检索结果-内蒙古大学图书馆

Skeptical deep learning with distribution correction

学校读者我要写书评

暂无评论

arXiv 2018年

作者： An, Mingxiao Chen, Yongzhou Liu, Qi Liu, Chuanren Lv, Guangyi Wu, Fangzhao Ma, Jianhui Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Drexel University Microsoft Research Asia China

Recently deep neural networks have been successfully used for various classification tasks, especially for problems with massive perfectly labeled training data. However, it is often costly to have large-scale credible labels in real-world applications. One solution is to make supervised learning robust with imperfectly labeled input. In this paper, we develop a distribution correction approach that allows deep neural networks to avoid overfitting imperfect training data. Specifically, we treat the noisy input as samples from an incorrect distribution, which will be automatically corrected during our training process. We test our approach on several classification datasets with elaborately generated noisy labels. The results show significantly higher prediction and recovery accuracy with our approach compared to alternative methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

How images inspire poems: Generating classical Chinese poetry from images with memory networks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Xu, Linli Jiang, Liang Qin, Chuan Wang, Zhe Du, Dongfang Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China AI Department Ant Financial Services Group

With the recent advances of neural models and natural language processing, automatic generation of classical Chinese poetry has drawn significant attention due to its artistic and cultural value. Previous works mainly focus on generating poetry given keywords or other text information, while visual inspirations for poetry have been rarely explored. Generating poetry from images is much more challenging than generating poetry from text, since images contain very rich visual information which cannot be described completely using several keywords, and a good poem should convey the image accurately. In this paper, we propose a memory based neural model which exploits images to generate poems. Specifically, an Encoder-Decoder model with a topic memory network is proposed to generate classical Chinese poetry from images. To the best of our knowledge, this is the first work attempting to generate classical Chinese poetry from images with neural networks. A comprehensive experimental investigation with both human evaluation and quantitative analysis demonstrates that the proposed model can generate poems which convey images accurately. Copyright © 2018, The Authors. All rights reserved.

关键词： Natural language processing systems

Non-autoregressive neural machine translation with enhanced decoder input

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Guo, Junliang Tan, Xu He, Di Qin, Tao Xu, Linli Liu, Tie-Yan Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Microsoft Research School of EECS Peking University

Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive translation (AT) models. Previous work shows that the quality of the inputs of the decoder is important and largely impacts the model accuracy. In this paper, we propose two methods to enhance the decoder inputs so as to improve NAT models. The first one directly leverages a phrase table generated by conventional SMT approaches to translate source tokens to target tokens, which are then fed into the decoder as inputs. The second one transforms source-side word embeddings to target-side word embeddings through sentence-level alignment and word-level adversary learning, and then feeds the transformed word embeddings into the decoder as inputs. Experimental results show our method largely outperforms the NAT baseline (Gu et al. 2017) by 5.11 BLEU scores on WMT14 English-German task and 4.72 BLEU scores on WMT16 English-Romanian task. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

Research on the Brain-inspired Cross-modal Neural Cognitive Computing Framework

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Yang Key Laboratory of Big Data Analysis and Processing of Henan province Intelligent Technology and Application Engineering Research Centre of Henan province College of Computer Science and Information Engineering Henan University Kaifeng475004 China

To address modeling problems of brain-inspired intelligence, this thesis is focused on researching in the semantic-oriented framework design for multimedia and multimodal information. The Multimedia Neural Cognitive Computing (MNCC) model was designed based on the nervous mechanism and cognitive architecture. Furthermore, the semantic-oriented hierarchical Cross-modal Neural Cognitive Computing (CNCC) framework was proposed based on MNCC model, and formal description and analysis for CNCC framework was given. It would effectively improve the performance of semantic processing for multimedia and cross-modal information, and has far-reaching significance for exploration and realization brain-inspired computing. Copyright © 2018, The Authors. All rights reserved.

关键词： Semantics

A Ship Draft Line Detection Method Based on Image Processing and Deep Learning

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2020年第1期1575卷

作者： Zhong Wang Peibei Shi Chao Wu School of Computer Science and Technology Hefei Normal University No. 1688 Lianhua Road Hefei Anhui China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China No. 96 Jinzhai Road Hefei Anhui China Network and Information Center University of Science and Technology of China No. 96 Jinzhai Road Hefei Anhui China

The traditional ship draft detection method mainly adopts the method of the human eye observation, which has the problems of large precision error and slow detection speed. Aiming at this problem, this paper proposes a ship draft line detection method based on image processing and deep learning. The color image is first transformed into a grayscale image, and the corner detection is carried out by Harris operator. Contour map is obtained using Canny operator for edge detection, and line segment detection is performed using Hough algorithm. The water surface is determined by calculating the lowest position of the corner point. Then the grayscale image is binarized to increase the contrast of the image, the digital area is determined by the corner positions of the highest and lowest points, and finally the convolutional neural network is used to perform character recognition and calculate the draft of the ship. Tested on videos of various scenes, the error of the proposed method is less than 1cm.

关键词：

A Fatigue Driving Detection Method based on Deep Learning and Image Processing

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2020年第1期1575卷

作者： Zhong Wang Peibei Shi Chao Wu School of Computer Science and Technology Hefei Normal University No. 1688 Lianhua Road Hefei Anhui China. Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China No. 96 Jinzhai Road Hefei Anhui China. Network and Information Center University of Science and Technology of China No. 96 Jinzhai Road Hefei Anhui China

Driving fatigue is one of the important causes of traffic accidents. It is of great significance to study fatigue driving detection algorithms to improve human life and property safety. This paper proposes a fatigue driving detection method based on deep learning and image processing. First, the driver's face image is obtained in real time through the camera and the face image is detected using the MTCNN model. Next the image processing is performed on the face image, including three steps: grayscale processing, binarization processing, and human eye detection. Then we check the legitimacy of the human eye image and calculate the eye closure rate, and finally use the PERCLOS principle to analyze the fatigue state of the driver. The experimental results show that the proposed method has high detection rate and low false alarm rate, and has strong practicality.

关键词：

Aggregation Signature for Small Object Tracking

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Chunlei Ding, Wenrui Yang, Jinyu Murino, Vittorio Zhang, Baochang Han, Jungong Guo, Guodong School of Electrical and Information Engineering Beihang University Beijing China Unmanned System Research Institute Beihang University Beijing China School of Computer Science University of Birmingham British United Kingdom University of Verona Verona Italy Pattern Analysis and Computer Vision department Istituto Italiano di Tecnologia Genoa Italy School of Automation Science and Electrical Engineering Beihang University Beijing China Shenzhen Academy of Aerospace Technology Shenzhen China WMG Data Science Group University of Warwick CoventryCV4 7AL United Kingdom Institute of Deep Learning Baidu Research and National Engineering Laboratory for Deep Learning Technology and Application

—Small object tracking becomes an increasingly important task, which however has been largely unexplored in computer vision. The great challenges stem from the facts that: 1) small objects show extreme vague and variable appearances, and 2) they tend to be lost easier as compared to normal-sized ones due to the shaking of lens. In this paper, we propose a novel aggregation signature suitable for small object tracking, especially aiming for the challenge of sudden and large drift. We make three-fold contributions in this work. First, technically, we propose a new descriptor, named aggregation signature, based on saliency, able to represent highly distinctive features for small objects. Second, theoretically, we prove that the proposed signature matches the foreground object more accurately with a high probability. Third, experimentally, the aggregation signature achieves a high performance on multiple datasets, outperforming the state-of-the-art methods by large margins. Moreover, we contribute with two newly collected benchmark datasets, i.e., small90 and small112, for visually small object tracking. The datasets will be available in https://***/bczhangbczhang/. Copyright © 2019, The Authors. All rights reserved.

关键词： Large dataset

Enhancing network embedding with auxiliary information: An explicit matrix factorization perspective

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Guo, Junliang Xu, Linli Huang, Xunpeng Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China

Recent advances in the field of network embedding have shown the low-dimensional network representation is playing a critical role in network analysis. However, most of the existing principles of network embedding do not incorporate auxiliary information such as content and labels of nodes exibly. In this paper, we take a matrix factorization perspective of network embedding, and incorporate structure, content and label information of the network simultaneously. For structure, we validate that the matrix we construct preserves high-order proximities of the network. Label information can be further integrated into the matrix via the process of random walk sampling to enhance the quality of embedding in an unsupervised manner, i.e., without leveraging downstream classifiers. In addition, we generalize the Skip-Gram Negative Sampling model to integrate the content of the network in a matrix factorization framework. As a consequence, network embedding can be learned in a unified framework integrating network structure and node content as well as label information simultaneously. We demonstrate the efficacy of the proposed model with the tasks of semi-supervised node classification and link prediction on a variety of real-world benchmark network datasets. Copyright © 2017, The Authors. All rights reserved.

关键词： Network embeddings

A Framework for Passengers Demand Prediction and Recommendation

学校读者我要写书评

暂无评论

A Framework for Passengers Demand Prediction and Recommendat...

IEEE International Conference on Services Computing (SCC)

作者： Kai Zhang Zhiyong Feng Shizhan Chen Keman Huang Guiling Wang Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China School of Computer Science and Technologv Tianjin University Tianjin China School of Computer Software Tianjin University Tianjin China Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data Beijing China

With the rapid development of mobile internet and wireless network technologies, more and more people use the mobile app to call a taxicab to pick them up. Therefore, understanding the passengers' travel demand becomes crucial to improve the utilization of the taxicabs and reduce their cost. In this paper, based on spatio-temporal clustering, we propose a demand hotspots prediction framework to generate recommendation for taxi drivers. Specially, an adaptive prediction approach is presented to demand hotspots and their hotness, and then combing the driver's location and the hotness, top candidates are recommended and visually presented to drivers. Based on the dataset provided by CAR INC., the experiment shows that our approach gains a significant improvement in hotspots prediction and recommendation, with 15.21% improvement on average f-measure for prediction and 79.6% hit ratio for recommendation.

关键词： Public transportation Trajectory Vehicles Global Positioning System Mobile communication Clustering algorithms Filtering algorithms