With ultra-high-definition (UHD) video services developing in B5G networks, such as an UHD video surveillance system with a resolution of$7680\times 4320$p, that generates video data 24/7, the high-service overhead caused by the bandwidth resource bottleneck will greatly affect the performance of video services. Network slice provider (NSP) focuses on the overall revenue. However, network slice user (NSU) emphasizes task requirements and cost. A crucial challenge to find a desirable tradeoff between NSPs and NSUs since the objective of NSPs’ Quality of Experience (QoE) is partially in conflict with the objective of NSUs’ QoE. In order to investigate the performance of data transmission for UHD video from the perspective of QoE, a Stackelberg game model is leveraged to achieve the optimization goals after constructed a novel QoE model. After analyzing the game process, Nash equilibrium can be achieved that indicates a relatively optimal state. A problem of maximizing the overall effective QoE is formulated by jointly optimizing NSPs’ QoE, NSUs’ QoE and the bandwidth resource allocation. To tackle the nonconvex formulated problem, a QoE-Aware Game-theoretic Band-width Resource Allocation Strategy for UHD Video Services named “QAGBRAS” is proposed. Extensive experiments are conducted to evaluate performance of the proposed approach against the state-of-the art solutions in terms of network congestion control, bandwidth utilization, and QoE factors, including NSP’s revenue, NSU’s task requirements, and cost. Simulation results show that our proposed approach can effectively achieve the optimal solution in the context of QoE.

Image memorability is to measure the degree to which an image is remembered. Generally image memorability prediction involves two steps: feature representation and prediction. Most previous work just focused on addressing the first step by investigating the factors of making an image memorable. They not only lack the use of a learning mechanism in feature representation, but also often neglect the second step. In this paper, we first propose a joint low-rank and sparse regression (JLRSR) framework to address this problem. JLRSR aims to jointly learn: 1) a low-rank projection matrix that enables us to decompose the original data into a component part and an error part and 2) a sparse regression coefficient vector for image memorability prediction. The projection matrix and the regression coefficients are bound by a sparse constraint to make our approach invariant to training samples. Moreover, a graph regularizer is constructed to improve the generalization performance and prevent overfitting. We then extend JLRSR to a multi-view version called Mv-JLRSR by imposing the block-wise constraint to ensure the group effect and the view correlation constraint to eliminate the heterogeneity among views. Experiment results validate the effectiveness of our proposed approaches.

Remembering images is an innate human capability. Camera images are captured by different people under varying environmental conditions, which leads to highly diverse image memorability scores. However, the factors that make an image more or less memorable are unclear, and it remains unknown how we can more accurately predict image memorability by using such factors. In this paper, we propose a novel framework called multiview transfer learning from external sources (MTLES) to predict image memorability. In this framework, we simultaneously leverage different types of visual feature sets and multiple types of predefined image attributes derived from external sources. In particular, to enhance representation ability of visual features, we construct connections between visual feature sets and higher level image attributes by transferring attribute knowledge from external sources. MTLES integrates weak learning through external sources, transfer learning, and multiview consistency loss with different types of feature sets into a joint framework. To better solve this joint optimization problem, we further develop an alternating iterative algorithm to deal with it. Experiments performed on the publicly available LaMem dataset demonstrate the effectiveness of the proposed scheme.