{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T18:09:56Z","timestamp":1768586996291,"version":"3.49.0"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["61972009"],"award-info":[{"award-number":["61972009"]}],"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":["61972448"],"award-info":[{"award-number":["61972448"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2023.3238514","type":"journal-article","created":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T18:48:25Z","timestamp":1674240505000},"page":"8539-8553","source":"Crossref","is-referenced-by-count":29,"title":["Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8179-4508","authenticated-orcid":false,"given":"Daizong","family":"Liu","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3231-5771","authenticated-orcid":false,"given":"Xiang","family":"Fang","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9860-0922","authenticated-orcid":false,"given":"Wei","family":"Hu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8629-4622","authenticated-orcid":false,"given":"Pan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3096087"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063631"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050067"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002669"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414026"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00225"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/149"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3139918"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00176"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00513"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00374"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00273"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","first-page":"1","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3056892"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icip.2019.8803447"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2921539"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016486"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019235"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3038993"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3073867"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1518"},{"key":"ref53","article-title":"Tripping through time: Efficient localization of activities in videos","volume-title":"arXiv:1904.09936","author":"Hahn","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940677"},{"key":"ref57","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Simonyan","year":"2014"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref59","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref60","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Chung","year":"2014"},{"key":"ref61","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414053"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"ref71","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. naacL-HLT","author":"Devlin","year":"2019"},{"key":"ref72","first-page":"1","article-title":"XLNET: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang","year":"2019,"},{"key":"ref73","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Lu","year":"2016"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.773"},{"key":"ref75","article-title":"Explore and match: End-to-end video grounding with transformer","author":"Woo","year":"2022","journal-title":"arXiv:2201.10168"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/10023968.pdf?arnumber=10023968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:02:36Z","timestamp":1703030556000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023968\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3238514","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}