Search

Recently, due to the surge in the use of social networks, link prediction has become an essential technique which could enable service providers to anticipate future friendships between users based on the network structure and personal data so as to enhance consumer loyalty and experience. Undoubtedly, link prediction analysis becomes increasingly difficult when social networks expand quickly, particularly in light of the major advancements in complex social network modelling. Prior studies which predicted social links based on static network settings may have ignored the dynamic variation of networks over time. In this research, an end-to-end model, convolution-3D-based long-short-term memory (abbreviated as C3D-LSTM), is developed to integrate the convolution neural network (CNN) and long-short-term memory (LSTM) network for effective link prediction. We employ 3D convolution to detect subtle patterns in social network snapshots, capturing short-term spatial-temporal features. LSTM layers then interpret these features to model the network's long-term temporal dynamics. To demonstrate its practicability, extensive experiments are conducted to show that C3D-LSTM surpasses current state-of-the-art techniques and delivers remarkable performance.

The widespread occurrences of airborne outbreaks (e.g., COVID-19) and pollution (e.g., PM2.5) have urged people in the affected regions to protect themselves by wearing face masks. In certain areas, wearing masks amidst such health-endangering times is even enforced by law. While most people wear masks to guard themselves against airborne substances, some exploit such excuses and use face masks to conceal their identity for criminal purposes such as shoplifting, robbery, drug transport, and assault. While automatic face recognition models have been proposed, most of these models aim to identify clear, unobstructed faces for authentication purposes and cannot effectively handle cases where masks cover most facial areas. To mitigate such a problem, this paper proposes a deep-learning-based feature-fusion framework, FIREC, that combines additional demographic-estimated features such as age, gender, and race into the underlying facial representation to compensate for the information lost due to mask obstruction. Given an image of a masked face, our system recommends a ranked list of potential identities of the person behind the mask. Empirical results show that the best configuration of our proposed framework can recognize bare faces and masked faces with the accuracy of 99.34% and 97.65% in terms of Hit@10, respectively. The proposed framework could greatly benefit high-recall facial identity recognition applications such as identifying potential suspects from CCTV or passers-by’s cameras, especially during crisis times when people commonly cover their faces with protective masks.