20.500.12556/RUL-185624 UVFace utility driven video-based face recognition Face recognition methods are primarily designed for single-image analysis, even though video-based recognition has seen a dramatic increase in popularity in edge security and surveillance applications. Typically, a video template is constructed from the features of individual frames. Feature norms are commonly used as weights in the construction process, as they correlate well with the usefulness of samples for recognition. Classical training approaches directly optimize only the angular distances, in turn also guiding the feature norms. This can lead to suboptimal alignment between feature norms and the usefulness (utility) of samples, resulting in subpar video performance. Motivated by this insight, we propose the UVFace methodology, which presents an extended feature norm alignment branch. Through careful design of the quality ranking step, which produces feature norm labels and a new feature norm loss, UVFace improves performance over the reproduced AdaFace baseline on video-oriented benchmarks while retaining strong image-based performance. Code is available at https://github.com/LSIbabnikz/UVFace computer vision biometrics face recognition face image quality assessment računalniški vid biometrija razpoznavanje obrazov ocena kakovosti obraznih slik true false true Angleški jezik Slovenski jezik Članek v reviji 2026-08-13 12:16:09 2026-08-13 12:16:13 2026-08-14 04:03:57 0000-00-00 00:00:00 2026 0 0 Str. 868-873 issue 4 Vol. 12 Aug. 2026 0000-00-00 Zaloznikova Objavljeno apc 0000-00-00 0000-00-00 0000-00-00 004.93 2405-9595 10.1016/j.icte.2026.05.014 281768451 1-s2.0-S2405959526000871-main.pdf 1-s2.0-S2405959526000871-main.pdf 1 D95DD505F5790E8967D4A22EBBE7368C 04811ee967c9697188356ec4f173e385187f74716da6b45e3d12d4d58ffca7ce d40c8460-96ff-11f1-9b0d-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=244343 https://www.sciencedirect.com/science/article/pii/S2405959526000871 1 a87dd28f-96ff-11f1-9b0d-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=244342 Fakulteta za elektrotehniko 0 0 0