{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T13:27:15Z","timestamp":1773840435651,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["62132016"],"award-info":[{"award-number":["62132016"]}],"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":["62171343"],"award-info":[{"award-number":["62171343"]}],"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":["62071361"],"award-info":[{"award-number":["62071361"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Shaanxi","award":["2021ZDLGY01-03"],"award-info":[{"award-number":["2021ZDLGY01-03"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZDRC2102"],"award-info":[{"award-number":["ZDRC2102"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3191841","type":"journal-article","created":{"date-parts":[[2022,8,4]],"date-time":"2022-08-04T19:23:06Z","timestamp":1659640986000},"page":"5178-5188","source":"Crossref","is-referenced-by-count":22,"title":["HiSA: Hierarchically Semantic Associating for Video Temporal Grounding"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6898-3443","authenticated-orcid":false,"given":"Zhe","family":"Xu","sequence":"first","affiliation":[{"name":"School of Electronic Engineering, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5062-0270","authenticated-orcid":false,"given":"Da","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7228-5322","authenticated-orcid":false,"given":"Kun","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2620-3247","authenticated-orcid":false,"given":"Cheng","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Xidian University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2093-2839","authenticated-orcid":false,"given":"Hui","family":"Xue","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.873449"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2917867"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_52"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.106"},{"key":"ref6","first-page":"1","article-title":"The visual object tracking VOT2015 challenge results","volume-title":"Proc. ICCVW","author":"Kristan"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2922108"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016486"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2839534"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2404779"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref17","article-title":"TVQA: Spatio-temporal grounding for video question answering","author":"Lei","year":"2019","journal-title":"arXiv:1904.11574"},{"key":"ref18","first-page":"1","article-title":"STAR: A benchmark for situated reasoning in real-world videos","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Wu"},{"key":"ref19","first-page":"1","article-title":"Grounding physical concepts of objects and events through dynamic visual reasoning","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref20","first-page":"887","article-title":"Dynamic visual reasoning by learning differentiable physics models from video and language","volume-title":"Proc. NeurIPS","volume":"34","author":"Ding"},{"key":"ref21","first-page":"1","article-title":"CLEVRER: Collision events for video representation and reasoning","volume-title":"Proc. ICLR","author":"Yi"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"ref27","article-title":"Tripping through time: Efficient localization of activities in videos","author":"Hahn","year":"2019","journal-title":"arXiv:1904.09936"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063631"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref36","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume-title":"Proc. ICML","author":"Locatello"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_3"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00649"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00853"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01500"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.141"},{"key":"ref43","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","author":"Chen","year":"2016","journal-title":"arXiv:1606.03657"},{"key":"ref44","article-title":"Disentangling by factorising","author":"Kim","year":"2018","journal-title":"arXiv:1802.05983"},{"key":"ref45","article-title":"CausalVAE: Structured causal disentanglement in variational autoencoder","author":"Yang","year":"2020","journal-title":"arXiv:2004.08697"},{"key":"ref46","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013","journal-title":"arXiv:1312.6114"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00657"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00949"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16189"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref52","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"arXiv:2002.05709"},{"key":"ref53","article-title":"Supervised contrastive learning","author":"Khosla","year":"2020","journal-title":"arXiv:2004.11362"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.201"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1183"},{"key":"ref56","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref63","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","author":"Paszke"},{"key":"ref64","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref67","article-title":"Semantic conditioned dynamic modulation for temporal sentence grounding in videos","author":"Yuan","year":"2019","journal-title":"arXiv:1910.14303"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00750"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"issue":"11","key":"ref72","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal Of Mach. Learn. Res."}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09846867.pdf?arnumber=9846867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T09:10:16Z","timestamp":1706778616000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9846867\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3191841","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}