{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T08:32:00Z","timestamp":1773131520279,"version":"3.50.1"},"reference-count":78,"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":[{"name":"National Science and Technology","award":["2020AAA0106900"],"award-info":[{"award-number":["2020AAA0106900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U19B2037"],"award-info":[{"award-number":["U19B2037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shaanxi Provincial Key R&D Program","award":["2021KWZ-03"],"award-info":[{"award-number":["2021KWZ-03"]}]},{"name":"Natural Science Basic Research Program of Shaanxi","award":["2021JCW-03"],"award-info":[{"award-number":["2021JCW-03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3414263","type":"journal-article","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T19:29:10Z","timestamp":1719948550000},"page":"10867-10878","source":"Crossref","is-referenced-by-count":1,"title":["Human-Centric Behavior Description in Videos: New Benchmark and Model"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1730-2507","authenticated-orcid":false,"given":"Lingru","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqi","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2938-6798","authenticated-orcid":false,"given":"Peng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9218-9132","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2977-8057","authenticated-orcid":false,"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Ningbo Institute, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2955387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2950530"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01227"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2984093"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933554"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062192"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01402"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374070"},{"key":"ref11","first-page":"76","article-title":"Multi-object tracking by using strong SORT tracker and YOLOv7 network","author":"Hongxu","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3291379"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref15","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Chen","year":"2011"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref20","article-title":"VALOR: Vision-audio-language omni-perception pretraining model and dataset","author":"Chen","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_41"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02082"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245883"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451740"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16788-1_25"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416288"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38989-4_10"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.11.021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2072508.2072515"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301284"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2670780"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.02.006"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2848210"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2846411"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.315"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.878"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102920"},{"key":"ref44","article-title":"Anomaly detection using one-class neural networks","author":"Chalapathy","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1049\/el.2016.0440"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2878538"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"ref49","article-title":"Modeling representation of videos for anomaly detection using deep learning: A review","author":"Chong","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref52","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref54","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3240881"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250518"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3240001"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3243725"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235704"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref65","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Meas. Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref67","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_31"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref70","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3246091"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref73","first-page":"38728","article-title":"mPLUG-2: A modularized multi-modal foundation model across text, image and video","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2023"},{"key":"ref74","article-title":"VAST: A vision-audio-subtitle-text omni-modality foundation model and dataset","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Chen","year":"2024"},{"key":"ref75","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022"},{"key":"ref76","article-title":"VLAB: Enhancing video language pre-training by feature adapting and blending","author":"He","year":"2023"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref78","article-title":"Better use of audio-visual cues: Dense video captioning with bi-modal transformer","author":"Iashin","year":"2020"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10384483\/10582309.pdf?arnumber=10582309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:30:25Z","timestamp":1732667425000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10582309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3414263","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}