{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:15:19Z","timestamp":1775578519393,"version":"3.50.1"},"reference-count":103,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62076192"],"award-info":[{"award-number":["62076192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Key Program of National Natural Science of China","award":["61836009"],"award-info":[{"award-number":["61836009"]}]},{"name":"Key Scientific Technological Innovation Research Project by Ministry of Education"},{"name":"Program for Cheung Kong Scholars and Innovative Research Team in University","award":["IRT_15R53"],"award-info":[{"award-number":["IRT_15R53"]}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China"},{"name":"CAAI-Huawei MindSpore Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3386339","type":"journal-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T17:30:33Z","timestamp":1712943033000},"page":"9135-9149","source":"Crossref","is-referenced-by-count":21,"title":["A Knowledge-Based Hierarchical Causal Inference Network for Video Action Recognition"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2604-4381","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6025-3881","authenticated-orcid":false,"given":"Qianyue","family":"Bao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6095-8830","authenticated-orcid":false,"given":"Yuwei","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5472-1426","authenticated-orcid":false,"given":"Puhua","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi'an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053249"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548199"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/c2019-0-00628-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3253054"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3059742"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2965434"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3204684"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180585"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2973828"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3086618"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3491228"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.339"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185638"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3135248"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref19","first-page":"3020","article-title":"Learning representations for counterfactual inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Johansson","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2307\/2669380"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612167"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00807"},{"key":"ref23","article-title":"FHA-kitchens: A novel dataset for fine-grained hand action recognition in kitchen scenes","author":"Zhe","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3105637"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3234362"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-013-0370-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296680"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.226"},{"key":"ref31","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 27: Annu. Conf. Neural Inf. Process. Syst.","author":"Simonyan","year":"2014"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref37","article-title":"Temporal 3D ConvNets: New architecture and transfer learning for video classification","author":"Diba","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref39","article-title":"ConvNet architecture search for spatiotemporal feature learning","author":"Tran","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.161"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2778563"},{"key":"ref44","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Bertasius","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475272"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref49","article-title":"UniFormer: Unified transformer for efficient spatiotemporal representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3302471"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2952088"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050058"},{"key":"ref54","article-title":"Zero-shot action recognition from diverse object-scene compositions","volume-title":"Proc. 32nd Brit. Mach. Vis. Conf.","author":"Bretti","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_39"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.158"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3070688"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3501714.3501736"},{"key":"ref59","volume-title":"Models, Reasoning and Inference","volume":"19","author":"Pearl","year":"2000"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3487042"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475328"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3290012"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.265"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2021.103581"},{"key":"ref66","article-title":"Question-conditioned counterfactual image generation for VQA","author":"Pan","year":"2019"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3136717"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00471"},{"key":"ref70","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2020"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3284594"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3330534"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475472"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref75","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref79","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00685"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_18"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12232"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3076522"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00346"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25069-9_36"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100842"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3057503"},{"key":"ref93","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Tong","year":"2022"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01345"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.10.037"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612490"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_9"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00632"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007826"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01352"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00336"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10496835.pdf?arnumber=10496835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T04:33:31Z","timestamp":1725078811000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10496835\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":103,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3386339","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}