{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:12:11Z","timestamp":1778051531852,"version":"3.51.4"},"reference-count":48,"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\/wacv61042.2026.00203","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2042-2051","source":"Crossref","is-referenced-by-count":0,"title":["CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video"],"prefix":"10.1109","author":[{"given":"Xinyi","family":"Wang","sequence":"first","affiliation":[{"name":"University of Bristol,School of Computer Science,Bristol,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angeliki","family":"Katsenou","sequence":"additional","affiliation":[{"name":"University of Bristol,School of Computer Science,Bristol,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junxiao","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Bristol,School of Computer Science,Bristol,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Bull","sequence":"additional","affiliation":[{"name":"University of Bristol,School of Computer Science,Bristol,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown"},{"issue":"70","key":"ref2","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00305"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00167"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3571788"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889302"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00589"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754696"},{"key":"ref12","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01408-w"},{"key":"ref18","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"},{"issue":"2","key":"ref19","article-title":"Toward a practical perceptual video quality metric","volume":"6","author":"Li","year":"2016","journal-title":"The Netflix Tech Blog"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240643"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28170"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02453"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3310344"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4133-3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2011.6190099"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2562513"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2869673"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"ref34","article-title":"Relax-vqa: Residual fragment and layer stack extraction for enhancing video quality assessment","volume-title":"IEEE 2025 25th International Conference on Digital Signal Processing","author":"Wang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP55913.2025.11084568"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901772"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref38","article-title":"A strong baseline for image and video quality assessment","author":"Wen","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3319332"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249741"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611737"},{"key":"ref43","article-title":"Q-align: Teaching lmms for visual scoring via discrete text-defined levels","author":"Wu","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01380"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475368"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3293093"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00274"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00137"}],"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\/11492275.pdf?arnumber=11492275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:16:37Z","timestamp":1778048197000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00203","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}