18 citations · 38 across the 6 of their papers we have counts for
8 papers
Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features
Yuanbo Xiangli, Ruojin Cai, Hanyu Chen +2
Accurate 3D reconstruction is frequently hindered by visual aliasing, where visually similar but distinct surfaces (aka, doppelgangers), are incorrectly matched. These spurious mat…
Fine-grained Activities of People Worldwide
Jeffrey Byrne, Greg Castanon, Zhongheng Li +1
Every day, humans perform many closely related activities that involve subtle discriminative motions, such as putting on a shirt vs. putting on a jacket, or shaking hands vs. givin…
Key-Nets: Optical Transformation Convolutional Networks for Privacy Preserving Vision Sensors
Jeffrey Byrne, Brian DeCann, Scott Bloom
Modern cameras are not designed with computer vision or machine learning as the target application. There is a need for a new class of vision sensors that are privacy preserving by…
Inducing Predictive Uncertainty Estimation for Face Recognition
Weidi Xie, Jeffrey Byrne, Andrew Zisserman
Knowing when an output can be trusted is critical for reliably using face recognition systems. While there has been enormous effort in recent research on improving face verificatio…
Explainable Face Recognition
Jonathan R. Williford, Brandon B. May, Jeffrey Byrne
Explainable face recognition is the problem of explaining why a facial matcher matches faces. In this paper, we provide the first comprehensive benchmark and baseline evaluation fo…
Out the Window: A Crowd-Sourced Dataset for Activity Classification in Security Video
Gregory Castanon, Nathan Shnidman, Tim Anderson +1
The Out the Window (OTW) dataset is a crowdsourced activity dataset containing 5,668 instances of 17 activities from the NIST Activities in Extended Video (ActEV) challenge. These…
Dataset Augmentation for Pose and Lighting Invariant Face Recognition
Daniel Crispell, Octavian Biris, Nate Crosswhite +2
The performance of modern face recognition systems is a function of the dataset on which they are trained. Most datasets are largely biased toward "near-frontal" views with benign…
Template Adaptation for Face Verification and Identification
Nate Crosswhite, Jeffrey Byrne, Omkar M. Parkhi +3
Face recognition performance evaluation has traditionally focused on one-to-one verification, popularized by the Labeled Faces in the Wild dataset for imagery and the YouTubeFaces…