{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:38:49Z","timestamp":1782833929014,"version":"3.54.5"},"reference-count":72,"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":[{"name":"Shuguang Program"},{"DOI":"10.13039\/501100003024","name":"Shanghai Education Development Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003024","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003395","name":"Shanghai Municipal Education Commission","doi-asserted-by":"publisher","award":["18SG01"],"award-info":[{"award-number":["18SG01"]}],"id":[{"id":"10.13039\/501100003395","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Science and Technology Program","award":["21JC1400600"],"award-info":[{"award-number":["21JC1400600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3228167","type":"journal-article","created":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T18:39:18Z","timestamp":1670611158000},"page":"7747-7757","source":"Crossref","is-referenced-by-count":18,"title":["Self-Supervised Learning for Semi-Supervised Temporal Language Grounding"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7470-8023","authenticated-orcid":false,"given":"Fan","family":"Luo","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center on Intelligent Visual Computing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoxiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center on Intelligent Visual Computing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3148-264X","authenticated-orcid":false,"given":"Jingjing","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center on Intelligent Visual Computing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center on Intelligent Visual Computing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Intelligent Information Processing, Shanghai Collaborative Innovation Center on Intelligent Visual Computing, School of Computer Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/wacv45572.2020.9093328"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00418"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3060449"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00834"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref20","first-page":"3063","article-title":"Weakly supervised dense event captioning in videos","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Duan","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1157"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01186"},{"key":"ref23","article-title":"WMAN: Weakly-supervised moment alignment network for text-based video segment retrieval","volume-title":"CoRR","author":"Tan","year":"2019"},{"key":"ref24","first-page":"18123","article-title":"Counterfactual Contrastive Learning for Weakly-Supervised Vision-Language Grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2020"},{"key":"ref25","article-title":"Weakly-supervised multi-level attentional reconstruction network for grounding textual queries in videos","volume-title":"CoRR","author":"Song","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413967"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_10"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00407"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00717"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00194"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00315"},{"key":"ref35","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Tarvainen","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref37","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Sohn","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"ref40","first-page":"10758","article-title":"Consistency-based semi-supervised learning for object detection","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Jeong","year":"2019"},{"key":"ref41","article-title":"A simple semi-supervised learning framework for object detection","volume-title":"CoRR","author":"Sohn"},{"key":"ref42","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Laine","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3475723.3484247"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3038993"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00984"},{"key":"ref57","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref58","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref60","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.4324\/9780080479538"},{"key":"ref62","article-title":"Uncovering hidden challenges in query-based video moment retrieval","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Otani","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00211"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00911"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01039"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/163788"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3120745"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.324"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3096087"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063631"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09978670.pdf?arnumber=9978670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T22:24:46Z","timestamp":1703024686000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9978670\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3228167","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}