Multi-scale feature compression is essential in machine vision tasks for reducing storage and transmission costs while maintaining task performance. However, existing multi-scale feature compression methods fail to effectively extract and aggregate the local and global correlations of multi-scale features, resulting in incomplete elimination of feature redundancies. Moreover, these multi-scale feature compression methods mainly rely on mean square error-based loss functions to optimize signal fidelity, but they fail to adequately preserve semantic information critical to machine vision tasks. To address these issues, a Multi-receptive-field Convolutional Neural Network (MCNN)-based multi-scale feature compression method is proposed in this paper, which not only achieves compact fusion of multi-scale features but also enhances the semantic fidelity of reconstructed features. To effectively eliminate feature redundancies, a multi-receptive-field-based feature fusion module is designed for capturing both local and global correlations in multi-scale features. To enhance the quality of the reconstructed features, a cosine similarity-based multi-fidelity loss function is developed by considering both signal and semantic fidelity. Extensive experiments on the object detection and instance segmentation tasks show that the proposed MCNN outperforms the state-of-the-art multi-scale feature compression methods in terms of compression efficiency. The source code of our proposed MCNN is publicly available athttps://github.com/NUIST-Videocoding/MCNN.git.

Joint entity and relation extraction plays a crucial role in various fields, including natural language processing, knowledge graph construction, and question answering systems. Among these methods, the joint extraction approach based on table filling has become a focal point for researchers due to its excellent performance and ability to accurately extract entities and relations from intricate sentences. Despite this, there is still potential to be further explored in such methods. Currently, most methods focus on learning relational features between words but neglect the relational features between labels and between labels and words. These relations are also important because a relation triplet can only be correctly identified when all labels are predicted correctly. This some what increases the risk of missing key information and inefficient decoding in the entity and relation extraction process. To overcome this limitation, we design a fine-grained relation feature extraction module that aims to encourage the model to fully consider the associations between words and labels, as well as between labels, while focusing on the relationships between words. Specifically, we create label representations and embed them into fine-grained relation extraction, enabling it to treat labels and word representations as queries, keys, and values, and then utilize the self-attention mechanism to model the associations between them. Additionally, the table labeling strategy has a significant impact on model performance, especially in terms of decoding efficiency. We propose a vertex labeling method to label the table, enhancing the model’s accuracy in entity recognition and overall decoding efficiency. We evaluate our proposed model on three benchmark datasets. The experimental results demonstrate that our model is effective and achieves state-of-the-art performance on all these datasets.

In recent years, federated learning has been rapidly developing as an emerging privacy computing method. Its unique distributed computing feature enables multiple participants to collaborate on modelling while ensuring that the data remains local and only the model parameters are passed on, thus effectively preserving privacy. This characteristic has led to the gradual introduction of Federated learning into real-world engineering applications, particularly in the financial sector. Banks, insurance companies, and other financial institutions are able to integrate financial data from multiple enterprises through federated learning to effectively perform a range of important financial tasks. However, financial data usually contains a large amount of personal information, and in addition to its privacy, unprocessed character data is difficult to be directly applied to models. Therefore, how to efficiently encode and convert these data into digital features has become an important problem to be solved in federated learning. The paper introduces a WOE(Weight Of Evidence) encoding method within a vertical federated learning framework, designed to maintain label confidentiality. This approach allows unlabelled participants to leverage label information for effective character feature WOE encoding, enhancing data utility while ensuring privacy. A classification task model for insurance anti-fraud is constructed and a series of evaluation metrics are used to demonstrate the effectiveness of the proposed method compared to other unsupervised coding methods. It also verifies that federated learning can integrate multi-party data and thus improve the classification ability of anti-fraud models.

The Versatile Video Coding (VVC) is the latest video coding standard that includes advanced intra coding techniques such as the chroma separate tree and cross-component linear model to improve the prediction accuracy of chroma components. However, these sophisticated techniques inevitably increase the computational complexity of chroma intra coding. In this paper, we propose a fast chroma intra-prediction mode decision algorithm to reduce the computational complexity of the VVC encoder. Firstly, the mode selection correlation between the current chroma Coding Unit (CU) and its nearest-encoded chroma CU is analyzed. Then, based on the variation of the sum of modulus differences, an early mode decision is proposed for the current chroma CU to determine whether the best coding mode should be traversed or directly inherited from its nearest encoded chroma CU. The experimental results show that the proposed algorithm significantly reduces the computational complexity of chroma intra-prediction and achieves an average of 28% chroma intra encoding time saving with only 0.08-1.43% performance degradation in terms of BD-rate.

Soft robots have a wide rang of applications due to their compliance, flexibility and low fabrication cost. Compare to rigid robots, soft robots are more safe for human. In this work, we design various multi-DoF actuators with spring reinforce and particle jamming, and two fabrication methods are proposed to make them. Each type of actuator is tested to evaluate the mechanical properties by experiments. Experimental results show that both spring and particle jamming have effect on the stiffness. Besides, Spring reinforced actuator (SRA) increases the maximum allowable inflation pressure, output bending force and gives a good linear relationship of bending. We also integrate spring and particles to fabricate a hybrid actuator whose behaviors are explored by experiments. Finally, we create a snake-like robotic manipulator assembled with two actuators and show its bending motion. Results show that the manipulator is able to achieve several bending shapes steadily and large range of motion.

Soft robots apply compliant materials to perform motions and behaviors not typically achievable by rigid robots. An underwater, compliant, multi-segment continuum manipulator that can bend, swallow, disgorge is developed in this study. The manipulator is driven by McKibben water hydraulic artificial muscle (WHAM). The mechanical properties of the WHAM are tested and analyzed experimentally. The kinematics model, which concerns about the variable diameter structure of the soft grippers, are established to simulate the behaviors of the manipulator among the bending, swallowing and disgorging procedure. A mouth-tongue collaborative soft robot assembled with another single-segment soft robot arm is presented. And its functions are experimentally testified. The distinctive functions were verified according to the experimental results.

A smart card based scheme is practical and widely used in remote mutual authentication. In 2006, Shieh-Wang pointed out the weakness of Juang’s remote mutual authentication scheme using smart card and further proposed a novel one to improve Juang’s. The advantages in Shieh-Wang’s scheme include effective mutual authentication, freely chosen password, no verification tables, low computational cost, session key agreement and no synchronized clocks. However, in 2007, Yoon-Yoo showed that Shieh-Wang’s scheme does not provide perfect forward secrecy, and is vulnerable to a privileged insider’s attack. Furthermore, the current paper demonstrates that Shieh-Wang’s scheme is also vulnerable to the parallel session attack and lack of wrong password detection and then presents a more efficient and secure scheme to resolve all the above problems including those that Yoon-Yoo has pointed out with less computational cost increase.