Relational-Convergent Transformer for image captioning

Image captioning describes the visual content of a given image by using natural language sentences, and plays a key role in the fusion and utilization of the image features. However, in the existing image captioning models, the decoder sometimes fails to efficiently capture the relationships between image features because of their lack of sequential dependencies. In this paper, we propose a Relational-Convergent Transformer (RCT) network to obtain complex intramodality representations in image captioning. In RCT, a Relational Fusion Module (RFM) is designed for capturing the local and global information of an image by a recursive fusion. Then, a Relational-Convergent Attention (RCA) is proposed, which is composed of a self-attention and a hierarchical fusion module for aggregating global relational information to extract a more comprehensive intramodal contextual representation. To validate the effectiveness of the proposed model, extensive experiments are conducted on the MSCOCO dataset. The experimental results show that the proposed method outperforms some of the state-of-the-art methods.     

基于多流网络一致性的视频显著性检测

现有的视频显著性检测算法通常采用双流结构提取视频的时空线索,其中运动信息作为双流结构的一个分支,在显著物体发生剧烈或慢速移动时存在运动估计准确率低的问题,并且不合理的训练数据或方案使得权重偏向单个分支结构。提出一种基于多流网络一致性的视频显著性检测算法MSNC。设计并使用一种新的三重网络结构提取预选目标区域的颜色信息、时序信息和先验特征,通过先验特征补偿运动流的缺陷,并提高运动线索的利用率。采用多流一致性融合模型优化三流分支,得到不同特征的最佳融合方案。同时通过循环训练策略平衡三重网络的权重,以避免网络过度拟合单流分支,从而有效地提高运动估计和定位的准确率。在Davis数据集上的实验结果表明,相比PCSA、SSAV、MGA等算法,该算法的鲁棒性更优,其maxF和S-Measure值分别达到0.893和0.912,MAE仅为0.021。     

Neural Machine Translation by Fusing Key Information of Text

When the Transformer proposed by Google in 2017, it was first used for machine translation tasks and achieved the state of the art at that time. Although the current neural machine translation model can generate high quality translation results, there are still mistranslations and omissions in the translation of key information of long sentences. On the other hand, the most important part in traditional translation tasks is the translation of key information. In the translation results, as long as the key information is translated accurately and completely, even if other parts of the results are translated incorrect, the final translation results’ quality can still be guaranteed. In order to solve the problem of mistranslation and missed translation effectively, and improve the accuracy and completeness of long sentence translation in machine translation, this paper proposes a key information fused neural machine translation model based on Transformer. The model proposed in this paper extracts the keywords of the source language text separately as the input of the encoder. After the same encoding as the source language text, it is fused with the output of the source language text encoded by the encoder, then the key information is processed and input into the decoder. With incorporating keyword information from the source language sentence, the model’s performance in the task of translating long sentences is very reliable. In order to verify the effectiveness of the method of fusion of key information proposed in this paper, a series of experiments were carried out on the verification set. The experimental results show that the Bilingual Evaluation Understudy (BLEU) score of the model proposed in this paper on the Workshop on Machine Translation (WMT) 2017 test dataset is higher than the BLEU score of Transformer proposed by Google on the WMT2017 test dataset. The experimental results show the advantages of the model proposed in this paper.     

Residual Feature Attentional Fusion Network for Lightweight Chest CT Image Super-Resolution

The diagnosis of COVID-19 requires chest computed tomography (CT). High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease, so it is of clinical importance to study super-resolution (SR) algorithms applied to CT images to improve the resolution of CT images. However, most of the existing SR algorithms are studied based on natural images, which are not suitable for medical images; and most of these algorithms improve the reconstruction quality by increasing the network depth, which is not suitable for machines with limited resources. To alleviate these issues, we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution (RFAFN). Specifically, we design a contextual feature extraction block (CFEB) that can extract CT image features more efficiently and accurately than ordinary residual blocks. In addition, we propose a feature-weighted cascading strategy (FWCS) based on attentional feature fusion blocks (AFFB) to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information. Finally, we suggest a global hierarchical feature fusion strategy (GHFFS), which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels. Numerous experiments show that our method performs better than most of the state-of-the-art (SOTA) methods on the COVID-19 chest CT dataset. In detail, the peak signal-to-noise ratio (PSNR) is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at SR compared to the suboptimal method, but the number of parameters and multi-adds are reduced by 22K and 0.43G, respectively. Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.     

Diode-Pumped Solid-State Lasers for Inertial Fusion Energy

We have begun building the Mercury laser system as the first in a series of new generation diode-pumped solid-state lasers for inertial fusion research. Mercury will integrate three key technologies: diodes, crystals, and gas cooling, within a unique laser architecture that is scalable to kilojoule and megajoule energy levels for fusion energy applications. The primary near-term performance goals include 10% electrical efficiencies at 10 Hz and 100J with a 2–10 ns pulse length at 1.047 m wavelength. When completed, Mercury will allow rep-rated target experiments with multiple chambers for high energy density physics research.     

A hybrid data-fusion system using modal data and probabilistic neural network for damage detection

This paper addresses a novel hybrid data-fusion system for damage detection by integrating the data fusion technique, probabilistic neural network (PNN) models and measured modal data. The hybrid system proposed consists of three models, i.e. a feature-level fusion model, a decision-level fusion model and a single PNN classifier model without data fusion. Underlying this system is the idea that we can choose any of these models for damage detection under different circumstances, i.e. the feature-level model is preferable to other models when enormous data are made available through multi-sensors, whereas the confidence level for each of multi-sensors must be determined (as a prerequisite) before the adoption of the decision-level model, and lastly, the single model is applicable only when data collected is somehow limited as in the cases when few sensors have been installed or are known to be functioning properly. The hybrid system is suitable for damage detection and identification of a complex structure, especially when a huge volume of measured data, often with uncertainties, are involved, such as the data available from a large-scale structural health monitoring system. The numerical simulations conducted by applying the proposed system to detect both single- and multi-damage patterns of a 7-storey steel frame show that the hybrid data-fusion system cannot only reliably identify damage with different noise levels, but also have excellent anti-noise capability and robustness.     

Structure damage diagnosis using neural network and feature fusion

A structure damage diagnosis method combining the wavelet packet decomposition, multi-sensor feature fusion theory and neural network pattern classification was presented. Firstly, vibration signals gathered from sensors were decomposed using orthogonal wavelet. Secondly, the relative energy of decomposed frequency band was calculated. Thirdly, the input feature vectors of neural network classifier were built by fusing wavelet packet relative energy distribution of these sensors. Finally, with the trained classifier, damage diagnosis and assessment was realized. The result indicates that, a much more precise and reliable diagnosis information is obtained and the diagnosis accuracy is improved as well.     

Finite-time weighted average consensus with respect to a monotonic function and its application

The consensus state is an important and fundamental quantity for consensus problems of multi-agent systems, which indicates where all the dynamical agents reach. In this paper, weighted average consensus with respect to a monotonic function, which means that the trajectories of the monotonic function along the state of each agent reach the weighted average of their initial values, is studied for a group of kinematic agents with time-varying topology. By constructing a continuous nonlinear distributed protocol, such a consensus problem can be solved in finite time even though the time-varying topology involves unconnected graphs. Then the distributed protocol is employed to compute the maximum-likelihood estimation of unknown parameters over sensor networks. Compared with the existing results, the estimate scheme proposed here may reduce the costs of data communication, storage memory, book-keeping and computational overheads.