Search

Graph convolutional network has been extensively employed in semi-supervised classification tasks. Although some studies have attempted to leverage graph convolutional networks to explore multi-view data, they mostly consider the fusion of feature and topology individually, leading to the underutilization of the consistency and complementarity of multi-view data. In this paper, we propose an end-to-end joint fusion framework that aims to simultaneously conduct a consistent feature integration and an adaptive topology adjustment. Specifically, to capture the feature consistency, we construct a deep matrix decomposition module, which maps data from different views onto a feature space obtaining a consistent feature representation. Moreover, we design a more flexible graph convolution that allows to adaptively learn a more robust topology. A dynamic topology can greatly reduce the influence of unreliable information, which acquires a more adaptive representation. As a result, our method jointly designs an effective feature fusion module and a topology adjustment module, and lets these two modules mutually enhance each other. It takes full advantage of the consistency and complementarity to better capture the more intrinsic information. The experimental results indicate that our method surpasses state-of-the-art semi-supervised classification methods. • Propose an end-to-end framework for multi-view semi-supervised classification. • Design a multi-view auto-encoder to fuse feature by approximating the matrix decomposition. • Explore a more robust topology that fuses the adjacency matrices generated by k NN and k FN. [ABSTRACT FROM AUTHOR]

Video question answering (VideoQA) is a challenging video understanding task that requires a comprehensive understanding of multimodal information and accurate answers to related questions. Most existing VideoQA models use Graph Neural Networks (GNN) to capture temporal–spatial interactions between objects. Despite achieving certain success, we argue that current schemes have two limitations: (i) existing graph-based methods require stacking multi-layers of GNN to capture high-order relations between objects, which inevitably introduces irrelevant noise; (ii) neglecting the unique self-supervised signals in the high-order relational structures among multiple objects that can facilitate more accurate QA. To this end, we propose a novel Multi-scale Self-supervised Hypergraph Contrastive Learning (MSHCL) framework for VideoQA. Specifically, we first segment the video from multiple temporal dimensions to obtain multiple frame groups. For different frame groups, we design appearance and motion hyperedges based on node semantics to connect object nodes. In this way, we construct a multi-scale temporal–spatial hypergraph to directly capture high-order relations among multiple objects. Furthermore, the node features after hypergraph convolution are injected into a Transformer to capture the global information of the input sequence. Second, we design a self-supervised hypergraph contrastive learning task based on the node- and hyperedge-dropping data augmentation and an improved question-guided multimodal interaction module to enhance the accuracy and robustness of the VideoQA model. Finally, extensive experiments on three benchmark datasets demonstrate the superiority of our proposed MSHCL compared with stat-of-the-art methods. • We propose a novel hypergraph-based contrastive learning framework MSHCL, which fully explores multimodal representation to achieve better QA. • We design appearance and motion hyperedges to construct the multi-scale temporal–spatial hypergraph, which directly captures higher-order relations among multiple objects. Besides, we use Transformer to capture global information of input sequences. • We design a self-supervised hypergraph contrastive learning task based on node and hyperedgedropping data augmentation and improved QMI module to improve accuracy and robustness of the model. • We conduct extensive experiments on three benchmark datasets to demonstrate the superiority of our proposed MSHCL compared with the state-of-the-art. [ABSTRACT FROM AUTHOR]

Electric vehicles require fast, economical and reliable charging systems for efficient performance. Wireless charging systems remove the hassle to plug in the device to be charged when compared with the conventional wired charging systems. Moreover, wireless charging is considered to be environment and user friendly as the wires and mechanical connectors and related infrastructure are not required. This paper reviews the methods and techniques used for wireless charging in electric vehicles. First, the general techniques for wireless power transfer are described and explained. Capacitive power transfer and inductive power transfer which are the two main types of wireless charging are compared and contrasted. Next wireless charging systems for electric vehicles are classified and discussed in depth. Both the stationary and the dynamic wireless charging systems are discussed and reviewed. In addition, a typical model and design parameters of a dynamic charging system, which is a wireless charging system for moving vehicles, are examined. Control system functions of a wireless charging system of an electric vehicle are important for an effective and efficient performance. These are also discussed in the context of better efficiency of power transfer and improved communication between the transmitter and the receiver side of a vehicle charging system. Battery is an important part of an electric vehicle as different parameters of a charging system depend upon the battery characteristics. Therefore, different battery types are compared and battery models are reviewed. Findings of this state of the art review are discussed and recommendations for future research are also provided. • This work presents a state of the art review of the wireless charging systems for electric vehicles. • A review of the related survey articles along with a tabular summary has been presented. • Different types of electric vehicle wireless charging techniques are described and reviewed. • Stationary and dynamic wireless charging systems are reviewed and summaries have been presented. • Wireless charging system communication and control aspects have been discussed. [ABSTRACT FROM AUTHOR]