{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:46:27Z","timestamp":1785912387890,"version":"3.56.0"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/wacvw68408.2026.00011","type":"proceedings-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:12:14Z","timestamp":1785870734000},"page":"55-65","source":"Crossref","is-referenced-by-count":0,"title":["PrismVAU: Prompt-Refined Inference System for Multimodal Video Anomaly Understanding"],"prefix":"10.1109","author":[{"given":"I\u00f1aki","family":"Erregue","sequence":"first","affiliation":[{"name":"Universitat de Barcelona"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamal","family":"Nasrollahi","sequence":"additional","affiliation":[{"name":"Aalborg University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergio","family":"Escalera","sequence":"additional","affiliation":[{"name":"Universitat de Barcelona"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models are few-shot learners","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Brown"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01953"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01734"},{"key":"ref4","article-title":"Understanding transferable representation learning and zeroshot transfer in CLIP","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen","year":"2024"},{"key":"ref5","article-title":"Exploring what why and how: A multifaceted benchmark for causation understanding of video anomaly","author":"Du","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01778"},{"key":"ref7","article-title":"Promptbreeder: selfreferential self-improvement via prompt evolution","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Fernando","year":"2024"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.32388\/JG3I10","volume-title":"Video anomaly detection with structured keywords","author":"Foltz","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3389\/fimag.2025.1547166"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3143990"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3462203.3475892"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"ref16","volume-title":"Video anomaly detection and explanation via large language models","author":"Lv","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01517"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00775"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539872"},{"key":"ref20","article-title":"Improving textto-image consistency via automatic prompt optimization","author":"Ma\u00f1as","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00094"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3451935"},{"key":"ref24","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093457"},{"key":"ref26","article-title":"Prompt smart, pay less: Cost-aware APO for real-world applications","volume-title":"First International KDD Workshop on Prompt Optimization","author":"Singh","year":"2025"},{"key":"ref27","first-page":"16857","article-title":"Mpnet: Masked and permuted pre-training for language understanding","volume-title":"Advances in Neural Information Processing Systems","author":"Song","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02188"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4435"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43153-1_5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062192"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01732"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"ref38","volume-title":"Prompts as autooptimized training hyperparameters: Training best-in-class ir models from scratch with 10 gold labels","author":"Xian","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3522384"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00509"},{"key":"ref41","article-title":"Large language models as optimizers","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yang","year":"2024"},{"key":"ref42","first-page":"304","article-title":"Follow the rules: Reasoning for video anomaly detection with large language models","volume-title":"Computer Vision - ECCV 2024: 18th European Conference, Milan, Italy","author":"Yang","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01788"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967556"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00811"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2025.3589634"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01753"},{"key":"ref48","article-title":"Videollama 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01561"},{"key":"ref50","article-title":"Holmes-vad: Towards unbiased and explainable video anomaly detection via multi-modal llm","volume":"abs\/2406.12235","author":"Zhang","year":"2024","journal-title":"CoRR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01292"},{"key":"ref52","article-title":"Large language models are human-level prompt engineers","volume-title":"NeurIPS 2022 Foundation Models for Decision Making Workshop","author":"Zhou","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2856"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11617369\/11617396\/11617746.pdf?arnumber=11617746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:59:57Z","timestamp":1785909597000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11617746\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/wacvw68408.2026.00011","relation":{},"subject":[],"published":{"date-parts":[[2026,3]]}}}