CSPP-IQA: a multi-scale spatial pyramid pooling-based approach for blind image quality assessment

Abstract

The traditional image quality assessment (IQA) methods are usually based on convolutional neural networks (CNNs). For these IQA methods using CNNs, limited by the feature size of the fully connected layer, the input image needs be tailored to a pre-defined size, which usually results in destroying the original structure and content of the input image and thus reduces the accuracy of the quality assessment. In this paper, a blind image quality assessment method (named CSPP-IQA), which is based on multi-scale spatial pyramid pooling, is proposed. CSPP-IQA allows inputting the original image when assessing the image quality without any image adjustment. Moreover, by facilitating the convolutional block attention module and image understanding module, CSPP-IQA achieved better accuracy, generalization and efficiency than traditional IQA methods. The result of experiments running on real-scene IQA datasets in this study verified the effectiveness and efficiency of CSPP-IQA.

A Nonlinear Spatiotemporal Optimization Method of Hypergraph Convolution Networks for Traffic Prediction

“…Wu et al [40] proposed a cross-city spatiotemporal migration learning model, obtained prior knowledge by training the traffic data of source cities, and designed a learning strategy based on generative adversarial network to improve the predictive performance. The structures of traffic networks present non-Euclidean rules [41], so these methods were limited to European structural data such as convolutional neural networks [42,43], which had difficulties in the spatial modeling of traffic networks.…”