{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:21:12Z","timestamp":1778052072383,"version":"3.51.4"},"reference-count":57,"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\/wacv61042.2026.00677","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7008-7018","source":"Crossref","is-referenced-by-count":0,"title":["ScoreNet: Netting Lightweight Quality Scores for Better Visual Assessment with Large Multi-Modality Models"],"prefix":"10.1109","author":[{"given":"Bahador","family":"Rashidi","sequence":"first","affiliation":[{"name":"Huawei Technologies Canada Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kiarash","family":"Aghakasiri","sequence":"additional","affiliation":[{"name":"Huawei Technologies Canada Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shupei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Canada Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amirmohsen","family":"Sattarifard","sequence":"additional","affiliation":[{"name":"Huawei Technologies Canada Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Canada Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Gao","sequence":"additional","affiliation":[{"name":"Huawei Technologies Canada Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Quality-aware image-text alignment for real-world image quality assessment","author":"Agnolucci","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00026"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2760518"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","author":"Brown","year":"2020"},{"key":"ref5","article-title":"IQA-PyTorch: Pytorch toolbox for image quality assessment","author":"Chen","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378466"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612524"},{"key":"ref8","author":"Chen","year":"2023","journal-title":"Iqagpt: Image quality assessment with vision-language and chatgpt models"},{"key":"ref9","author":"Derakhshani","year":"2022","journal-title":"Variational prompt tuning improves generalization of vision-language models."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref11","author":"Dosovitskiy","year":"2021","journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_10"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00404"},{"key":"ref14","article-title":"A systematic survey of prompt engineering on vision-language foundation models","author":"Gu","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.11.003"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2894958"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0911-6_17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref19","first-page":"4319","article-title":"Topic: Transformer-based predictor for image quality","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.118"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2708503"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2774045"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803390"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2011.6190099"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref27","article-title":"Multi-modal prompt learning on blind image quality assessment","author":"Pan","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2014.10.009"},{"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","first-page":"5846","article-title":"Reiqa: Unsupervised learning for image quality assessment in the wild","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Saha"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859378"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01216"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref34","first-page":"3556","article-title":"Hyperiqa: Generalizing image quality assessment via hypernetwork","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Su"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref38","first-page":"54015","article-title":"Q-align: Teaching LMMs for visual scoring via discrete text-defined levels","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Wu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_21"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3002478"},{"key":"ref41","article-title":"Visual prompting in multimodal large language models: A survey","author":"Wu","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00257"},{"key":"ref43","article-title":"Prompt tuning for generative multimodal pretrained models","author":"Yang","year":"2022"},{"key":"ref44","author":"Ye","year":"2023","journal-title":"mplug-owl: Modularization empowers large language models with multimodality"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_15"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3209889"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2426416"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2886771"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"ref54","first-page":"1207","article-title":"Unique: Unsupervised quality estimation for natural images","volume-title":"Proceedings of the ACM International Conference on Multimedia","author":"Zhang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"}],"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\/11492415.pdf?arnumber=11492415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:44:57Z","timestamp":1778049897000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00677","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}