Publications (11)
TransFIRA: Transfer Learning for Face Image Recognizability Assessment
Allen Tu, Kartik Narayan, Joshua Gleason +4
Face recognition in unconstrained environments such as surveillance, video, and web imagery must contend with extreme variation in pose, blur, illumination, and occlusion, where co…
How are attributes expressed in face DCNNs?
Prithviraj Dhar, Ankan Bansal, Carlos D. Castillo +3
As deep networks become increasingly accurate at recognizing faces, it is vital to understand how these networks process faces. While these networks are solely trained to recognize…
A Fast and Accurate System for Face Detection, Identification, and Verification
Rajeev Ranjan, Ankan Bansal, Jingxiao Zheng +7
The availability of large annotated datasets and affordable computation power have led to impressive improvements in the performance of CNNs on various object detection and recogni…
Distill and De-bias: Mitigating Bias in Face Verification using Knowledge Distillation
Prithviraj Dhar, Joshua Gleason, Aniket Roy +3
Face recognition networks generally demonstrate bias with respect to sensitive attributes like gender, skintone etc. For gender and skintone, we observe that the regions of the fac…
A Synthesis-Based Approach for Thermal-to-Visible Face Verification
Neehar Peri, Joshua Gleason, Carlos D. Castillo +3
In recent years, visible-spectrum face verification systems have been shown to match the performance of experienced forensic examiners. However, such systems are ineffective in low…
Where in the World is this Image? Transformer-based Geo-localization in the Wild
Shraman Pramanick, Ewa M. Nowara, Joshua Gleason +2
Predicting the geographic location (geo-localization) from a single ground-level RGB image taken anywhere in the world is a very challenging problem. The challenges include huge di…
PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition
Prithviraj Dhar, Joshua Gleason, Aniket Roy +2
Face recognition networks encode information about sensitive attributes while being trained for identity classification. Such encoding has two major issues: (a) it makes the face r…
Weighted Risk Invariance: Domain Generalization under Invariant Feature Shift
Gina Wong, Joshua Gleason, Rama Chellappa +2
Learning models whose predictions are invariant under multiple environments is a promising approach for out-of-distribution generalization. Such models are trained to extract featu…
A Brief Survey on Person Recognition at a Distance
Chrisopher B. Nalty, Neehar Peri, Joshua Gleason +4
Person recognition at a distance entails recognizing the identity of an individual appearing in images or videos collected by long-range imaging systems such as drones or surveilla…
Towards Gender-Neutral Face Descriptors for Mitigating Bias in Face Recognition
Prithviraj Dhar, Joshua Gleason, Hossein Souri +2
State-of-the-art deep networks implicitly encode gender information while being trained for face recognition. Gender is often viewed as an important attribute with respect to ident…
A Proposal-Based Solution to Spatio-Temporal Action Detection in Untrimmed Videos
Joshua Gleason, Rajeev Ranjan, Steven Schwarcz +3
Existing approaches for spatio-temporal action detection in videos are limited by the spatial extent and temporal duration of the actions. In this paper, we present a modular syste…