{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:29:25Z","timestamp":1774420165263,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890027","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Vision-text Enhancement Network For Weakly Supervised Video Anomaly Detection"],"prefix":"10.1109","author":[{"given":"Yiheng","family":"Chen","sequence":"first","affiliation":[{"name":"Northeast Normal University,ChangChun,China"}]},{"given":"Shuai","family":"Fu","sequence":"additional","affiliation":[{"name":"Changchun Humanities and Sciences College,ChangChun,China"}]},{"given":"Niantong","family":"Qin","sequence":"additional","affiliation":[{"name":"Northeast Normal University,ChangChun,China"}]},{"given":"Xinning","family":"Du","sequence":"additional","affiliation":[{"name":"Northeast Normal University,ChangChun,China"}]},{"given":"Jianping","family":"Ren","sequence":"additional","affiliation":[{"name":"Northeast Normal University,ChangChun,China"}]},{"given":"Shuhua","family":"Liu","sequence":"additional","affiliation":[{"name":"Northeast Normal University,ChangChun,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_42"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3147369"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222289"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01561"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25489"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_22"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00321"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00877"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision[C]","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref17","article-title":"Simvlm: Simple visual language model pretraining with weak supervision[J]","author":"Wang","year":"2021"},{"key":"ref18","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale[J]","author":"Dosovitskiy","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref20","article-title":"Actionclip: A new paradigm for video action recognition[J]","author":"Wang","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_39"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref24","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision[C]","volume-title":"International conference on machine learning","author":"Kim"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00775"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890027.pdf?arnumber=10890027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:46Z","timestamp":1774416406000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890027","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}