Gérard Medioni

Amazon (United States) — United States

Computer Science · Physical Sciences

27h-index3.4kcitations100works0.52yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Vision and Imaging(32), Advanced Image and Video Retrieval Techniques(24), Robotics and Sensor-Based Localization(21), Face recognition and analysis(17), Video Surveillance and Tracking Methods(15)

Publications100 total

Data Pruning via Separability, Integrity, and Model Uncertainty-Aware Importance Sampling
Lecture notes in computer science·2024
Data Pruning via Separability, Integrity, and Model Uncertainty-Aware Importance Sampling
arXiv (Cornell University)·2024· 1 citedOpen Access
MILA: Multi-Task Learning from Videos via Efficient Inter-Frame Local Attention
arXiv (Cornell University)·2020Open Access
Face-Specific Data Augmentation for Unconstrained Face Recognition
International Journal of Computer Vision·2019· 53 cited
Deep, Landmark-Free FAME: Face Alignment, Modeling, and Expression Estimation
International Journal of Computer Vision·2019· 52 cited
On Face Segmentation, Face Swapping, and Face Perception
2018· 286 cited
Extreme 3D Face Reconstruction: Seeing Through Occlusions
arXiv (Cornell University)·2017· 4 citedOpen Access
The Multi-strand Graph for a PTZ Tracker
Journal of Mathematical Imaging and Vision·2017
Deep 3D face identification
2017· 116 cited
FacePoseNet: Making a Case for Landmark-Free Face Alignment
arXiv (Cornell University)·2017· 16 citedOpen Access
Rapid Synthesis of Massive Face Sets for Improved Face Recognition
2017· 48 cited
Local-Global Landmark Confidences for Face Recognition
2017· 4 cited
On Face Segmentation, Face Swapping, and Face Perception
arXiv (Cornell University)·2017· 13 citedOpen Access
Deep 3D Face Identification
arXiv (Cornell University)·2017· 6 citedOpen Access
A Closed-Form Solution to Tensor Voting: Theory and Applications
arXiv (Cornell University)·2016· 2 citedOpen Access
Do We Really Need to Collect Millions of Faces for Effective Face Recognition?
Lecture notes in computer science·2016· 311 cited
Capturing Dynamic Textured Surfaces of Moving Targets
Lecture notes in computer science·2016· 42 cited
Facial Landmark Detection with Tweaked Convolutional Neural Networks
arXiv (Cornell University)·2015· 25 citedOpen Access
A System for Assisting the Visually Impaired in Localization and Grasp of Desired Objects
Lecture notes in computer science·2015· 21 cited
Wearable RGBD Indoor Navigation System for the Blind
Lecture notes in computer science·2015· 68 cited
page 1 of 5Next →

Frequent Co-authors

Tal Hassner(8), Iacopo Masi(7), Anh Tran(3), Qian Yu(3), Thang Ba Dinh(3), Anh Tran(3), Ram Nevatia(3), James D. Weiland(3), Ramakant Nevatia(2), Yuval Nirkin(2), Sing Bing Kang(2), I. Cohen(2), Isaac Cohen(2), Jongmoo Choi(2), F. Ulupinar(2), Yuping Lin(2), Feng-Ju Chang(2), Ruizhe Wang(2), Jatuporn Toy Leksut(1), Anh Tran Tuan(1)