检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Zhang, Kai Danelljan, Martin Li, Yawei Timofte, Radu Liu, Jie Tang, Jie Wu, Gangshan Zhu, Yu He, Xiangyu Xu, Wenjie Li, Chenghua Leng, Cong Cheng, Jian Wu, Guangyang Wang, Wenyi Liu, Xiaohong Zhao, Hengyuan Kong, Xiangtao He, Jingwen Qiao, Yu Dong, Chao Luo, Xiaotong Chen, Liang Zhang, Jiangtao Suin, Maitreya Purohit, Kuldeep Rajagopalan, A.N. Li, Xiaochuan Lang, Zhiqiang Nie, Jiangtao Wei, Wei Zhang, Lei Muqeet, Abdul Hwang, Jiwon Yang, Subin Kang, JungHeum Bae, Sungho Kim, Yongwoo Chen, Liang Zhang, Jiangtao Luo, Xiaotong Qu, Yanyun Jeon, Geun-Woo Choi, Jun-Ho Kim, Jun-Hyuk Lee, Jong-Seok Marty, Steven Marty, Eric Xiong, Dongliang Chen, Siang Zha, Lin Jiang, Jiande Gao, Xinbo Lu, Wen Wang, Haicheng Bhaskara, Vineeth Levinshtein, Alex Tsogkas, Stavros Jepson, Allan Kong, Xiangzhen Zhao, Tongtong Zhao, Shanshan Hrishikesh, P.S. Puthussery, Densen Jiji, C.V. Nan, Nan Liu, Shuai Cai, Jie Meng, Zibo Ding, Jiaming Ho, Chiu Man Wang, Xuehui Yan, Qiong Zhao, Yuzhi Chen, Long Zhang, Jiangtao Luo, Xiaotong Chen, Liang Qu, Yanyun Sun, Long Wang, Wenhao Liu, Zhenbing Lan, Rushi Umer, Rao Muhammad Micheloni, Christian Computer Vision Lab ETH Zurich Switzerland State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China MAICRO China University of Electronic Science and Technology of China China McMaster University Canada Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Xiamen University China Indian Institute of Technology Madras India Nanjing University of Aeronautics and Astronautics Nanjing China School of Computer Science Northwestern Polytechnical University China Kyung Hee University Korea Republic of Sang Myung University Korea Republic of Xianmen University China Yonsei University Korea Republic of ETH Zurich Switzerland Zhejiang University China Qingdao Hi-image Technologies Co. Ltd [Hisense Visual Technology Co.Ltd. China Xidian University China Samsung AI Centre Toronto Canada Dalian Maritime University China China Everbright Bank Co. Ltd China College of Engineering Trivandrum India InnoPeak Technology Inc. United States SenseTime Research Hong Kong Sun Yat-sen University China City University of Hong Kong Hong Kong Guilin University of Electronic Technology Guilin541004 China University of Udine Italy

This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor ×4 based on a set of prior examples of low and corresponding high resolution images. The goal is to devise a network that reduces one or several aspects such as runtime, parameter count, FLOPs, activations, and memory consumption while at least maintaining PSNR of MSRResNet. The track had 150 registered participants, and 25 teams submitted the final results. They gauge the state-of-the-art in efficient single image super-resolution. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Occluded Pedestrian Detection Through Guided Attention in CNNs 31

Occluded Pedestrian Detection Through Guided Attention in CN...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition

作者： Shanshan Zhang Jian Yang Bernt Schiele Ministry of Education Key Lab of Intelligent Perception and Systems for High-Dimensional Information Jiangsu Key Lab of Image and Video Understanding for Social Security Nanjing University of Science and Technology China Saarland Informatics Campus Max Planck Institute for Informatics Germany

ISBN: (纸本)9781538664216;9781538664209

Pedestrian detection has progressed significantly in the last years. However, occluded people are notoriously hard to detect, as their appearance varies substantially depending on a wide range of occlusion patterns. In this paper, we aim to propose a simple and compact method based on the FasterRCNN architecture for occluded pedestrian detection. We start with interpreting CNN channel features of a pedestrian detector, and we find that different channels activate responses for different body parts respectively. These findings motivate us to employ an attention mechanism across channels to represent various occlusion patterns in one single model, as each occlusion pattern can be formulated as some specific combination of body parts. Therefore, an attention network with self or external guidances is proposed as an add-on to the baseline FasterRCNN detector. When evaluating on the heavy occlusion subset, we achieve a significant improvement of 8pp to the baseline FasterRCNN detector on CityPersons and on Caltech we outperform the state-of-the-art method by 4pp.

关键词： Detectors Feature extraction Computer architecture Object detection Training Body regions Correlation

来源：评论

学校读者我要写书评

暂无评论

A General End-to-end Diagnosis Framework for Manufacturing Systems

arXiv

引用

arXiv 2018年

作者： Yuan, Ye Ma, Guijun Cheng, Cheng Zhou, Beitong Zhao, Huan Zhang, Hai-Tao Ding, Han State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation MOE Key Lab of Intelligent Control and Image Processing Huazhong University of Science and Technology Wuhan430074 China School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

The manufacturing sector is envisioned to be heavily influenced by artificial intelligence-based technologies with the extraordinary increases in computational power and data volumes1,2. A central challenge in manufacturing sector lies in the requirement of a general framework to ensure satisfied diagnosis and monitoring performances in different manufacturing applications. Here we propose a general data-driven, end-to-end framework for the monitoring of manufacturing systems. This framework, derived from deep learning techniques, evaluates fused sensory measurements to detect and even predict faults and wearing conditions. This work exploits the predictive power of deep learning to automatically extract hidden degradation features from noisy, time-course data. We have experimented the proposed framework on ten representative datasets drawn from a wide variety of manufacturing applications. Results reveal that the framework performs well in examined benchmark applications and can be applied in diverse contexts, indicating its potential use as a critical corner stone in smart manufacturing. Copyright © 2018, The Authors. All rights reserved.

关键词： Manufacture

来源：评论

学校读者我要写书评

暂无评论

Coupled convolutional neural network with adaptive response function learning for unsupervised hyperspectral super-resolution

arXiv

引用

arXiv 2020年

作者： Zheng, Ke Gao, Lianru Liao, Wenzhi Hong, Danfeng Zhang, Bing Cui, Ximin Chanussot, Jocelyn Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China College of Geoscience and Surveying Engineering China University of Mining and Technology [Bei Jing Beijing100083 China Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Mol2400 Belgium Image Processing and Interpretation IMEC Research Group Ghent University Ghent9000 Belgium Weling82234 Germany College of Resources and Environment University of Chinese Academy of Sciences Beijing100049 China College of Geoscience and Surveying Engineering China University of Mining and Technology [Bei Jing Beijing100083 China Univ. Grenoble Alpes CNRS Grenoble INP GIPSA-lab GrenobleF-38000 France Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China

Due to the limitations of hyperspectral imaging systems, hyperspectral imagery (HSI) often suffers from poor spatial resolution, thus hampering many applications of the imagery. Hyperspectral super-resolution refers to fusing HSI and MSI to generate an image with both high spatial and high spectral resolutions. Recently, several new methods have been proposed to solve this fusion problem, and most of these methods assume that the prior information of the Point Spread Function (PSF) and Spectral Response Function (SRF) are known. However, in practice, this information is often limited or unavailable. In this work, an unsupervised deep learning based fusion method HyCoNet that can solve the problems in HSIMSI fusion without the prior PSF and SRF information is proposed. HyCoNet consists of three coupled autoencoder nets in which the HSI and MSI are unmixed into endmembers and abundances based on the linear unmixing model. Two special convolutional layers are designed to act as a bridge that coordinates with the three autoencoder nets, and the PSF and SRF parameters are learned adaptively in the two convolution layers during the training process. Furthermore, driven by the joint loss function, the proposed method is straightforward and easily implemented in an end-to-end training manner. The experiments performed in the study demonstrate that the proposed method performs well and produces robust results for different datasets and arbitrary PSFs and SRFs. Copyright © 2020, The Authors. All rights reserved.

关键词： Spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Gaussian-induced convolution for graphs

arXiv

引用

arXiv 2018年

作者： Jiang, Jiatao Cui, Zhen Xu, Chunyan Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

Learning representation on graph plays a crucial role in numerous tasks of pattern recognition. Different from grid-shaped images/videos, on which local convolution kernels can be lattices, however, graphs are fully coordinate-free on vertices and edges. In this work, we propose a Gaussian-induced convolution (GIC) framework to conduct local convolution filtering on irregular graphs. Specifically, an edge-induced Gaussian mixture model is designed to encode variations of subgraph region by integrating edge information into weighted Gaussian models, each of which implicitly characterizes one component of subgraph variations. In order to coarsen a graph, we derive a vertex-induced Gaussian mixture model to cluster vertices dynamically according to the connection of edges, which is approximately equivalent to the weighted graph cut. We conduct our multi-layer graph convolution network on several public datasets of graph classification. The extensive experiments demonstrate that our GIC is effective and can achieve the state-of-the-art results. Copyright © 2018, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

DSFD: Dual shot face detector

arXiv

引用

arXiv 2018年

作者： Li, Jian Wang, Yabiao Wang, Changan Tai, Ying Qian, Jianjun Yang, Jian Wang, Chengjie Li, Jilin Huang, Feiyue PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Youtu Lab Tencent

In this paper, we propose a novel face detection network with three novel contributions that address three key aspects of face detection, including better feature learning, progressive loss design and anchor assign based data augmentation, respectively. First, we propose a Feature Enhance Module (FEM) for enhancing the original feature maps to extend the single shot detector to dual shot detector. Second, we adopt Progressive Anchor Loss (PAL) computed by two different sets of anchors to effectively facilitate the features. Third, we use an Improved Anchor Matching (IAM) by integrating novel anchor assign strategy into data augmentation to provide better initialization for the regressor. Since these techniques are all related to the two-stream design, we name the proposed network as Dual Shot Face Detector (DSFD). Extensive experiments on popular benchmarks, WIDER FACE and FDDB, demonstrate the superiority of DSFD over the state-of-the-art face detectors. Copyright © 2018, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Person search via a mask-guided two-stream CNN model

arXiv

引用

arXiv 2018年

作者： Chen, Di Zhang, Shanshan Ouyang, Wanli Yang, Jian Tai, Ying PCA Lab Key Lab of Intelligent Perception Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image School of Computer Science and Engineering Nanjing University of Science and Technology University of Sydney Sensetime Intelligent Multimedia Laboratory Group Youtu Lab Tencent

In this work, we tackle the problem of person search, which is a challenging task consisted of pedestrian detection and person re-identification (re-ID). Instead of sharing representations in a single joint model, we find that separating detector and re-ID feature extraction yields better performance. In order to extract more representative features for each identity, we propose a simple yet effective re-ID method, which models foreground person and original image patches individually, and obtains enriched representations from two separate CNN streams. On the standard person search benchmark datasets, we achieve mAP of 83:0% and 32:6% respectively for CUHK-SYSU and PRW, surpassing the state of the art by a large margin (more than 5pp). Copyright © 2018, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DEEP MATCH TRACKER: CLASSIFYING WHEN DISSIMILAR, SIMILARITY MATCHING WHEN NOT

DEEP MATCH TRACKER: CLASSIFYING WHEN DISSIMILAR, SIMILARITY ...

引用

IEEE International Conference on image Processing

作者： T.Kokul C.Fookes S.Sridharan A.Ramanan UO_2.J.Pinidiyaarachchi PGIS Image and Video Lab Queensland University of Technology Australia Dept. of Computer Science University of Jaffna Sri Lanka Dept. of Statistics and Computer Science University of Peradeniya Sri Lanka

Visual tracking frameworks employing Convolutional Neural Networks (CNNs) have shown state-of-the-art performance due to their hierarchical feature representation. While classification and update based deep neural net tracking have shown good performance in terms of accuracy, they have poor tracking speed. On the other hand, recent matching based techniques using CNNs show higher than real-time speed in tracking but this speed is achieved at a considerably lower accuracy. To successfully manage the trade-off between accuracy and speed, we propose a novel CNN architecture for visual tracking. We achieve this trade-off balance by using an approach in which consecutive similar frames are processed with a similarity matching technique, and dissimilar frames are processed with a classification approach within the CNN architecture. The tracking speed is improved by avoiding unnecessary model updates through the measurement of similarity between adjacent frames, while the accuracy is maintained by adopting a classification approach when needed, with deeper level features. Extensive evaluation performed on a publicly available benchmark dataset demonstrates our proposed tracker shows competitive performance while maintaining near real-time speed.

关键词： Target tracking Feature extraction Training Task analysis Visualization Real-time systems Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Tangram Algorithm:High image Quality Secret Sharing Scheme Using Two Steganographic images

Tangram Algorithm:High Image Quality Secret Sharing Scheme U...

引用

2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)

作者： Wanli Lyu Jiahao Deng Yu Zhang Dongshuo Yin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityKey Lab of Industrial Image Processing and Analysis of Anhui Province

ISBN: (纸本)9781510871076

In this paper,our proposed scheme using two steganography *** other data hiding schemes,this scheme studies the characteristics of the Tangram puzzle model and the secret message bytes that make up the eight binary bits that are hidden into the two *** matrix M *,horizontal and vertical coordinate range from 0 to 255,and the pixel pairs in the cover image are used to help hide the secret message bytes in our *** paired pixel points into single and double number hidden in two *** show that the program can hide relatively more pixels in a cover image with less losing image quality.

关键词： steganography images Tangram puzzle matrix M hide relatively scenario

来源：评论

学校读者我要写书评

暂无评论

A Reliable Data Hiding Scheme Using Jigsaw Sudoku

A Reliable Data Hiding Scheme Using Jigsaw Sudoku

引用

2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)

作者： Wanli Lyu Dongshuo Yin Yu Zhang Jiahao Deng Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityKey Lab of Industrial Image Processing and Analysis of Anhui Province

ISBN: (纸本)9781510871076

A distinctive data hiding method based on Jigsaw Sudoku is proposed in this *** from other methods,the proposed method is based on Jigsaw Sudoku which is a kind of irregularly shaped *** to the novelty of Jigsaw Sudoku,the proposed method can provide a safer scheme for data hiding than that with pure *** proposed method can hide a certain number of 9-ary numbers in a steganographic image which has a corresponding *** a 256*256 key matrix stretched from a size 9*9 Jigsaw Sudoku,secret message can be hidden in a vector image byte by byte in the form of *** results show that,the proposed method has a better peaksignal-to-noise-ratio(PSNR) compared with some other data hiding methods.

关键词： Sudoku PSNR hiding methods irregularly shaped steganographic image corresponding specification

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：