{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:27:05Z","timestamp":1774420025684,"version":"3.50.1"},"reference-count":40,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888524","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["An Ensemble Approach to Short-form Video Quality Assessment Using Multimodal LLM"],"prefix":"10.1109","author":[{"given":"Wen","family":"Wen","sequence":"first","affiliation":[{"name":"City University of Hong Kong,Hong Kong SAR"}]},{"given":"Yilin","family":"Wang","sequence":"additional","affiliation":[{"name":"Google Inc.,Mountain View,CA,USA"}]},{"given":"Neil","family":"Birkbeck","sequence":"additional","affiliation":[{"name":"Google Inc.,Mountain View,CA,USA"}]},{"given":"Balu","family":"Adsumilli","sequence":"additional","affiliation":[{"name":"Google Inc.,Mountain View,CA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2299154"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2502725"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01380"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01323"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3385364"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00267"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647927"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901772"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3319332"},{"key":"ref17","article-title":"Internlm-xcomposer: A vision-language large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref19","article-title":"InternLM-XComposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024"},{"key":"ref20","first-page":"1","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","first-page":"1","article-title":"Grounding multimodal large language models to the world","volume-title":"International Conference on Learning Representations","author":"Peng"},{"key":"ref22","first-page":"1","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"International Conference on Learning Representations","author":"Zhu"},{"key":"ref23","first-page":"1","article-title":"Q-Bench: A benchmark for general-purpose foundation models on low-level vision","volume-title":"International Conference on Learning Representations","author":"Wu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_15"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02408"},{"key":"ref27","first-page":"81","article-title":"Q-Align: Teaching LMMs for visual scoring via discrete text-defined levels","volume-title":"International Conference on Machine Learning","author":"Wu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_21"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3571788"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451225"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-27202-9_14"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00174"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02453"},{"key":"ref35","article-title":"PaliGemma: A versatile 3B VLM for transfer","author":"Beyer","year":"2024"},{"key":"ref36","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International Conference on Machine Learning","author":"Jaegle"},{"key":"ref37","first-page":"23 716","article-title":"Flamingo: A visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","first-page":"19 730","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":"ref39","article-title":"PaLi-3 vision language models: Smaller, faster, stronger","author":"Chen","year":"2023"},{"key":"ref40","article-title":"Gemma: Open models based on gemini research and technology","year":"2024"}],"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\/10888524.pdf?arnumber=10888524","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:00Z","timestamp":1774416360000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888524\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888524","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}