Uncertainty Modeling of Contextual-Connections Between Tracklets for Unconstrained Video-Based Face Recognition

Abstract

Unconstrained video-based face recognition is a challenging problem due to significant within-video variations caused by pose, occlusion and blur. To tackle this problem, an effective idea is to propagate the identity from highquality faces to low-quality ones through contextual connections, which are constructed based on context such as body appearance. However, previous methods have often propagated erroneous information due to lack of uncertainty modeling of the noisy contextual connections. In this paper, we propose the Uncertainty-Gated Graph (UGG), which conducts graph-based identity propagation between tracklets, which are represented by nodes in a graph. UGG explicitly models the uncertainty of the contextual connections by adaptively updating the weights of the edge gates according to the identity distributions of the nodes during inference. UGG is a generic graphical model that can be applied at only inference time or with end-to-end training. We demonstrate the effectiveness of UGG with state-of-theart results in the recently released challenging Cast Search in Movies and IARPA Janus Surveillance Video Benchmark dataset.

A review of uncertainty quantification in deep learning: Techniques, applications and challenges

“…Therefore, it's important to take uncertainty into account, where the predictions made by deep learning based computer vision algorithms. To date, there have been number of studies addressed uncertainty in deep learning algorithms for various applications including but not limited to image/video retrieval [399], [400], depth estimation [401], [402], object detection [403], [404], [405], semantic segmentation and scene understanding [406], [407], [408], [409], [10], optical flow estimation and motion prediction [249], [410], [411], human pose estimation and pedestrian localization [412], [413], [305], person re-identification and face recognition [414], [415], [416], camera re-localization [397], avoiding adversarial attacks [417], [418], during the years 2016 to 2020. As a fact, most of research studies in deep learning applications are concentrating on prediction accuracy.…”

AdaFace: Quality Adaptive Margin for Face Recognition

“…Several studies [20,21,26,30,31,36,41,54,63,80,84,85] tackle recognition with low-quality imagery. Particularly, AdaFace [30] introduces an image quality adaptive loss function that reduces the influence of low-quality or unidentifiable samples.…”

PA-GAN: A Patch-Attention Based Aggregation Network for Face Recognition in Surveillance

“…Ref. [17] proposed a generic graphical algorithm, in which a contextual connecting formulate between highquality and low-quality faces is designed. In ref.…”