Object understanding in egocentric visual data is arguably a fundamental research topic in
egocentric vision. However, existing object datasets are either non-egocentric or have …

As a widely used loss function in deep face recognition, the softmax loss cannot guarantee
that the minimum positive sample-to-class similarity is larger than the maximum negative …

Speaker modeling plays a crucial role in various tasks, and fixed-dimensional vector
representations, known as speaker embeddings, are the predominant modeling approach …

In this work we focus on learning facial representations that can be adapted to train effective
face recognition models particularly in the absence of labels. Firstly compared with existing …

Small on-device models have been successfully trained with user-level differential privacy
(DP) for next word prediction and image classification tasks in the past. However, existing …

Universal domain adaptation (UniDA) aims to transfer the knowledge learned from a labeled
source domain to an unlabeled target domain without any constraints on the label sets …

Current state-of-the-art deep learning based face recognition (FR) models require a large
number of face identities for central training. However, due to the growing privacy …

This paper addresses the deep face recognition problem under an open-set protocol, where
ideal face features are expected to have smaller maximal intra-class distance than minimal …

Currently available face datasets mainly consist of a large number of high-quality and a
small number of low-quality samples. As a result, a Face Recognition (FR) network fails to …

We propose an experimental method for measuring bias in face recognition systems.
Existing methods to measure bias depend on benchmark datasets that are collected in the …