{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T06:29:51Z","timestamp":1788848991511,"version":"build-2803163510"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Zhejiang NSF","award":["LR21F020004"],"award-info":[{"award-number":["LR21F020004"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272411"],"award-info":[{"award-number":["62272411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ant Group and Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tpami.2023.3274139","type":"journal-article","created":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T18:46:32Z","timestamp":1683571592000},"page":"12601-12617","source":"Crossref","is-referenced-by-count":18,"title":["Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2258-1291","authenticated-orcid":false,"given":"Juncheng","family":"Li","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7356-9711","authenticated-orcid":false,"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4093-7557","authenticated-orcid":false,"given":"Linchao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5988-7609","authenticated-orcid":false,"given":"Wenqiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7361-3084","authenticated-orcid":false,"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Domain-adversarial neural networks","author":"Ajakan","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.676"},{"key":"ref4","article-title":"Closure: Assessing systematic generalization of CLEVR models","author":"Bahdanau","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00402"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1515\/9783112316009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref11","article-title":"Weakly supervised dense event captioning in videos","author":"Duan","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref13","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(88)90031-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1157"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2501"},{"key":"ref18","first-page":"1","article-title":"Permutation equivariant models for compositional generalization in language","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gordon"},{"issue":"1","key":"ref19","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref20","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"Grill","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01113"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2627563"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","article-title":"Compositional attention networks for machine reasoning","author":"Drew Hudson","year":"2018"},{"key":"ref27","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref29","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref30","article-title":"Auto-encoding variational bayes","author":"Diederik Kingma","year":"2013"},{"key":"ref31","article-title":"Semantics in generative grammar","volume":"1185","author":"Kratzer","year":"1998"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.288"},{"key":"ref35","first-page":"2873","article-title":"Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lake"},{"key":"ref36","article-title":"Compositional generalization through meta sequence-to-sequence learning","author":"BrendenLake","year":"2019"},{"key":"ref37","article-title":"Fine-grained semantically aligned vision-language pre-training","author":"Li","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00188"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01214"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00304"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1438"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6820"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_34"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref45","article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","author":"Mao","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079041"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00113"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01186"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.4135\/9781412952484.n622"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1009"},{"key":"ref53","article-title":"Learning compositional rules via neural program synthesis","author":"Nye","year":"2020"},{"key":"ref54","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref55","article-title":"Uncovering hidden challenges in query-based video moment retrieval","author":"Otani","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref57","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref58","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-srw.42"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.569"},{"key":"ref62","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume":"28","author":"Sohn","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref63","article-title":"Weakly-supervised multi-level attentional reconstruction network for grounding textual queries in videos","author":"Song","year":"2020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00054"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3475723.3484247"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3038993"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref77","first-page":"18123","article-title":"Counterfactual contrastive learning for weakly-supervised vision-language grounding","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10241246\/10121664.pdf?arnumber=10121664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T17:30:28Z","timestamp":1717781428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10121664\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":78,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3274139","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}