Stan Z. Li

TL;DR: In this article, a cross-modal auxiliary network (CMA) is proposed for face anti-spoofing detection, which consists of a modality translation network (MT-Net) and a Modality Assistance Network (MA-Net), which can close the visible gap between different modalities via a generative model that maps inputs from one modality (i.e., RGB) to another ( i.e., NIR).

TL;DR: Both face and facial feature localization and face recognition are performed using local features with AdaBoost learning and the system achieves excellent accuracy, speed and usability.

TL;DR: A diverse range of advanced techniques to speed up the diffusion models – training schedule, training-free sampling, mixed-modeling, and score & diffusion unification are presented.

TL;DR: This paper recasts facial attractiveness computation as a label distribution learning problem, and an end-to-end attractiveness learning framework is established that shows significant advantages over the other state-of-the-art work.

TL;DR: A novel face representation and recognition approach that describes the neighboring relationship in spatial domain, but also exploit those between different scales (frequency) and orientations, and uses the weighted histogram intersection metric to measure the dissimilarity of faces.