{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T01:36:14Z","timestamp":1780104974594,"version":"3.54.0"},"reference-count":86,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02107","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22695-22706","source":"Crossref","is-referenced-by-count":1,"title":["Aligning Effective Tokens with Video Anomaly in Large Language Models"],"prefix":"10.1109","author":[{"given":"Yingxian","family":"Chen","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahui","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruidi","family":"Fan","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanwei","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chirui","family":"Chang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shizhen","family":"Zhao","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wilton W.T.","family":"Fok","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yik-Chung","family":"Wu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126525"},{"key":"ref3","article-title":"Language models are few-shot learners","volume":"abs\/2005.14165","author":"Brown","year":"2020","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16177"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_20"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25112"},{"key":"ref7","article-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","author":"Won Chung","year":"2022","journal-title":"Scaling instruction-finetuned language models"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref10","author":"Devlin","year":"2019","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref11","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01778"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2606"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00179"},{"key":"ref17","article-title":"A path-building procedure for iterative circuit computers","volume-title":"Technical report","author":"Gonzalez","year":"1962"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00803"},{"key":"ref21","author":"Jia","year":"2021","journal-title":"Scaling up visual and vision-language representation learning with noisy text supervision"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icip49359.2023.10222289"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206771"},{"key":"ref24","author":"Kuo","year":"2023","journal-title":"F-vlm: Open-vocabulary object detection upon frozen vision and language models"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"ref28","author":"Li","year":"2023","journal-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref32","author":"Lin","year":"2023","journal-title":"Video-llava: Learning united visual representation by alignment before projection"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2026.3654458"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00904"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_13"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3796716"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019325"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01971"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00136"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.26599\/cvm.2025.9450516"},{"key":"ref45","article-title":"Introducing chatgpt","volume-title":"OpenAI","year":"2022"},{"key":"ref46","author":"Oquab","year":"2024","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"ref48","author":"Peng","year":"2023","journal-title":"Instruction tuning with gpt-4"},{"key":"ref49","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref50","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093417"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"ref53","author":"Su","year":"2023","journal-title":"Pandagpt: One model to instruction-follow them all"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref55","author":"Tang","year":"2024","journal-title":"Hawk: Learning to understand open-world video anomalies"},{"key":"ref56","author":"Thoppilan","year":"2022","journal-title":"Lamda: Language models for dialog applications"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref58","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref59","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102722"},{"key":"ref61","author":"Wang","year":"2023","journal-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/162"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062192"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01732"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_18"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01788"},{"key":"ref69","author":"Yao","year":"2021","journal-title":"Filip: Fine-grained interactive language-image pre-training"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02082"},{"key":"ref71","first-page":"358","article-title":"Claws: Clustering assisted weakly supervised learning with normalcy suppression for anomalous event detection","volume-title":"European Conference on Computer Vision (ECCV)","author":"Zaigham Zaheer","year":"2020"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01433"},{"key":"ref73","article-title":"Cleaning label noise with clusters for minimally supervised anomaly detection","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","author":"Zaigham Zaheer"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01292"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803657"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43987-2_18"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995524"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681407"},{"key":"ref80","author":"Xin Zhao","year":"2023","journal-title":"A survey of large language models"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123451"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00133"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2025.3595111"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25489"},{"key":"ref85","author":"Zhu","year":"2023","journal-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models"},{"key":"ref86","article-title":"Motion-aware feature for improved video anomaly detection","volume-title":"British Machine Vision Conference (BMVC)","author":"Zhu","year":"2019"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444541.pdf?arnumber=11444541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:44Z","timestamp":1777529984000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444541\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02107","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}