Event Details

Nov19Tue

CS Colloquium: Iacopo Masi (USC ISI) - Towards Visual Understanding of Humans for Recognition, Reconstruction, and Synthesis

Tue, Nov 19, 2019
11:00 AM - 12:00 PM
Location: RTH 115
Speaker: Iacopo Masi, USC

Talk Title: Towards Visual Understanding of Humans for Recognition, Reconstruction, and Synthesis

Abstract: Computer vision is arguably the most rapidly evolving topic in computer science, undergoing drastic and exciting changes. A primary goal is teaching machines how to understand and model humans from visual information.

The main thread of my research is giving machines the capability to (1) build an internal representation of humans, as seen from a camera in uncooperative environments, that is highly discriminative with respect to identity (e.g., person re-identification and face recognition); and (2) to semantically analyze human faces to detect, segment, reconstruct, and synthesis them (e.g., occlusion detection and face completion).

In this talk, I demonstrate how we can effectively design and learn discriminative representations for person re-identification and how face recognition can improve without the need for massive human supervision or labeled data, using face-specific augmentation. Then I show how to enforce smoothness in a deep neural network for better, structured face occlusion detection and how this occlusion detection can ease the learning of the face completion task.

This lecture satisfies requirements for CSCI 591: Research Colloquium


Biography: Iacopo Masi is a Research Computer Scientist at the USC Information Sciences Institute (ISI). He received a Ph.D. in Computer Engineering at the University of Firenze, Italy. He was a postdoctoral scholar at the University of Southern California, USA. Iacopo has been Area-Chair of several WACVs and currently serves as Associate Editor for The Visual Computer - International Journal of Computer Graphics. He organized an International Workshop on Human Identification at ICCV'17 and was Workshop Chair at SIBGRAPI'18. His main research interest lies in solving the computer vision problem, specifically, the subjects of tracking, person re-identification, 2D/3D face recognition, and modeling.

Host: Bill Swartout