检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Li, Zekang Niu, Cheng Meng, Fandong Feng, Yang Li, Qian Zhou, Jie Dian Group School of Electronic Information and Communications Huazhong University of Science and Technology Pattern Recognition Center WeChat AI Tencent Inc China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Engineering Northeastern University China

Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document. Obviously, document knowledge plays a critical role in Document Grounded Conversations, while existing dialogue models do not exploit this kind of knowledge effectively enough. In this paper, we propose a novel Transformerbased architecture for multi-turn document grounded conversations. In particular, we devise an Incremental Transformer to encode multi-turn utterances along with knowledge in related documents. Motivated by the human cognitive process, we design a two-pass decoder (Deliberation Decoder) to improve context coherence and knowledge correctness. Our empirical study on a real-world Document Grounded Dataset proves that responses generated by our model significantly outperform competitive baselines on both context coherence and knowledge relevance. Copyright © 2019, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Fcsr-gan: Joint face completion and super-resolution via multi-task learning

arXiv

引用

arXiv 2019年

作者： Cai, Jiancheng Han, Hu Shan, Shiguang Chen, Xilin Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University ofChinese Academy of Sciences Beijing100049 China Institute of Computing Technology CAS Beijing100190 China Peng Cheng Laboratory Shenzhen China University of Chinese Academy of Sciences Beijing100049 China

Combined variations containing low-resolution and occlusion often present in face images in the wild, e.g., under the scenario of video surveillance. While most of the existing face image recovery approaches can handle only one type of variation per model, in this work, we propose a deep generative adversarial network (FCSR-GAN) for performing joint face completion and face super-resolution via multi-task learning. The generator of FCSR-GAN aims to recover a high-resolution face image without occlusion given an input low-resolution face image with occlusion. The discriminator of FCSR-GAN uses a set of carefully designed losses (an adversarial loss, a perceptual loss, a pixel loss, a smooth loss, a style loss, and a face prior loss) to assure the high quality of the recovered high-resolution face images without occlusion. The whole network of FCSR-GAN can be trained end-to-end using our two-stage training strategy. Experimental results on the public-domain CelebA and Helen databases show that the proposed approach outperforms the state-of-the-art methods in jointly performing face super-resolution (up to 8 ×) and face completion, and shows good generalization ability in cross-database testing. Our FCSR-GAN is also useful for improving face identification performance when there are low-resolution and occlusion in face images. The code of FCSR-GAN is available at: https://***/swordcheng/FCSR-GAN. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Constrained Multi-scale Dense Connections for Accurate Biomedical Image Segmentation

Constrained Multi-scale Dense Connections for Accurate Biome...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jiawei Zhang Yanchun Zhang Shanfeng Zhu Xiaowei Xu Shanghai key Laboratory of Data Science School of Computer Science Fudan University Shanghai China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China College of Engineering and Science Victoria University Melbourne Australia ISTBI and Shanghai Institute of Artificial Intelligence Algorithms Fudan University Shanghai China Nanjing University Institute of Artificial Intelligence Biomedicine Nanjing China Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China Guangdong Provincial People’s Hospital Guangdong Cardiovascular Institute Guangzhou China

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

Biomedical image segmentation plays a critical role in clinical diagnosis and medical intervention. Recently, a variety of deep neural networks have boosted the biomedical image segmentation performance with a large margin, which adopts dense connections to explore rich representations in multiple scales. In multi-scale dense connections, features from all or most scales are fused or iteratively aggregated. In this paper, we propose constrained multi-scale dense connections (CMDC) for accurate biomedical image segmentation, which only fuse features from the nearest scales containing the most relevant appearance or semantic information. Based on CMDC, we further construct constraint multi-scale dense networks (CMD-Net) by applying CMDC to existing segmentation networks. Experiments across various architectures (including FCN-8s, U-Net, and DeeplabV3) and datasets (including GlaS, CRAG, KID, and ECS) demonstrate that CMD-Net not only outperforms existing schemes on both accuracy and efficiency but also can be easily generalized to a variety of segmentation networks. In addition, CMD-Net achieves state-of-the-art performance on two instance segmentation datasets, GlaS and CRAG.

关键词： Decoding Image segmentation Image resolution Biomedical imaging Glands Fuses Cancer

来源：评论

学校读者我要写书评

暂无评论

Tongue image segmentation via color decomposition and thresholding

Tongue image segmentation via color decomposition and thresh...

引用

作者： Li, Zuoyong Yu, Zhaochai Liu, Weixia Xu, Yong Zhang, Daoqiang Cheng, Yong Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China The Fujian College's Research Base of Humanities and Social Science for Internet Innovation Research Center Minjiang University Fuzhou350121 China Straits Institute Minjiang University Fuzhou350121 China Bio-Computing Research Center Shenzhen Graduate School Harbin Institute of Technology Shenzhen518055 China Department of Computer Science and Engineering Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Communication Engineering Nanjing Institute of Technology Nanjing211167 China

Tongue image segmentation is a crucial step in developing an automatic tongue diagnosis system. After exploring characteristics of image thresholding in different color spaces, we propose a simple and effective tongue image segmentation method. Specifically, the proposed method first extracts an initial tongue body region by performing image thresholding on the transformed hue component in HSI (Hue, Saturation, and Intensity) color space. Then, one of two image thresholding results on the red component of an original tongue image is adaptively selected to find the gap region between the tongue body root and the upper lip. Finally, the initial tongue body region is refined by removing fake object regions such as the upper lip to obtain final tongue image segmentation result. Experimental results on a tongue image dataset containing 200 subjects demonstrate the effectiveness of the proposed method. © 2018 John Wiley & Sons, Ltd.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Adaptive Fusion Network for High Performance RGBT Tracking

Deep Adaptive Fusion Network for High Performance RGBT Track...

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Yuan Gao Chenglong Li Yabin Zhu Jin Tang Tao He Futian Wang Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Institute of Physical Science and Information Technology Anhui University Hefei China Key Laboratory of Industrial Image Processing and Analysis of Anhui Province Hefei China Anhui COWAROBOT CO. Ltd Wuhu China

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Due to the complementarity of RGB and thermal data, RGBT tracking has received more and more attention in recent years because it can effectively solve the degradation of tracking performance in dark environments and bad weather conditions. How to effectively fuse the information from RGB and thermal modality is the key to give full play to their complementarities for effective RGBT tracking. In this paper, we propose a high performance RGBT tracking framework based on a novel deep adaptive fusion network, named DAFNet. Our DAFNet consists of a recursive fusion chain that could adaptively integrate all layer features in an end-to-end manner. Due to simple yet effective operations in DAFNet, our tracker is able to reach the near-real-time speed. Comparing with the state-of-the-art trackers on two public datasets, our DAFNet tracker achieves the outstanding performance and yields a new state-of-the-art in RGBT tracking.

关键词： Feature extraction Target tracking Robustness Fuses Convolution Adaptive systems

来源：评论

学校读者我要写书评

暂无评论

An automatic biomedical ontology meta-matching technique

Journal of Network Intelligence

引用

Journal of Network Intelligence 2019年第3期4卷 109-113页

作者： Xue, Xingsi Yang, Haiyan Zhang, Jie Zhang, Jing Chen, Dongxu College of Information Science and Engineering Intelligent Information Processing Research Center Fujian Key Lab for Automotive Electronics and Electric Drive Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology No.3 Xueyuan Road University Town Minhou Fuzhou CityFujian Province350118 China College of Information Science and Engineering Fujian University of Technology No.33 Xuefu South Road University Town Minhou Fuzhou CityFujian Province350118 China School of Computer Science and Engineering Yulin Normal University No.299 Education Middle Road Yulin CityGuanxi Province537000 China School of Computing Ulster University Jordanstown BT370QB United Kingdom Fujian Medical University Union Hospital No.29 Xinquan Road Gulou Fuzhou CityFujian Province350001 China

Biomedical ontology matching aims at determining the heterogeneous biomed-ical concepts, and bridging the semantic gap between heterogeneous biomedical ontologies. The foundation of a biomedical ontology matching technique is the Biomedical Concept Similarity Measure (BCSM), which calculates the similarity value between two biomed-ical concepts. Since various BCSMs have different advantages, usually several BCSMs are aggregated together to improve the result’s confidence. How to tune the aggregating weights to ensure the quality of the alignment is called biomedical ontology meta-matching problem, which is a challenge in the ontology matching domain. Currently, researchers mainly focus on how to tune the aggregating weights for various similarity measures to improve the quality of the ontology alignments. However, the ignorance of the effects brought about by different biomedical concept mapping’s preference on different similarity measures significantly reduces the alignment’s quality. To overcome this drawback, in this work, we formally define the biomedical ontology meta-matching problem, and then present an Ordered Weighted Average (OWA) based approach to automatically aggregate various biomedical concept similarity measures. In our method, the aggregating weights determined for each concept mapping is associated with the ordered position of the similarity value instead of a particular concept similarity measure. The experiment utilizes the large biomed track provided by Ontology Alignment Evaluation Initiative (OAEI) to test our proposal’s performance, and the experimental results show the effectiveness of our proposal. © 2019, Taiwan Ubiquitous information. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

iSplit LBI: Individualized partial ranking with ties via split LBI

arXiv

引用

arXiv 2019年

作者： Xu, Qianqian Sun, Xinwei Yang, Zhiyong Cao, Xiaochun Huang, Qingming Yao, Yuan Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS Microsoft Research Asia State Key Laboratory of Information Security Institute of Information Engineering CAS School of Cyber Security University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences Key Laboratory of Big Data Mining and Knowledge Management CAS Peng Cheng Laboratory Department of Mathematics Hong Kong University of Science and Technology Hong Kong

Due to the inherent uncertainty of data, the problem of predicting partial ranking from pairwise comparison data with ties has attracted increasing interest in recent years. However, in real-world scenarios, different individuals often hold distinct preferences. It might be misleading to merely look at a global partial ranking while ignoring personal diversity. In this paper, instead of learning a global ranking which is agreed with the consensus, we pursue the tie-aware partial ranking from an individualized perspective. Particularly, we formulate a unified framework which not only can be used for individualized partial ranking prediction, but also be helpful for abnormal user selection. This is realized by a variable splitting-based algorithm called iSplitLBI. Specifically, our algorithm generates a sequence of estimations with a regularization path, where both the hyperparameters and model parameters are updated. At each step of the path, the parameters can be decomposed into three orthogonal parts, namely, abnormal signals, personalized signals and random noise. The abnormal signals can serve the purpose of abnormal user selection, while the abnormal signals and personalized signals together are mainly responsible for individual partial ranking prediction. Extensive experiments on simulated and real-world datasets demonstrate that our new approach significantly outperforms state-of-the-art alternatives. The code is now availiable at https://***/qianqianxu010/ NeurIPS2019-iSplitLBI. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Network Parameter Generation for One-Shot Object Detection

Network Parameter Generation for One-Shot Object Detection

引用

IEEE International Conference on Unmanned Systems (ICUS)

作者： Kang Wang Jiajia Zhao Yang Wang Shuigeng Zhou Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-Mechanical Engineer Institute Beijing China School of Information Engineering Nanchang University China

ISBN: (纸本)9781728137933

Recent object detection models have achieved satisfactory performance by deep learning with large-scale annotated datasets. However, these models often perform poorly when the training examples are not sufficient enough, especially for one-shot object detection where there is only one training example of each target class. In this paper, we propose a network parameter generation framework for effective one-shot object detection. By leveraging the semantic relationship between the source-domain and the target-domain (new classes), our framework can generate network parameters for the new classes directly. Furthermore, we develop two implementation schemes for this framework: weighting-based parameter generation and regression-based parameter generation. These two schemes use different information to construct the relationship and transfer knowledge from the source-domain to the target-domain. Experiments on the PASCAL-OSCD benchmark show that our methods can significantly boost the performance of one-shot object detection.

关键词： Object detection Detectors Head Training Feature extraction Task analysis Training data

来源：评论

学校读者我要写书评

暂无评论

Relative influence maximization in competitive social networks

引用

Science China(information Sciences) 2017年第10期60卷 252-254页

作者： Dingda YANG Xiangwen LIAO Huawei SHEN Xueqi CHENG Guolong CHEN College of Physics and Information Engineering Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing College of Mathematics and Computer Science Fuzhou University Institute of Computing Technology Chinese Academy of Sciences

In many realistic scenarios,such as political election and viral marketing,two opposite opinions,i.e.,positive opinion and negative opinion,spread simultaneously in the same social networks[1,2].Consequently,to achiev... 详细信息

关键词： net RIM Relative influence maximization in competitive social networks Figure

来源：评论

学校读者我要写书评

暂无评论

Attributed rhetorical structure grammar for domain text summarization

arXiv

引用

arXiv 2019年

作者： Lu, Ruqian Hou, Shengluan Wang, Chuanqing Huang, Yu Fei, Chaoqun Zhang, Songmao Key Laboratory of MADIS Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

This paper presents a new approach of automatic text summarization which combines domain oriented text analysis (DoTA) and rhetorical structure theory (RST) in a grammar form: the attributed rhetorical structure grammar (ARSG), where the non-terminal symbols are domain keywords, called domain relations, while the rhetorical relations serve as attributes. We developed machine learning algorithms for learning such a grammar from a corpus of sample domain texts, as well as parsing algorithms for the learned grammar, together with adjustable text summarization algorithms for generating domain specific summaries. Our practical experiments have shown that with support of domain knowledge the drawback of missing very large training data set can be effectively compensated. We have also shown that the knowledge based approach may be made more powerful by introducing grammar parsing and RST as inference engine. For checking the feasibility of model transfer, we introduced a technique for mapping a grammar from one domain to others with acceptable cost. We have also made a comprehensive comparison of our approach with some others. Copyright © 2019, The Authors. All rights reserved.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：