I
Iacopo Masi
Researcher at Information Sciences Institute
Publications - 62
Citations - 4462
Iacopo Masi is an academic researcher from Information Sciences Institute. The author has contributed to research in topics: Facial recognition system & Face (geometry). The author has an hindex of 26, co-authored 59 publications receiving 3423 citations. Previous affiliations of Iacopo Masi include Sapienza University of Rome & University of Florence.
Papers
More filters
Book ChapterDOI
Face Segmentation, Face Swapping, and How They Impact Face Recognition
TL;DR: In this article, a fully convolutional network (FCN) was proposed for face swapping, which does not require training on faces being swapped and can be easily applied even when face images are unpaired and arbitrarily paired.
Book ChapterDOI
Multi-target Data Association Using Sparse Reconstruction
Andrew D. Bagdanov,Alberto Del Bimbo,Dario Di Fina,Svebor Karaman,Giuseppe Lisanti,Iacopo Masi +5 more
TL;DR: A solution to multi-target data association problem based on l1-regularized sparse basis expansions that allows the approach to exploit multiple instances of the target when performing data association rather than relying on an average representation of target appearance.
Posted Content
AIRD: Adversarial Learning Framework for Image Repurposing Detection
TL;DR: In this article, a real-world adversarial interplay between a bad actor who repurposes images with counterfeit metadata and a watchdog who verifies the semantic consistency between images and their accompanying metadata is proposed.
Journal ArticleDOI
Exploring the Connection between Robust and Generative Models
TL;DR: In this article , robust discriminative classifiers trained with adversarial training (AT) with generative modeling in the form of Energy-based Models (EBM) are proposed.
Proceedings Article
Multi-pose face detection for accurate face logging
TL;DR: Results show that the system can simultaneously minimizing false positives and identity mismatches, while balancing this against the need to obtain face images of all people in a scene.