{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:33:54Z","timestamp":1778081634025,"version":"3.51.4"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"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":[[2025,6,10]]},"DOI":"10.1109\/cvpr52734.2025.00811","type":"proceedings-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T17:26:42Z","timestamp":1755106002000},"page":"8679-8688","source":"Crossref","is-referenced-by-count":16,"title":["VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Muchao","family":"Ye","sequence":"first","affiliation":[{"name":"The University of Iowa"}]},{"given":"Weiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Tübingen"}]},{"given":"Pan","family":"He","sequence":"additional","affiliation":[{"name":"Auburn University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00495"},{"key":"ref3","article-title":"The surprising effectiveness of multimodal large language models for video moment retrieval","author":"Boris","year":"2024"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01734"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25112"},{"key":"ref7","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"CVPR","author":"Chen"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref11","volume-title":"Digital image processing","author":"Gonzalez","year":"2009"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01309"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref14","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222289"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_20"},{"key":"ref18","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref21","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref22","article-title":"Deep hyperspherical learning","author":"Liu","year":"2017","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"ref24","article-title":"Parameter-efficient orthogonal finetuning via butterfly factorization","volume-title":"ICLR","author":"Liu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"ref26","article-title":"Video anomaly detection and explanation via large language models","author":"Lv","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00775"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref29","article-title":"Controlling text-to-image diffusion by orthogonal finetuning","author":"Qiu","year":"2023","journal-title":"NeurIPS"},{"key":"ref30","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref33","first-page":"139751","article-title":"Hawk: Learning to understand open-world video anomalies","volume":"37","author":"Tang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109567"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00550"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43153-1_5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00829"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref40","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_42"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01732"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"ref45","article-title":"Verbalized machine learning: Revisiting machine learning with language models","author":"Xiao","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_18"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01788"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350899"},{"key":"ref49","article-title":"Textgrad: Automatic \u201cdifferentiation\u201d via text","author":"Yuksekgonul","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_22"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01433"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01753"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01561"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref55","article-title":"Holmes-vad: Towards unbiased and explainable video anomaly detection via multi-modal llm","author":"Zhang","year":"2024"},{"key":"ref56","article-title":"Multiscale video anomaly detection by multi-grained spatiotemporal representation learning","volume-title":"CVPR","author":"Zhang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00133"},{"key":"ref58","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume-title":"ICLR","author":"Zhu"}],"event":{"name":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Nashville, TN, USA","start":{"date-parts":[[2025,6,10]]},"end":{"date-parts":[[2025,6,17]]}},"container-title":["2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11091818\/11091608\/11094987.pdf?arnumber=11094987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T04:56:14Z","timestamp":1755233774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11094987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,10]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/cvpr52734.2025.00811","relation":{},"subject":[],"published":{"date-parts":[[2025,6,10]]}}}