Vision-language pretrained models have achieved significant success across various tasks. However, the lack of interpretability limits the application of multimodal models, especially for those that require the security of systems, data, and users. A key challenge in enhancing the interpretability of the models is the tradeoff between transparency and model performance in terms of accuracy and computing efficiency. We propose a vision-language multimodal pretrained model called multiway-fuzzy-experts bidirectional retention network (VL-MFER), which is designed to effectively interpret model decision processes while enhancing the consistent mapping between text and image features. We first propose a bidirectional retention network to handle and integrate the cross-modal high-dimensional data, which can effectively enhance both the performance and inference efficiency. Then, to improve the interpretability of vision-language pretrained models such as the unified vision-language pretraining with mixture-of-modality-experts, we propose a multiway fuzzy experts pool based on multiple different layered deep neuro-fuzzy systems for diverse downstream tasks. After training on diverse datasets consisting of images, text, and paired image-text data, we fine-tuned models for multiple vision and vision-language tasks. Experimental results show that VL-MFER performs well in all performance metrics of downstream tasks, and VL-MFER leads to enhancements in transparency compared to other methods, while improving computational efficiency and reducing inference time by up to 13%.

Online task-free continual learning (OTFCL) is a more challenging variant of continual learning that emphasizes the gradual shift of task boundaries and learning in an online mode. Existing methods rely on a memory buffer of old samples to prevent forgetting. However, the use of memory buffers not only raises privacy concerns but also hinders the efficient learning of new samples. To address this problem, we propose a novel framework called I$^{2}$CANSAY that gets rid of the dependence on memory buffers and efficiently learns the knowledge of new data from one-shot samples. Concretely, our framework comprises two main modules. Firstly, theInter-Class Analogical Augmentation(ICAN) module generates diverse pseudo-features for old classes based on the inter-class analogy of feature distributions for different new classes, serving as a substitute for the memory buffer. Secondly, theIntra-Class Significance Analysis(ISAY) module analyzes the significance of attributes for each class via its distribution standard deviation, and generates an importance vector as a correction bias for the linear classifier, thereby enhancing the capability of learning from new samples. We run our experiments on four popular image classification datasets: CoRe50, CIFAR-10, CIFAR-100, and CUB-200, our approach outperforms the prior state-of-the-art by a large margin.

In this paper, we focus on a challenging Online Task-Free Class Incremental Learning (OTFCIL) problem. Dif-ferent from the existing methods that continuously learn the feature space from data streams, we propose a novel compute-and-align paradigm for the OTFCIL. It first com-putes an optimal geometry, i.e., the class prototype distri-bution, for classifying existing classes and updates it when new classes emerge, and then trains a DNN model by aligning its feature space to the optimal geometry. To this end, we develop a novel Dynamic Neural Collapse (DNC) algorithm to compute and update the optimal geometry. The DNC ex-pands the geometry when new classes emerge without loss of the geometry optimality and guarantees the drift distance of old class prototypes with an explicit upper bound. On this basis, we propose a novel DYnamic feature space Self-OrganizatioN (DYSON) method containing three ma-jor components, including 1) a feature extractor, 2) a Dy-namic Feature-Geometry Alignment (DFGA) module aligning the feature space to the optimal geometry computed by DNC and 3) a training-free class-incremental classifier de-rived from the DNC geometry. Experimental comparison results on four benchmark datasets, including CIFAR10, CI-FAR100, CUB200, and CoRe50, demonstrate the efficiency and superiority of the DYSON method. The source code is released at https://github.com/isCDX2IDYSON.

Bolts are important parts of transmission lines, and their states are closely related to the safe operation of transmission lines. Compared with insulators, U-shaped rings, and other fittings, bolts are small objects, and the detection of bolt and pin missing is difficult for transmission line patrol video analysis. This paper optimizes the parameters of the YOLOX network to adapt to the multiscale object detection task in the complex scene of the transmission line, and proposes a cascaded network model. The cascaded network locates the important large-scale fittings with bolts by the first layer and then detects the small-scale bolts on the fittings by the second layer, which greatly improves the detection accuracy of the small bolts. Finally, the effectiveness of the method is verified by experiments. The experimental results show that the cascaded YOLOX network can accurately detect the bolts that are originally difficult to detect. It effectively solves the problems of low detection rate of small bolts and pin missing defects.

With the development of social networks, we are more interested in every aspect of the relationship. We conducted a visualization analysis of the papers published on two journals of Communication University of China in five years. In addition, we combine the academic social network of three art universities in Beijing based on CNKI and use complex network-related knowledge to analyze the collaboration of these universities. In this paper, we apply the knowledge of visualization tools and complex networks to analyze the authors who have high productivity, the keywords of these papers and the academic partnerships of the three universities. In experiments, each college is regarded as a social network model. From the perspective of academic social networks and collaborative networks, we extract some features of each of the three art universities and make some conclusions.

Universal service terminal (UST) has been proposed as a novel virtual distributed terminal supporting pervasive applications. It provides proactive services via aggregating diverse capabilities of devices around the user and auto-configuring them according to the capabilities, availability, user's preference and application context, which results in always the best experience (ABE). The issues related to concept, architecture, design, and simulation are addressed and some basic procedures are introduced. Moreover, the results of simulation comparing two scenarios are given to validate the mechanisms designed in UST.

The development of mobile communication technologies and smart portable device has great impact on the society, which makes the ubiquitous computing and seamless service come true. However, a major challenge is that how to provide a software platform supporting personalized and context-aware services and applications. Research on universal service terminal (UST) aims at providing light-weight application layer to enable the interconnection between the terminals and providing user with always the best service experience (ABE). In this paper, we propose a dynamic aggregation mechanism, which introduces the multi-objective optimal functions to optimize the user satisfaction. Furthermore, a rapid optimal algorithm based on simulated annealing algorithm is provided to improve the search efficiency.