{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:22:06Z","timestamp":1778048526570,"version":"3.51.4"},"reference-count":73,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00705","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7301-7311","source":"Crossref","is-referenced-by-count":0,"title":["VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models"],"prefix":"10.1109","author":[{"given":"Ying","family":"Cheng","sequence":"first","affiliation":[{"name":"National Tsing Hua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Ho","family":"Lin","sequence":"additional","affiliation":[{"name":"National Tsing Hua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min-Hung","family":"Chen","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fu-En","family":"Yang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shang-Hong","family":"Lai","sequence":"additional","affiliation":[{"name":"National Tsing Hua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01951"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref4","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3536165"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70738"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3546107"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59081-3_23"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01778"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888431"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01255"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"issue":"2","key":"ref15","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","volume":"1","author":"Hu"},{"key":"ref16","author":"Hu","year":"2024","journal-title":"Minicpm: Unveiling the potential of small language models with scalable training strategies"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02287"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3571946"},{"key":"ref20","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.111"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref24","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01169"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"ref29","author":"Liu","year":"2024","journal-title":"Oryx mllm: On-demand spatial-temporal understanding at arbitrary resolution"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00390"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IAVVC63304.2024.10786395"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"ref33","author":"Lv","year":"2024","journal-title":"Video anomaly detection and explanation via large language models"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00775"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206641"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.104078"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247917"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"ref44","author":"Su","year":"2023","journal-title":"Pandagpt: One model to instruction-follow them all"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4435"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref49","author":"Wang","year":"2024","journal-title":"Visiongpt: Llm-assisted real-time anomaly detection for safe visual navigation"},{"key":"ref50","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2010.5655356"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3083152"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_42"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.333"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_18"},{"key":"ref57","author":"Yang","year":"2025","journal-title":"Assistpda: An online video surveillance assistant for video anomaly prediction, detection, and analysis"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3150763"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00811"},{"key":"ref60","author":"Ye","year":"2023","journal-title":"mplug-owl: Modularization empowers large language models with multimodality"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02082"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_41"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104163"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01753"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01292"},{"key":"ref67","author":"Zhang","year":"2023","journal-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention"},{"key":"ref68","author":"Zhang","year":"2024","journal-title":"Video instruction tuning with synthetic data"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1053"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123451"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25489"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3450734"},{"key":"ref73","author":"Zhu","year":"2023","journal-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","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 (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492003.pdf?arnumber=11492003","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:07:56Z","timestamp":1778047676000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492003\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00705","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}