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
Proceedings ArticleDOI
Matching People across Camera Views using Kernel Canonical Correlation Analysis
TL;DR: This paper addresses the problem of person re-identification across disjoint cameras by proposing an efficient but robust kernel descriptor to encode the appearance of a person by applying a learning technique based on Kernel Canonical Correlation Analysis (KCCA).
Proceedings ArticleDOI
Face recognition using deep multi-pose representations
Wael AbdAlmageed,Yue Wu,Stephen Rawls,Shai Harel,Tal Hassner,Iacopo Masi,Jongmoo Choi,Jatuporn Lekust,Jungyeon Kim,Prem Natarajan,Ram Nevatia,Gerard Medioni +11 more
TL;DR: A novel representation of face recognition using multiple pose-aware deep learning models achieves better results than the state-of-the-art on IARPA's CS2 and NIST's IJB-A in both verification and identification tasks.
Proceedings ArticleDOI
FacePoseNet: Making a Case for Landmark-Free Face Alignment
TL;DR: In this paper, a simple convolutional neural network (CNN) is trained to accurately and robustly regress 6 degrees of freedom (6DoF) 3D head pose, directly from image intensities.
Proceedings ArticleDOI
ExpNet: Landmark-Free, Deep, 3D Facial Expressions
TL;DR: It is shown that the ExpNet produces expression coefficients which better discriminate between facial emotions than those obtained using state of the art, facial landmark detectors, and is more robust to scale changes than landmark detectors.
Posted Content
Extreme 3D Face Reconstruction: Seeing Through Occlusions
TL;DR: A layered approach which decouples estimation of a global shape from its mid-level details (e.g., wrinkles) and then separately layer this foundation with details represented by a bump map, motivated by the concept of bump mapping is proposed.