检索结果-内蒙古大学图书馆

A survey of facial expression recognition based on deep learning

学校读者我要写书评

暂无评论

A survey of facial expression recognition based on deep lear...

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Heng Wei Zhi Zhang Collage of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9781728151694

ISBN: (纸本)9781728151700

Facial expression recognition is the key research direction in many fields such as machine vision, pattern recognition and artificial intelligence. lt has become a research hotspot of many scholars and experts. This paper gives a comprehensive overview of deep expression recognition from image preprocessing, common expression recognition networks, and common expression databases. Then we review the current design and training strategies of deep neural networks based on static images and dynamic images, and discuss their advantages and limitations. Finally, the future challenges and corresponding opportunities in the field are analyzed, as well as the future direction of deep learning expression recognition systems.

关键词： Deep learning Training Image recognition databases Face recognition Neural networks Training data

Feature Location Benchmark for Decomposing and Reusing Android Apps

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tang, Yutian Zhou, Hao Xu, Zhou Luo, Xiapu Cai, Yan Zhang, Tao Department of Computing Hong Kong Polytechnic University Hong Kong School of Big Data and Software Engineering Chongqing University China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Faculty of Information Technology Macau University of Science and Technology China

Software reuse enables developers to reuse architecture, programs and other software artifacts. Realizing a systematical reuse in software brings a large amount of benefits for stakeholders, including lower maintenance efforts, lower development costs, and time to market. Unfortunately, currently implementing a framework for large-scale software reuse in Android apps is still a huge problem, regarding the complexity of the task and lacking of practical technical support from either tools or domain experts. Therefore, proposing a feature location benchmark for apps will help developers either optimize their feature location techniques or reuse the assets created in the benchmark for reusing. In this paper, we release a feature location benchmark, which can be used for those developers, who intend to compose software product lines (SPL) and release reuse in apps. The benchmark not only contributes to the research community for reuse research, but also helps participants in industry for optimizing their architecture and enhancing modularity. In addition, we also develop an Android Studio plugin named caIDE for developers to view and operate on the benchmark. Copyright © 2020, The Authors. All rights reserved.

关键词： Computer software reusability

Automatic Generation Method of Ancient Poetry Based on LSTM

学校读者我要写书评

暂无评论

Automatic Generation Method of Ancient Poetry Based on LSTM

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Hanshuang Zhang Zhi Zhang College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9781728151694

ISBN: (纸本)9781728151700

This paper mainly focuses on the literary genre of ancient poetry with a certain rhythm and cadence, and proposes a novel automatic generation model of ancient poetry. The model uses about 300,000 Tang poems and Song poems as training data, uses One-hot encoding to process data, and uses long short-term memory networks (LSTMs) to learn the semantics of ancient poetry texts and conduct research across a single RNN structure. According to the user's requirements, the model can automatically calculate the most relevant coherent words in the context of the selected context, and generate common ancient poetry and specified words. The method of BLEU automatic evaluation and manual evaluation finally demonstrates the effectiveness of the experiment.

关键词： Industrial electronics Semantics Training data Manuals Rhythm Encoding Periodic structures

Study on the Relationships between Utilization Ratios and Conversion Rates of Nitrogen,Phosphorus and Potassium for Wheat

学校读者我要写书评

暂无评论

Meteorological and Environmental Research 2020年第5期11卷 46-54页

作者： Zhiping HUANG Xianda HOU Shutian LIU Shuojin WANG Hongyan ZHENG Jian DING Changhong MI Ling LU Yanlin HOU Agro-Environmental Protection Institute Ministry of Agriculture and Rural AffairsTianjin 300191China Guangxi Geographical Indication Crops Research Center of Big Data Mining and Experimental Engineering Technology Nanning Normal UniversityNanning 530001China Guangxi Key Laboratory of Earth Surface Processes and Intelligent Simulation Nanning Normal UniversityNanning 530001China Key Laboratory of Environment Change and Resources Use in Beibu Gulf(Nanning Normal University) Nanning 530001China

This paper studied the relationships between utilization ratios and conversion rates of nitrogen,phosphorus and potassium for wheat by data mining method based on data of"3414 fertilizer field trials"of wheat by published papers from national soil testing and recommendation since *** results and conclusions were as follows:①the conceptual model of fertilizer utilization ratio of wheat for plot was that,Y N≈a+b×optimum nitrogen application amount+c×optimum fertilizer amount of K+d×rainfall in growth season,Y P≈a+b×optimum fertilizer amount of K+c×rainfall in growth season,Y K≈a+b×temperature in growth season+c×rainfall in growth season-d×optimum yield-e×optimum nitrogen application amount,respectively.②Fertilizer utilization ratio and nutrient conversion rate had 4 kinds of *** significant relationships:13,of which 8 were soil nutrients,the results showed that soil nutrients had little effect on nutrient conversion rate and fertilizer utilization ratio;consistent significant relationships:4,they were all nitrogen and phosphorus,explaining the importance of nitrogen and phosphorus;contrary significant relationships:6,they were all nitrogen and phosphorus,illustrating that phosphorus and nitrogen had inhibitory effect;complementary significant relationships:31,the cause of the complementary phenomenon was that the fertilizer utilization ratio was the measuring index of fertilizer efficiency in one season,while the nutrient conversion rate was the measuring index of fertilizer efficiency in more *** showed that the fertilizer utilization rate was significantly correlated,or the nutrient conversion rate was significantly correlated.

关键词： Optimum yield Optimum fertilization amount Nutrient conversion rate Fertilizer utilization ratio Relative abundance-deficiency value of soil nutrient

Syntax-enhanced Pre-trained model

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xu, Zenan Guo, Daya Tang, Duyu Su, Qinliang Shou, Linjun Gong, Ming Zhong, Wanjun Quan, Xiaojun Jiang, Daxin Duan, Nan School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Microsoft Research Asia Beijing China Microsoft Search Technology Center Asia Beijing China Guangdong Key Laboratory Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. Such a problem would lead to the necessity of having human-annotated syntactic information, which limits the application of existing methods to broader scenarios. To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. Our model is based on Transformer with a syntax-aware attention layer that considers the dependency tree of the text. We further introduce a new pre-training task of predicting the syntactic distance among tokens in the dependency tree. We evaluate the model on three downstream tasks, including relation classification, entity typing, and question answering. Results show that our model achieves state-of-the-art performance on six public benchmark datasets. We have two major findings. First, we demonstrate that infusing automatically produced syntax of text improves pre-trained models. Second, global syntactic distances among tokens bring larger performance gains compared to local head relations between contiguous tokens. Copyright © 2020, The Authors. All rights reserved.

关键词： Syntactics

A study on the uncertainty of convolutional layers in deep neural networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shen, Haojing Chen, Sihong Wang, Ran Big Data Institute College of Computer Science and Software Engineering Guangdong Key Lab. of Intelligent Information Processing Shenzhen University ShenzhenGuangdong518060 China College of Mathematics and Statistics Shenzhen University Shenzhen518060 China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen518060 China

This paper shows a Min-Max property existing in the connection weights of the convolutional layers in a neural network structure, i.e., the LeNet. Specifically, the Min-Max property means that, during the back propagation-based training for LeNet, the weights of the convolutional layers will become far away from their centers of intervals, i.e., decreasing to their minimum or increasing to their maximum. From the perspective of uncertainty, we demonstrate that the Min-Max property corresponds to minimizing the fuzziness of the model parameters through a simplified formulation of convolution. It is experimentally confirmed that the model with the Min-Max property has a stronger adversarial robustness, thus this property can be incorporated into the design of loss function. This paper points out a changing tendency of uncertainty in the convolutional layers of LeNet structure, and gives some insights to the interpretability of convolution. © 2020, CC-BY.

关键词： Convolution

Discriminative Additive Scale Loss for Deep Imbalanced Classification and Embedding

学校读者我要写书评

暂无评论

Discriminative Additive Scale Loss for Deep Imbalanced Class...

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Weiming Jiang Yang Wang Qiaolin Ye Mingbo Zhao Mingliang Xu Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China AI team Shanghai Shizhuang Information Technology Co. Ltd Shanghai China College of Information Science and Technology Nanjing Forestry University Nanjing China School of Information Science and Technology Donghua University Shanghai China School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (纸本)9781665423991

Real-world data in emerging applications may suffer from highly-skewed class imbalanced distribution, however how to deal with this kind of problem appropriately through deep learning needs further investigation. In this paper, we mainly propose a novel cross-entropy based loss function, referred to as Additive Scale Loss (ASL), for deep representation learning and imbalanced classification. To deal with the class imbalanced problem, ASL aims at increasing the loss in case of misclassification, which can avoid the superimposed loss values caused by the large amount of easily classified data in the unbalanced database to dominate the loss value of misclassified data. Moreover, in real-world applications, one data source may be used for multiple scenarios, such as classification and embedding learning, however training two separable models to handle these problems is costly, especially in deep learning area. To tackle this issue, we present and integrate a discriminative inter-class separation term into ASL, and propose a discriminative ASL (D-ASL), which can not only improve the classification performance, but also obtain discriminative representations simultaneously. The discriminative inter-class separation term is general, and can be easily integrated to other loss functions, such as CE and FL, as the byproducts. Finally, a new deep convolutional neural network equipped with D-ASL and a fully-connected (FC) layer is proposed, which can classify the imbalanced image data and obtain the discriminative representations at the same time. Extensive experimental results verified the superior performance of our method.

关键词： Deep learning Training Representation learning Additives databases Soft sensors Conferences

XTQA: Span-Level Explanations for Textbook Question Answering

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ma, Jie Chai, Qi Liu, Jun Yin, Qingyu Wang, Pinghui Zheng, Qinghua Ministry of Education of Key Lab for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering The School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Amazon United States

Textbook Question Answering (TQA) is the task of correctly answering diagram or non-diagram questions given large multi-modal contexts consisting of abundant essays and diagrams. In real-world scenarios, an explainable TQA system plays a key role in deepening humans’ understanding of learned knowledge. However, there is no work to investigate how to provide explanations currently. To address this issue, we devise a novel architecture towards span-level eXplanations for TQA (XTQA). In this paper, spans are the combinations of sentences within a paragraph. The key idea is to consider the entire textual context of a lesson as candidate evidence, and then use our proposed coarse-to-fine grained Explanation Extracting (EE) algorithm to narrow down the evidence scope and extract the span-level explanations with varying lengths for answering different questions. The EE algorithm can also be integrated into other TQA methods to make them explainable and improve the TQA performance. Experimental results show that XTQA obtains the best overall explanation result (mIoU) of 52.38% on the first 300 questions of CK12-QA test splits, demonstrating the explainability of our method (non-diagram: 150 and diagram: 150). The results also show that XTQA achieves the best TQA performance of 36.46% and 36.95% on the aforementioned splits respectively. We have released our code in https://***/dr-majie/*** Codes 68T07 Copyright © 2020, The Authors. All rights reserved.

关键词： Textbooks

Global context-aware progressive aggregation network for salient object detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Zuyao Xu, Qianqian Cong, Runmin Huang, Qingming University of Chinese Academy of Sciences Beijing China Key Lab. of Intelligent Information Processing ICT CAS Beijing China Institute of Information Science Beijing Jiaotong University Beijing China Key Lab. of Big Data Mining and Knowledge Management CAS Beijing China Peng Cheng Laboratory Shenzhen Guangdong China

Deep convolutional neural networks have achieved competitive performance in salient object detection, in which how to learn effective and comprehensive features plays a critical role. Most of the previous works mainly adopted multiplelevel feature integration yet ignored the gap between different features. Besides, there also exists a dilution process of high-level features as they passed on the top-down pathway. To remedy these issues, we propose a novel network named GCPANet to effectively integrate low-level appearance features, high-level semantic features, and global context features through some progressive context-aware Feature Interweaved Aggregation (FIA) modules and generate the saliency map in a supervised way. Moreover, a Head Attention (HA) module is used to reduce information redundancy and enhance the top layers features by leveraging the spatial and channel-wise attention, and the Self Refinement (SR) module is utilized to further refine and heighten the input features. Furthermore, we design the Global Context Flow (GCF) module to generate the global context information at different stages, which aims to learn the relationship among different salient regions and alleviate the dilution effect of high-level features. Experimental results on six benchmark datasets demonstrate that the proposed approach outperforms the state-of-the-art methods both quantitatively and qualitatively. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks