Fine-grained image datasets have small inter-class differences and large intra-class differences, which is a difficulty of the fine-grained image classification. Traditional fine-grained image classification methods only focus on the visual features of images. However, this limitation can be eliminated when these methods are improved with multimodal information. This paper proposes an improved fine-grained image classification method with multimodal information that includes multimodal data preprocessing, multimodal feature extraction, multi-temporal feature fusion and decision correction. The preprocessing method proposed solves the problems of scattered distribution, difficult processing and uneven contribution to prediction of multimodal data through normalization, packing phrases and weighted concatenating methods. When extracting multimodal features, the SAMLP (Self-Attention MLP) module proposed combines self-attention with MLP to capture the internal correlation of multimodal information. The multi-temporal feature fusion proposed is divided into early feature fusion and late feature fusion. The former refers to adding multimodal information markers to the original image, and the latter refers to designing a multi-cascade dynamic MLP structure to fuse visual features and multimodal features. In view of the limitation of feature fusion, a decision strategy is proposed to revise the prediction results of fused features according to the prediction results of multimodal features. Ablation experiment on INAT18-1K and INAT21-1K datasets shows that our method is effective in improving classification with multimodal information. Experiments on the INAT2021_mini large dataset show that the comprehensive method in this paper has higher accuracy and negligible efficiency loss compared with the state-of-the-art method.

With the development of the Internet of Things (IoTs), there is an increasing demand for Location Based Services (LBS) for various applications. Traditional indoor and outdoor positioning systems, such as global positioning system (GPS) and Wi-Fi, have mature solutions for line-of-sight (LOS) environments. However, performances of existing positioning techniques in multipath environments may experience significant degradation due to the lack of LOS path information and the inaccuracies in parameter estimation caused by the presence of non-line-of-sight (NLOS) influences. In this article, we provide an extensive overview of the positioning techniques for the outdoor and indoor environments. We first introduce the mainstream techniques of current positioning system and further give an insight for NLOS positioning techniques. Then a virtual station-based single-station NLOS positioning algorithm is proposed to improve the positioning accuracy and relax the constraints of existing NLOS positioning solutions. Finally, we investigate technologies that have great potential for positioning system in the sixth generation (6G) communication system.

Aiming for ultra-reliable low-latency wireless communications required in industrial internet of things (IIoT) applications, this paper studies a simple cognitive radio non-orthogonal multiple access (CR-NOMA) downlink system. This system consists of two secondary users (SUs) dynamically interfered by the primary user (PU), and its performance is characterized by the outage probability of the SU communications. This outage probability is calculated under two conditions where, a) the transmission of PU starts after the channel state information (CSI) is acquired, so the base station (BS) is oblivious of the interference, and b) when the BS is aware of the PU interference, and the NOMA transmission is adapted to the more comprehensive knowledge of the signal to interference plus noise ratio (SINR). These results are verified by simulations, and their good agreement suggests our calculations can be used to reduce the complexity of future analysis. We find the outage probability is reduced when the SUs move further away from the primary transmitter or when the signal from PU is less powerful, and the BS always has better performance when it is aware of the interference. The findings thus emphasize the importance of monitoring the channel quality and realtime feedback to optimize the performance of CR-NOMA system.

The social relation is a fundamental attribute of human beings in daily life. The ability of humans to form large organizations and institutions stems directly from our complex social networks. Therefore, understanding social relationships in the context of multimedia is crucial for building domain-specific or general artificial intelligence systems. The key to reason social relations lies in understanding the human interactions between individuals through multimodal representations such as action and utterance. However, due to video editing techniques and various narrative sequences in videos, two individuals with social relationships may not appear together in the same frame or clip. Additionally, social relations may manifest in different levels of granularity in video expressions. Previous research has not effectively addressed these challenges. Therefore, this paper proposes a Multi-Granularity Relation Graph Aggregation Framework (MGRG) to enhance the inference ability for social relation reasoning in multimedia content, like video. Different from existing methods, our method considers the paradigm of jointly inferring the relations by constructing a social relation graph. We design a hierarchical multimodal relation graph illustrating the exchange of information between individuals' roles, capturing the complex interactions at multi-levels of granularity from fine to coarse. In MGRG, we propose two aggregation modules to cluster multimodal features in different granularity layer relation graph, considering temporal aspects and importance. Experimental results show that our method generates a logical and coherent social relation graph and improves the performance in accuracy.