Recently, with the rapid development of mobile sensing technology, capturing scene information by mobile sensing devices in the form of images or videos has become a prevalent recording method. However, the moiré pattern phenomenon may occur when the scene contains digital screens or regular strips, which greatly degrade the visual performance and image quality. In this paper, considering the complexity and diversity of moiré patterns, we propose a novel end-to-end image demoiré method, which can learn moiré pattern elimination in both the frequency and spatial domains. To be specific, in the frequency domain, considering the signal energy of moiré pattern is widely distributed in the frequency, we introduce a wavelet transform to decompose the multi-scale image features, which can help the model identify the moiré features more precisely to suppress them effectively. On the other hand, we also design a spatial domain demoiré block (SDDB). The SDDB module can extract moiré features from the mixed features, then subtract them to obtain clean image features. The combination of the frequency domain and the spatial domain enhances the model’s ability in terms of moiré feature recognition and elimination. Finally, extensive experiments demonstrate the superior performance of our proposed method to other state-of-the-art methods. The Grad-CAM results in our ablation study fully indicate the effectiveness of the two proposed blocks in our method.

With the growth of urban population, a series of urban problems have emerged, and how to speed up smart city construction has received extensive attention. Remote sensing images have the advantages of wide spatial coverage and rich information, and it is suitable for use as research data for smart cities. However, due to limitations in the imaging sensor conditions and complex weather, remote sensing images face the problems of insufficient resolution and cloud occlusion, which cannot meet the resolution requirements of smart city tasks. The remote sensing image super-resolution (SR) technique can improve the details and texture information without upgrading the imaging sensor system, which becomes a feasible solution for the above problems. In this paper, we propose a novel remote sensing image super-resolution method which leverages the texture features from internal and external references to help with SR reconstruction. We introduce the transformer attention mechanism to select and extract parts of texture features with high reference values to ensure that the network is lightweight, effective, and easier to deploy on edge computing devices. In addition, our network can automatically learn and adjust the alignment angles and scales of texture features for better SR results. Extensive comparison experiments show that our proposed method achieves superior performance compared with several state-of-the-art SR methods. In addition, we also evaluate the application value of our proposed SR method in urban region function recognition in smart cities. The dataset used in this task is low-quality. The comparative experiment between the original dataset and the SR dataset generated by our proposed SR method indicates that our method can effectively improve the recognition accuracy.

In recent years, the media industry has achieved rapid development and experienced three development stages from traditional media to new media and then to the current convergence media. Convergence media has brought about great changes in content production, communication mechanism, operation and maintenance management, but also brought about problems such as declining credibility of the industry, difficulty in confirming content rights, difficulty in protecting user privacy, etc. Research on convergence media based on blockchain can make use of the characteristics of blockchain to design or optimize the media industry. In this paper, we introduced the development of convergence media, blockchain and consensus mechanism, then we described a sustainable convergence media ecology based on blockchain. Furthermore, we designed and implemented a consensus mechanism named proof of efficiency (PoE). After analysis, PoE can provide high security and resist 51% resource attack, sybil attack, etc. The experimental results show that PoE has the characteristics of decentralization, strong consistency, low energy consumption, short average block generation time, high throughput and short block confirmation time; the consensus results of PoE can reflect the node’s ecological characteristics in convergence media which can stimulate the activity of nodes and better solve the generation of the Matthew effect.

In recent years, graph neural networks (GNNS) have been demonstrated to be a powerful way to learn graph data. The existing recommender systems based on the implicit factor models mainly use the interactive information between users and items for training and learning. A user–item graph, a user–attribute graph, and an item–attribute graph are constructed according to the interactions between users and items. The latent factors of users and items can be learned in these graph structure data. There are many methods for learning the latent factors of users and items. Still, they do not fully consider the influence of node attribute information on the representation of the latent factors of users and items. We propose a rating prediction recommendation model, short for LNNSR, utilizing the level of information granularity allocated on each attribute by developing a granular neural network. The different granularity distribution proportion weights of each attribute can be learned in the granular neural network. The learned granularity allocation proportion weights are integrated into the latent factor representation of users and items. Thus, we can capture user-embedding representations and item-embedding representations more accurately, and it can also provide a reasonable explanation for the recommendation results. Finally, we concatenate the user latent factor-embedding and the item latent factor-embedding and then feed it into a multi-layer perceptron for rating prediction. Extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed framework.

Sports competition is one of the most popular programs for many audiences. Tracking the players in sports game videos from broadcasts is a nontrivial challenge for computer vision researchers. In sports videos, the direction of an athlete’s movement changes quickly and unpredictably. Mutual occlusion between athletes is also more frequent in team competitions. However, the rich temporal contexts among the adjacent frames have been excluded from consideration. To address this dilemma, we propose an online transformer-based learnable framework in an end-to-end fashion. We use a transformer architecture to extract the temporal contexts between the successive frames and add them to the network training, which is robust to occlusion and complex direction changes in multiplayer tracking. We demonstrate the effectiveness of our method on three sports video datasets by comparing them with recently advanced multiplayer trackers.