong","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.444"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2647386"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547969"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25251"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3275874"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1183"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.69"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350999"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.162"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00434"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250518"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075470"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"ref22","first-page":"29192","article-title":"Embracing consistency: A one-stage approach for spatio-temporal video grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jin","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00156"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085907"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222664"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3205404"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref33","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189245"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3256092"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532083"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.324"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3258628"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref40","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3204444"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref47","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref48","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547943"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.545"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018175"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/149"},{"key":"ref60","article-title":"RoBERTa: A. robustly optimized bert pretraining approach","author":"Liu","year":"2019"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10504631.pdf?arnumber=10504631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T04:31:40Z","timestamp":1725078700000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10504631\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3387696","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}