{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T05:51:05Z","timestamp":1781761865420,"version":"3.54.5"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017343","name":"Center for High Performance Computing","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017343","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,25]]},"DOI":"10.1109\/fg67764.2026.11557013","type":"proceedings-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:37:10Z","timestamp":1781725030000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Employing Vision-Language Models for Face Image Quality Assessment"],"prefix":"10.1109","author":[{"given":"Erdi","family":"Sar\u0131ta\u015f","sequence":"first","affiliation":[{"name":"Istanbul Technical University,Department of Computer Engineering,Istanbul,Türkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eren","family":"Onaran","sequence":"additional","affiliation":[{"name":"Istanbul Technical University,Department of Computer Engineering,Istanbul,Türkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vitomir","family":"\u0160truc","sequence":"additional","affiliation":[{"name":"University of Ljubljana,Faculty of Electrical Engineering,Ljubljana,Slovenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haz\u0131m Kemal","family":"Ekenel","sequence":"additional","affiliation":[{"name":"Istanbul Technical University,Department of Computer Engineering,Istanbul,Türkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Phi-4 technical report. arXiv preprint arXiv:2412.08905","author":"Abdin","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00624"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2024.3376236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956444"},{"key":"ref5","volume-title":"Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61042.2026.00260"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3774904.3792220"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01887"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755379"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-009-0417-2"},{"key":"ref13","article-title":"Labeled faces in the wild: A database for studying face recognition in unconstrained environments","volume-title":"Workshop on Faces in \u2018Real-Life\u2019 Images: Detection, Alignment, and Recognition (ECCV Workshop)","author":"Huang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00344"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92089-9_14"},{"key":"ref16","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"International Conference on Learning Representations","author":"Karras"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01819"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3138"},{"key":"ref19","first-page":"9459","article-title":"Retrievalaugmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"HERM: Benchmarking and enhancing multimodal LLMs for human-centric understanding","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2410.06777"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754939"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00365"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3402729"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00057"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00758"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00167"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01200"},{"key":"ref28","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10582014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3507901"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00390"},{"key":"ref32","volume-title":"Gemma 3 technical report. arXiv preprint arXiv:2503.19786","author":"Team","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00569"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i12.37945"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref36","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2409.12191"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.87"},{"key":"ref38","first-page":"5401554029","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":"10.1145\/3746027.3755332"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01101"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3639998"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmapro.2026.01.071"}],"event":{"name":"2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Kyoto, Japan","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE 20th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11556508\/11556510\/11557013.pdf?arnumber=11557013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:52:17Z","timestamp":1781758337000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11557013\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/fg67764.2026.11557013","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]}}}