Cross-resolution face recognition adversarial attacks

Autor: Fabio Valerio Massoli, Giuseppe Amato, Fabrizio Falchi

Publikováno v: Pattern recognition letters 140 (2020): 222–229. doi:10.1016/j.patrec.2020.10.008
info:cnr-pdr/source/autori:Massoli F.V.; Falchi F.; Amato G./titolo:Cross-resolution face recognition adversarial attacks/doi:10.1016%2Fj.patrec.2020.10.008/rivista:Pattern recognition letters/anno:2020/pagina_da:222/pagina_a:229/intervallo_pagine:222–229/volume:140

Face Recognition is among the best examples of computer vision problems where the supremacy of deep learning techniques compared to standard ones is undeniable. Unfortunately, it has been shown that they are vulnerable to adversarial examples - input

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0ba97fb30a09a37b1ed837526640be7c
https://doi.org/10.1016/j.patrec.2020.10.008

MOCCA: Multilayer One-Class Classification for Anomaly Detection

Autor: Fabio Valerio Massoli, Fabrizio Falchi, Alperen Kantarci, Seymanur Akti, Hazim Kemal Ekenel, Giuseppe Amato

Publikováno v: IEEE Transactions on Neural Networks and Learning Systems 33 (2021): 2313–2323. doi:10.1109/TNNLS.2021.3130074

Anomalies are ubiquitous in all scientific fields and can express an unexpected event due to incomplete knowledge about the data distribution or an unknown process that suddenly comes into play and distorts observations. Due to such events' rarity, t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e206fba5211f7be0a1959f5387ab51dc
https://pubmed.ncbi.nlm.nih.gov/34874873

Multi-Resolution Face Recognition with Drones

Autor: Claudio Vairo, Fabrizio Falchi, Fabio Valerio Massoli, Giuseppe Amato, Claudio Gennaro

Publikováno v: 3rd International Conference on Sensors, Signal and Image Processing, pp. 13–18, Praga, Czech Republic (Virtual), 23-25/10/2020
info:cnr-pdr/source/autori:Amato G.; Falchi F.; Gennaro C.; Massoli F. V.; Vairo C./congresso_nome:3rd International Conference on Sensors, Signal and Image Processing/congresso_luogo:Praga, Czech Republic (Virtual)/congresso_data:23-25%2F10%2F2020/anno:2020/pagina_da:13/pagina_a:18/intervallo_pagine:13–18
SSIP

Smart cameras have recently seen a large diffusion and represent a low-cost solution for improving public security in many scenarios. Moreover, they are light enough to be lifted by a drone. Face recognition enabled by drones equipped with smart came

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f268c0b2478eb4c87c8f4207250021d9
https://dl.acm.org/doi/abs/10.1145/3441233.3441237

Cross-resolution learning for face recognition

Autor: Fabio Valerio Massoli, Fabrizio Falchi, Giuseppe Amato

Publikováno v: Image and vision computing 99 (2020). doi:10.1016/j.imavis.2020.103927
info:cnr-pdr/source/autori:Massoli F.V.; Amato G.; Falchi F./titolo:Cross-resolution learning for face recognition/doi:10.1016%2Fj.imavis.2020.103927/rivista:Image and vision computing/anno:2020/pagina_da:/pagina_a:/intervallo_pagine:/volume:99

Convolutional Neural Network models have reached extremely high performance on the Face Recognition task. Mostly used datasets, such as VGGFace2, focus on gender, pose, and age variations, in the attempt of balancing them to empower models to better

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e632c5c205a1610612f12aab2d3f7861
https://www.sciencedirect.com/science/article/abs/pii/S0262885620300597

Improving Multi-scale Face Recognition Using VGGFace2

Autor: Claudio Gennaro, Giuseppe Amato, Fabrizio Falchi, Fabio Valerio Massoli, Claudio Vairo

Publikováno v: BioFor Workshop on Recent Advances in Digital Security: Biometrics and Forensics, pp. 21–29, Trento, Berlino, 8/9/2019
info:cnr-pdr/source/autori:Massoli F.V.; Amato G.; Falchi F.; Gennaro C.; Vairo C./congresso_nome:BioFor Workshop on Recent Advances in Digital Security: Biometrics and Forensics/congresso_luogo:Trento, Berlino/congresso_data:8%2F9%2F2019/anno:2019/pagina_da:21/pagina_a:29/intervallo_pagine:21–29
New Trends in Image Analysis and Processing – ICIAP 2019 ISBN: 9783030307530
ICIAP Workshops

Convolutional neural networks have reached extremely high performances on the Face Recognition task. These models are commonly trained by using high-resolution images and for this reason, their discrimination ability is usually degraded when they are

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b34699e7697c939bceb598338ea60a8f
http://www.cnr.it/prodotto/i/411375