检索结果-南通市图书馆

Unsupervised image-to-image translation by semantics consistency and self-attention

在线全文

学校读者我要写书评

暂无评论

Optoelectronics Letters 2022年第3期18卷 175-180页

作者： ZHANG Zhibin XUE Wanli FU Guokai The key laboratory of Computer Vision and System of Ministry of Education Tianjin Key Laboratory of Intelligence Computing and Novel Software TechnologyTianjin University of TechnologyTianjin 300384China

Unsupervised image-to-image translation is a challenging task for computer vision. The goal of image translation is to learn a mapping between two domains, without corresponding image pairs. Many previous works only focused on image-level translation but ignored image features processing, which led to a certain semantics loss, such as the changes of the background of the generated image, partial transformation, and so on. In this work, we propose a method of image-to-image translation based on generative adversarial nets(GANs). We use autoencoder structure to extract image features in the generator and add semantic consistency loss on extracted features to maintain the semantic consistency of the generated image. Self-attention mechanism at the end of generator is used to obtain long-distance dependency in image. At the same time, as expanding the convolution receptive field, the quality of the generated image is enhanced. Quantitative experiment shows that our method significantly outperforms previous works. Especially on images with obvious foreground, our model shows an impressive improvement.

关键词： translation features semantic

Solid-state green-light-emitting upconversion coherent random laser in macroporous LiNbO_3:Er

在线全文

学校读者我要写书评

暂无评论

Chinese Optics Letters 2018年第1期16卷 62-65页

作者：石凡赵萌贾晨赵宇峰陈胜勇 key laboratory of Computer Vision and System of Ministry of Education Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology

A solid-state green-light-emitting upconversion coherent random laser was realized by pumping macroporous erbium-doped lithium niobate with a 980 nm laser. The lasing threshold was determined to be about 40 k W∕cm~2.Above the threshold, the emission intensity increased sharply with the increasing pump intensity. Moreover, a narrow multi-peaks structure was observed in the green-light-emission band, and the positions of lasing lines were various at different angles. The results were the direct evidences of coherent random lasing emission from macroporous erbium-doped lithium niobate. These phenomena were attributed to the coexistence of upconversion emission and a multiple scattering feedback mechanism.

关键词： Solid-state green-light-emitting upconversion coherent random laser in macroporous LiNbO3:Er LN ETU

Cooperative Optimization for Container Multi-modal Transport based on MAS

在线全文

学校读者我要写书评

暂无评论

Cooperative Optimization for Container Multi-modal Transport...

On Quantitative Analysis Method of Detecting the Content of Molten Alloy Steel Element Based on LIBS technology

第36届中国控制会议

作者： Zhao Endi Sun Bin Yang Peng Sun Junqing Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology

ISBN: (纸本)9781538629185

As the international container multi-modal transport has become the important bridge of international trade,routing optimization and carrier selection has been already attracted extensive attention.Besides economy and timeliness,the transport reliability under uncertainty environment is considered and a cooperative optimization model for container multi-modal transport based on multi-agent is also proposed.To deal with the coordination between the agents,the negotiation mechanism based on multi-attribute auction is further designed.With the bidding and the winning strategy of the carriers and the multi-modal transport operator proposed respectively,a mechanism based on three-dimensional network and non-linear compensation function for updating the scheduling plan is designed.And the simulation experiments which use the instances from China to Australia verify the feasibility of the model and the method proposed.

关键词： Container multi-modal transport Uncertainty environment Multi-agent Auction Three-dimensional network

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

On Quantitative Analysis Method of Detecting the Content of ...

A novel policy iteration algorithm for solving the optimal consensus control problem of a discrete-time multiagent system with unknown dynamics

第36届中国控制会议

作者： Zhang Qin Yang Peng Feng Meiling Sun Junqing Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology

ISBN: (纸本)9781538629185

Based on laser induced breakdown spectroscopy（LIBS） technique, the content of the main elements in the liquid steel of steel alloy can be detected in real time during melting process. In order to improve the detecting accuracy, the quantitative analysis method of laser induced breakdown spectroscopy（LIBS） for the melting alloy steels has been investigated. In this paper,the clustering method combined with the partial least squares method is applied in the metallurgical industry to determine the the element concentration of the steels. The experimental results show that the relative standard error is less than 1.316% and the average absolute error is 0.869%. The accuracy of the method is better than that of traditional partial least squares method, and the relative standard error of measurement is obviously reduced.

关键词： laser induced breakdown spectroscopy quantitative analysis partial least squares method relative standard error

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2023年第8期66卷 269-270页

作者： Wenkai XU Li WANG Shiwen SUN Chengyi XIA Zengqiang CHEN Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology The Engineering Research Center of Learning-Based Intelligent System Ministry of Education College of Artificial intelligence Nankai University

At present, an increasing number of researchers have noticed the importance of optimal consensus control(OCC) of multiagent systems(MASs) because of their rich practical applications in various areas [1–4]. To accomp...

关键词：

Efficient Multiagent Policy Optimization Based on Weighted Estimators in Stochastic Cooperative Environments

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & technology 2020年第2期35卷 268-280页

作者： Yan Zheng Jian-Ye Hao Zong-Zhang Zhang Zhao-Peng Meng Xiao-Tian Hao College of intelligence and computing Tianjin UniversityTianjin 300350China National key laboratory for novel software technology Nanjing UniversityNanjing 210023China

Multiagent deep reinforcement learning (MA-DRL) has received increasingly wide attention. Most of the existing MA-DRL algorithms, however, are still inefficient when faced with the non-stationarity due to agents changing behavior consistently in stochastic environments. This paper extends the weighted double estimator to multiagent domains and proposes an MA-DRL framework, named Weighted Double Deep Q-Network (WDDQN). By leveraging the weighted double estimator and the deep neural network, WDDQN can not only reduce the bias effectively but also handle scenarios with raw visual inputs. To achieve efficient cooperation in multiagent domains, we introduce a lenient reward network and scheduled replay strategy. Empirical results show that WDDQN outperforms an existing DRL algorithm (double DQN) and an MA-DRL algorithm (lenient Q-learning) regarding the averaged reward and the convergence speed and is more likely to converge to the Pareto-optimal Nash equilibrium in stochastic cooperative environments.

关键词： deep reinforcement learning multiagent system weighted double estimator lenient reinforcement learning cooperative Markov game

Application of Question and Answering on Virtual Human Dialogue:a Review and Prediction

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Donghua University(English Edition) 2015年第2期32卷 341-344页

作者：刘里 Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology key laboratory of Computer Vision and System(tianjin University of technology) Ministry of Education

Nowadays,virtual human(VH) is becoming a hot research topic in virtualization.VH dialogue can be categorized as an application of natural language processing(NLP) technology,since it is relational to question and answering(QA) technologies.In order to integrate these technologies,this paper reviews some important work on VH dialogue,and predicts some research points on the view of QA technologies.

关键词： virtual human(VH) dialogue natural language processing(NLP) question and answering(QA) interaction

A lightweight convolutional neural network for large-scale Chinese image caption

在线全文

学校读者我要写书评

暂无评论

Optoelectronics Letters 2021年第6期17卷 361-366页

作者：赵德新杨瑞雪郭淑涛 Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of TechnologyTianjin 300384China

Image caption is a high-level task in the area of image understanding,in which most of the models adopt a convolutional neural network(CNN)to extract image features assigning a recurrent neural network(RNN)to generate sentences.Researchers tend to design complex networks with deeper layers to improve the performance of feature extraction in recent years.Increasing the size of the network could obtain features of high quality,but it is not an efficient way in terms of computational cost.A large number of parameters brought by CNN makes the research difficult to apply in human daily life.In order to reduce the information loss of the convolutional process with less cost,we propose a lightweight convolutional neural network,named as Bifurcate-CNN(B-CNN).Furthermore,recent works are devoted to generating captions in English,in this paper,we develop an image caption model that generates descriptions in Chinese.Compared with Inception-v3,the depth of our model is shallower with fewer parameters,and the computational cost is lower.Evaluated on the AI CHALLENGER dataset,we prove that our model can enhance the performance,improving BLEU-4 from 46.1 to 49.9 and CIDEr from 142.5 to 156.6 respectively.

关键词： neural network image

Time-Ordered Collaborative Filtering for News Recommendation

在线全文

学校读者我要写书评

暂无评论

China Communications 2015年第12期12卷 53-62页

作者： XIAO Yingyuan AI Pengqiang Ching-Hsien Hsu WANG Hongya JIAO Xu tianjin University of technology tianjin key Lab of intelligence computing and novel software technology Chung Hua University Donghua University

Faced with hundreds of thousands of news articles in the news websites,it is difficult for users to find the news articles they are interested in.Therefore,various news recommender systems were built.In the news recommendation,these news articles read by a user is typically in the form of a time sequence.However,traditional news recommendation algorithms rarely consider the time sequence characteristic of user browsing behaviors.Therefore,the performance of traditional news recommendation algorithms is not good enough in predicting the next news article which a user will read.To solve this problem,this paper proposes a time-ordered collaborative filtering recommendation algorithm(TOCF),which takes the time sequence characteristic of user behaviors into account.Besides,a new method to compute the similarity among different users,named time-dependent similarity,is proposed.To demonstrate the efficiency of our solution,extensive experiments are conducted along with detailed performance analysis.

关键词：新闻网站时间序列协同过滤用户浏览行为有序推荐算法序列特征性能分析