{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:45Z","timestamp":1740169245569,"version":"3.37.3"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971128"],"award-info":[{"award-number":["61971128"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3095229","type":"journal-article","created":{"date-parts":[[2021,7,6]],"date-time":"2021-07-06T19:19:37Z","timestamp":1625599177000},"page":"97430-97443","source":"Crossref","is-referenced-by-count":1,"title":["Coarse-to-Fine Spatial-Temporal Relationship Inference for Temporal Sentence Grounding"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5690-244X","authenticated-orcid":false,"given":"Shanshan","family":"Qi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1474-1806","authenticated-orcid":false,"given":"Luxi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4689-7226","authenticated-orcid":false,"given":"Chunguo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3616-4616","authenticated-orcid":false,"given":"Yongming","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413967"},{"key":"ref32","first-page":"1481","article-title":"WSLLN: Weakly supervised natural language localization networks","author":"gao","year":"2019","journal-title":"Proc Conf Empirical Methods Natural Lang Process (EMNLP)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3023339"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref34","first-page":"690","article-title":"Graph R-CNN for scene graph generation","volume":"11205","author":"yang","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414053"},{"key":"ref27","first-page":"534","article-title":"Semantic conditioned dynamic modulation for temporal sentence grounding in videos","author":"yuan","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414026"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2839534"},{"key":"ref1","first-page":"55","article-title":"Video re-localization","volume":"11218","author":"feng","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2959426"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00139"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2637379"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref50","first-page":"1","article-title":"QANet: Combining local convolution with global self-attention for reading comprehension","author":"yu","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00706"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"ref58","first-page":"3294","article-title":"Skip-thought vectors","author":"kiros","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref57","first-page":"257","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","author":"duchi","year":"2010","journal-title":"Proc Conf Learn Theory (COLT)"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref52","first-page":"144","article-title":"Script data for attribute-based recognition of composite activities","volume":"7572","author":"rohrbach","year":"2012","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref40","first-page":"1024","article-title":"Inductive representation learning on large graphs","author":"hamilton","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref14","first-page":"1984","article-title":"ExCL: Extractive clip localization using natural language descriptions","author":"ghosh","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2943204"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.88"},{"key":"ref18","first-page":"3119","article-title":"Non-autoregressive coarse-to-fine video captioning","author":"yang","year":"2021","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2866370"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00138"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6711"},{"key":"ref5","first-page":"37","article-title":"Two-stream consensus network for weakly-supervised temporal action localization","volume":"12351","author":"zhai","year":"2020","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"ref46","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"ref42","first-page":"593","article-title":"Modeling relational data with graph convolutional networks","volume":"10843","author":"schlichtkrull","year":"2018","journal-title":"Proc Extended Semantic Web Conf (ESWC)"},{"key":"ref41","first-page":"1","article-title":"Graph attention networks","author":"velickovic","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/540"},{"key":"ref43","first-page":"1","article-title":"Gated graph sequence neural networks","author":"li","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09475486.pdf?arnumber=9475486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T18:17:04Z","timestamp":1643221024000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9475486\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3095229","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}