{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:23:25Z","timestamp":1740169405560,"version":"3.37.3"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3487010","type":"journal-article","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T17:39:46Z","timestamp":1730137186000},"page":"160946-160956","source":"Crossref","is-referenced-by-count":0,"title":["QUASAR: QUality and Aesthetics Scoring With Advanced Representations"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9381-0541","authenticated-orcid":false,"given":"Sergey","family":"Kastryulin","sequence":"first","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4114-1788","authenticated-orcid":false,"given":"Denis","family":"Prokopenko","sequence":"additional","affiliation":[{"name":"Department of Biomedical Computing, King’s College London, London, U.K."}]},{"given":"Artem","family":"Babenko","sequence":"additional","affiliation":[{"name":"Yandex, Moscow, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2251-3221","authenticated-orcid":false,"given":"Dmitry V.","family":"Dylov","sequence":"additional","affiliation":[{"name":"Skolkovo Institute of Science and Technology, Moscow, Russia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4236\/jcc.2019.73002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3243466"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/132"},{"key":"ref4","first-page":"1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00194"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181496"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02238-8"},{"key":"ref11","first-page":"2","article-title":"A visual information fidelity approach to video quality assessment","volume-title":"Proc. 1st Int. Workshop VPQM Consum. Electron.","volume":"7","author":"Sheikh"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2109730"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00054"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00123"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2014.10.009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_37"},{"key":"ref19","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref21","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref22","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref23","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref24","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref25","article-title":"GridCLIP: One-stage object detection by grid-level CLIP representation learning","author":"Lin","year":"2023","journal-title":"arXiv:2303.09252"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611969"},{"key":"ref29","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref30","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2043888"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2831899"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2191563"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.84"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654927"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_40"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"volume-title":"Openclip","year":"2021","author":"Ilharco","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500021"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10736587.pdf?arnumber=10736587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T03:10:18Z","timestamp":1732677018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10736587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3487010","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}