{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T16:10:49Z","timestamp":1788019849032,"version":"build-2784847793"},"reference-count":90,"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":["62306240"],"award-info":[{"award-number":["62306240"]}],"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":["U23B2013"],"award-info":[{"award-number":["U23B2013"]}],"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":["U19B2037"],"award-info":[{"award-number":["U19B2037"]}],"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":["62272013"],"award-info":[{"award-number":["62272013"]}],"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":["61925201"],"award-info":[{"award-number":["61925201"]}],"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":["62132001"],"award-info":[{"award-number":["62132001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023TQ0272"],"award-info":[{"award-number":["2023TQ0272"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["D5000220431"],"award-info":[{"award-number":["D5000220431"]}],"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":[[2024]]},"DOI":"10.1109\/tip.2024.3374070","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T16:29:12Z","timestamp":1710779352000},"page":"2213-2225","source":"Crossref","is-referenced-by-count":59,"title":["Toward Video Anomaly Retrieval From Video Anomaly Detection: New Benchmarks and Model"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2938-6798","authenticated-orcid":false,"given":"Peng","family":"Wu","sequence":"first","affiliation":[{"name":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6834-5350","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangzhou Institute of Technology, Xidian University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8502-5685","authenticated-orcid":false,"given":"Xiangteng","family":"He","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7658-3845","authenticated-orcid":false,"given":"Yuxin","family":"Peng","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9218-9132","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2977-8057","authenticated-orcid":false,"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2670780"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933554"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01255"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/162"},{"key":"ref11","article-title":"Learning a text-video embedding from incomplete and heterogeneous data","author":"Miech","year":"2018","journal-title":"arXiv:1804.02516"},{"key":"ref12","article-title":"Use what you have: Video retrieval using representations from collaborative experts","author":"Liu","year":"2019","journal-title":"arXiv:1907.13487"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532078"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142420"},{"key":"ref18","article-title":"Dynamic neural networks: A survey","author":"Han","year":"2021","journal-title":"arXiv:2102.04906"},{"key":"ref19","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","author":"Rao","year":"2021","journal-title":"arXiv:2106.02034"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00154"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref22","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref23","article-title":"MILAN: Masked image pretraining on language assisted representation","author":"Hou","year":"2022","journal-title":"arXiv:2208.06049"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2948286"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00803"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00179"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_29"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_24"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01402"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00509"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072863"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062192"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3226411"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3227044"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2705068"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1601787"},{"key":"ref37","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3278474"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01463"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2227"},{"key":"ref41","article-title":"Masking modalities for cross-modal video retrieval","author":"Gabeur","year":"2021","journal-title":"arXiv:2111.01300"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1352"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3275071"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref46","article-title":"Learning in audio-visual context: A review, analysis, and new perspective","author":"Wei","year":"2022","journal-title":"arXiv:2208.09579"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350906"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00054"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475515"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475241"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/154"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref61","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020","journal-title":"arXiv:2002.06353"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531960"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547976"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01186"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3187288"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00365"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref72","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Kim"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548369"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2020.3020423"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2018.2869001"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195099713.001.0001"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"ref88","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref90","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv:1301.3781"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10471334.pdf?arnumber=10471334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T16:48:02Z","timestamp":1711644482000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10471334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3374070","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}