检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Alhaija, Hassan Abu Mustikovela, Siva Karthik Mescheder, Lars Geiger, Andreas Rother, Carsten Computer Vision Lab TU Dresden Autonomous Vision Group MPI for Intelligent Systems Tübingen Computer Vision and Geometry Group ETH Zürich

The success of deep learning in computer vision is based on the availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity. Unfortunately, creating realistic 3D content is challenging on its own and requires significant human effort. In this work, we propose an alternative paradigm which combines real and synthetic data for learning semantic instance segmentation and object detection models. Exploiting the fact that not all aspects of the scene are equally important for this task, we propose to augment real-world imagery with virtual objects of the target category. Capturing real-world images at large scale is easy and cheap, and directly provides real background appearances without the need for creating complex 3D models of the environment. We present an efficient procedure to augment these images with virtual objects. This allows us to create realistic composite images which exhibit both realistic background appearance as well as a large number of complex object arrangements. In contrast to modeling complete 3D environments, our data augmentation approach requires only a few user interactions in combination with 3D shapes of the target object category. Through an extensive set of experiments, we conclude the right set of parameters to produce augmented data which can maximally enhance the performance of instance segmentation models. Further, we demonstrate the utility of proposed approach on training standard deep models for semantic instance segmentation and object detection of cars in outdoor driving scenarios. We test the models trained on our augmented data on the KITTI 2015 dataset, which we have annotated with pixel-accurate ground truth, and on the Cityscapes dataset. Our experiments demonstrate that models trained on augmented imagery generalize better than those trained on synthetic data or models trained on limited amounts of annotated real data. Copyright © 2017, The

关键词：

来源：评论

学校读者我要写书评

暂无评论

Publisher Correction: Global estimates on the number of people blind or visually impaired by cataract: a meta-analysis from 2000 to 2020

引用

Eye (London, England) 2024年第11期38卷 2229-2231页

作者： Konrad Pesudovs Hugh R. Taylor Tabassom Sedighi Rupert R. A. Bourne Shahina Pardhan Van Charles Lansingh John H. Kempen Ian Tapply Arthur G. Fernandes Maria Vittoria Cicinelli Alessandro Arrigo Nicolas Leveziel Serge Resnikoff Seth Flaxman Mukkharram M. Bikbov Tasanee Braithwaite Alain Bron Ching-Yu Cheng Monte A. Del Monte Joshua R. Ehrlich Leon B. Ellwein David Friedman João M. Furtado Gus Gazzard Ronnie George M. Elizabeth Hartnett Jost B. Jonas Rim Kahloun Moncef Khairallah Rohit C. Khanna Janet Leasher Julie-Anne Little Vinay Nangia Michal Nowak Tunde Peto Pradeep Ramulu Fotis Topouzis Mitiadis Tsilimbaris Ya Xing Wang Ningli Wang Paul Svitil Briant Theo Vos Katrin Burkart Kaleb Coberly Xiaochen Dai Stephen S. Lim Tomislav Mestrovic Ali H. Mokdad Christopher J. L. Murray Jaimie D. Steinmetz Awoke Misganaw Yohannes Habtegiorgis Abate Mohammad Abdollahi Mozhan Abdollahi Ayele Mamo Abebe Olumide Abiodun Richard Gyan Aboagye Woldu Aberhe Abrha Hasan Abualruz Hiwa Abubaker Ali Eman Abu-Gharbieh Salahdein Aburuz Tadele Girum Girum Adal Mesafint Molla Adane Isaac Yeboah Addo Qorinah Estiningtyas Sakilah Adnani Muhammad Sohail Afzal Muhammad Umair Shahin Aghamiri Bright Opoku Ahinkorah Aqeel Ahmad Sajjad Ahmad Ali Ahmadi Siamak Sabour Ayman Ahmed Haroon Ahmed Ahmad Samir Alfaar Abid Ali Syed Shujait Shujait Ali Awais Altaf Hubert Amu Emmanuel Manu Sofia Androudi Rodrigo Anguita Abhishek Anil Rimple Jeet Kaur Muhammad Aaqib Shamim Saeid Anvari Anayochukwu Edward Anyasodor Francis Appiah Jalal Arabloo Haleh Ayatollahi Mosab Arafat Damelash Areda Reza Arefnezhad Brhane Berhe Aregawi Akeza Awealom Asgedom Tahira Ashraf Seyyed Shamsadin Athari Bantalem Tilaye Tilaye Atinafu Birhan Tsegaw Taye Maha Moh’d Wahbi Atout Alok Atreya Ahmed Y. Azzam Hassan Babamohamadi Sara Bagherieh Yogesh Bahurupi Atif Amin Baig Shumaila Nargus Biswajit Banik Mainak Bardhan Saurav Basu Kavita Batra Nebiyou Simegnew Bayileyegn Fatemeh Bazvand Addisu Shunu Beyene Awoke Masrie Asrat Derese Devidas S. Bhagat Akshaya Srikanth Bhagavathula Pankaj Bh Medicine & Health University of New South Wales Sydney NSW Australia School of Optometry and Vision Science University of New South Wales Sydney NSW Australia School of Population and Global Health University of Melbourne Carlton VIC Australia Vision and Eye Research Institute Anglia Ruskin University Cambridge UK HelpMeSee Instituto Mexicano de Oftalmologia Santiago de Querétaro Mexico University of Miami Gables FL USA University of Utah Salt Lake City UT USA Chief Medical Office HelpMeSee New York NY USA Mexican Institute of Ophthalmology Queretaro Mexico Department of Ophthalmology Massachusetts Eye and Ear/Shepens Eye Research Institute/Harvard Medical School Boston MA USA Eye Unit MyungSung Christian Medical Center (MCM) Comprehensive Specialized Hospital and MyungSun Medical College Addis Ababa Ethiopia Department of Ophthalmology Addis Ababa University Addis Ababa Ethiopia Sight for Souls Bellevue WA USA Department of Ophthalmology Harvard University Boston MA USA Eye Unit MyungSung Medical College Addis Ababa Ethiopia Addenbrooke’s Hospital Cambridge UK Department of Ophthalmology Cambridge University Hospitals Cambridge UK Federal University of Sao Paolo Sao Paolo SP Brazil University of Calgary Calgary AB Canada Department of Ophthalmology and Visual Sciences Federal University of São Paulo Sao Paulo Brazil School of Medicine Vita-Salute San Raffaele University Milan Italy Department of Ophthalmology IRCCS San Raffaele Scientific Institute Milan Italy Department of Ophthalmology San Raffaele Scientific Institute Milano Italy IRCCS San Raffaele Scientific Institute Vita-Salute University Milan Italy Scientific Institute San Raffaele Hospital Vita-Salute University Milan Italy University of Poitiers Poitiers France CHU de Poitiers Poitiers France Ophthalmology Department CHU de Poitiers (Poitiers University Hospital) Poitiers France Unité 1084 National Institute of Health and Medical Research (INSERM) Poitiers France

来源：评论

学校读者我要写书评

暂无评论

Smart Cloud System for Forensic Thermal Image Enhancement Using Local and Global Logarithmic Transform Histogram Matching

Smart Cloud System for Forensic Thermal Image Enhancement Us...

引用

IEEE International Conference on Smart Cloud (SmartCloud)

作者： Viacheslav Voronin Evgenii Semenishchev Vladimir Frants Sos Agaian Lab. “Mathematical methods of image processing and intelligent computer vision systems” Don State Technical University Rostov-on-Don Russian Federation “STANKIN” Moscow State University of Technology Moscow Russian Federation Dept. of Computer Science CUNY/The College of Staten Island Staten Island New York United States

Digital images used in the investigation of a crime often undergo several concurrent enhancement operations for improved automated analysis. The challenges are related to the big size of data and complexity of the forensic image processing. Our purpose is providing a smart cloud system to image processing for PC and Smartphones with limited computation complexity. This paper presents a new thermal image enhancement algorithm based on combined local and global image processing in the frequency domain. The presented approach uses the fact that the relationship between stimulus and perception is logarithmic. The basic idea is to apply logarithmic transform histogram matching with spatial equalization approach on different image blocks. The resulting image is a weighted mean of all processing blocks. The weights for every local and global enhanced image driven through optimization of measure of enhancement (EME). Some presented experimental results illustrate the performance of the proposed cloud system on real thermal images in comparison with the traditional methods.

关键词： Histograms Transforms Image enhancement Forensics Adaptive equalizers Clouds

来源：评论

学校读者我要写书评

暂无评论

Chinese poetry generation with a working memory model

arXiv

引用

arXiv 2018年

作者： Yi, Xiaoyuan Sun, Maosong Li, Ruoyu Yang, Zonghan State Key Lab on Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China 6ESTATES PTE LTD Singapore

As an exquisite and concise literary form, poetry is a gem of human culture. Automatic poetry generation is an essential step towards computer creativity. In recent years, several neural models have been designed for this task. However, among lines of a whole poem, the coherence in meaning and topics still remains a big challenge. In this paper, inspired by the theoretical concept in cognitive psychology, we propose a novel Working Memory model for poetry generation. Different from previous methods, our model explicitly maintains topics and informative limited history in a neural memory. During the generation process, our model reads the most relevant parts from memory slots to generate the current line. After each line is generated, it writes the most salient parts of the previous line into memory slots. By dynamic manipulation of the memory, our model keeps a coherent information flow and learns to express each topic flexibly and naturally. We experiment on three different genres of Chinese poetry: quatrain, iambic and chinoiserie lyric. Both automatic and human evaluation results show that our model outperforms current state-of-the-art methods. Copyright © 2018, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ChaLearn looking at people: IsoGD and ConGD large-scale RGB-D gesture recognition

arXiv

引用

arXiv 2019年

作者： Wan, Jun Lin, Chi Wen, Longyin Li, Yunan Miao, Qiguang Escalera, Sergio Anbarjafari, Gholamreza Guyon, Isabelle Guo, Guodong Li, Stan Z. National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China JD Finance Mountain ViewCA United States University of Southern California Los AngelesCA90089-0911 United States School of Computer Science and Technology Xidian University & Xi'an Key Laboratory of Big Data and Intelligent Vision 2nd South Taibai Road Xi'an710071 China Universitat de Barcelona Computer Vision Center Spain iCV Lab Institute of Technology University of Tartu Estonia Faculty of Engineering Hasan Kalyoncu University Gaziantep Turkey Institute of Digital Technologies Loughborough University London United Kingdom ChaLearn United States University Paris-Saclay France institute of Deep Learning Baidu Research National Engineering Laboratory for Deep Learning Technology and Application China

The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on computer vision (ICCV) 2017, attracting more than 200 teams around the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. This paper describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. We discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition, and provide a detailed analysis of the current state-of-the-art methods for large-scale isolated and continuous gesture recognition based on RGB-D video sequences. In addition to recognition rate and mean jaccard index (MJI) as evaluation metrics used in our previous challenges, we also introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) baseline method, determining the video division points based on the skeleton points extracted by convolutional pose machine (CPM). Experiments demonstrate that the proposed Bi-LSTM outperforms the state-of-the-art methods with an absolute improvement of 8.1% (from 0.8917 to 0.9639) of CSR. Copyright © 2019, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Fast task-specific target detection via graph based constraints representation and checking

Fast task-specific target detection via graph based constrai...

引用

2017 IEEE International Conference on Robotics and Automation, ICRA 2017

作者： Luan, Wentao Yang, Yezhou Fermuller, Cornelia Baras, John S. Institute for Systems Research University of Maryland College Park United States Computer Vision Lab University of Maryland College Park United States School of Computing Informatics and Decision Systems Engineering Arizona State University United States

ISBN: (纸本)9781509046331

We present a framework for fast target detection in real-world robotics applications. Considering that an intelligent agent attends to a task-specific object target during execution, our goal is to detect the object efficiently. We propose the concept of early recognition, which influences the candidate proposal process to achieve fast and reliable detection performance. To check the target constraints efficiently, we put forward a novel policy which generates a sub-optimal checking order, and we prove that it has bounded time cost compared to the optimal checking sequence, which is not achievable in polynomial time. Experiments on two different scenarios: 1) rigid object and 2) non-rigid body part detection validate our pipeline. To show that our method is widely applicable, we further present a human-robot interaction system based on our non-rigid body part detection. © 2017 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Multi-View Images Fusion Model

引用

IOP Conference Series: Materials Science and Engineering 2019年第1期680卷

作者： M M Zhdanova V V Voronin R A Sizyakin M S Minkin A A Zelensky Lab. 'Mathematical methods of image processing and intelligent computer vision systems' Don State Technical University Gagarin sq. 1 Rostov-on-Don 344000 Russia Moscow State University of Technology 'STANKIN' Vadkovsky line 1 Moscow 127055 Russia

The tasks of recognition actions and classification objects are fundamental in computer vision systems. Even subtasks, such as recognition of atomic motion and single objects form the basis for understanding the situation in the work area and the scene in general. This is especially important in video surveillance systems designed to ensure security. Thus, the effectiveness of recognition and classification methods is one of the primary tasks of computer vision. But the visual methods implemented in similar video surveillance systems, encounter some difficulties, such as inhomogeneous background, uncontrolled operating environments, irregular illumination, etc. To address these drawbacks, the paper presents a model for combining visible range images and depth images. This model allows to improve the quality of recognized images, provides the construction of a more informative descriptor, which also positively affects the recognition efficiency. Our results show that it has good performance in fusion visible image and depth map.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Robust Neural Machine Translation

arXiv

引用

arXiv 2018年

作者： Cheng, Yong Tu, Zhaopeng Meng, Fandong Zhai, Junjie Liu, Yang Tencent AI Lab China State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing Advanced Innovation Center for Language Resources Beijing China

Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation (NMT) models. In this paper, we propose to improve the robustness of NMT models with adversarial stability training. The basic idea is to make both the encoder and decoder in NMT models robust against input perturbations by enabling them to behave similarly for the original input and its perturbed counterpart. Experimental results on Chinese-English, English-German and English-French translation tasks show that our approaches can not only achieve significant improvements over strong NMT systems but also improve the robustness of NMT models. Copyright © 2018, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Blind Visual Quality Assessment for Smart Cloud-Based Video Storage

Blind Visual Quality Assessment for Smart Cloud-Based Video ...

引用

IEEE International Conference on Smart Cloud (SmartCloud)

作者： Vladimir Frants Viacheslav Voronin Alexander Zelenskiy Sos Agaian Metrological lab. “Small GIC” Moscow State University of Technology “STANKIN” Moscow Russian Federation Pro-rector for Research Work and R&D Politics Moscow State University of Technology “STANKIN” Moscow Russian Federation Lab. “Mathematical methods of image processing and intelligent computer vision systems.” Don State Technical University Rostov-on-Don Russian Federation Dept. of Computer Science CUNY The College of Staten Island Staten Island New York United States

In this paper, we present a new video quality metric targeted for use within cloud-based video storage systems. Because of the limited capacity of storage solutions currently in use, it is common for stored videos to have low perceived video quality. Ability to predict the quality of coded video sequence in fully automatic fashion is crucial for optimal coding parameters selection. We have developed general quality estimation approach applicable for different kinds of video content and useful for online correction of perceived quality of stored video sequence. Proposed objective video quality metric is designed to have a high level of correlation with human-based quality assessment results. A high level of conformity of predicted video quality to perceived quality level is achieved by using a convolutional neural network trained on a large volume of video data in the framework of generative adversarial learning and combination of carefully selected regularization techniques. Evaluation of developed VQA metric on commonly used datasets shows equal or better correlation with MOS than the current state of the art approaches.

关键词： Quality assessment Measurement Video recording Video sequences Streaming media Training Visualization

来源：评论

学校读者我要写书评

暂无评论

Architecture-aware design and implementation of CNN algorithms for embedded inference: the ALOHA project

Architecture-aware design and implementation of CNN algorith...

引用

International Conference on Microelectronics, ICM

作者： Paolo Meloni Daniela Loi Gianfranco Deriu Andy D. Pimentel Dolly Saprat Maura Pintort Battista Biggio Oscar Ripolles David Solans Francesco Conti Luca Benini Todor Stefanov Svetlana Minakova Bernhard Moser Natalia Shepeleva Michael Masin Francesca Palumbo Nikos Fragoulis Ilias Theodorakopoulos Department of Electrical and Electronic Engineering University of Cagliari Italy Institute of Informatics University of Amsterdam The Netherlands Pluribus One Italy CA Technologies Spain Integrated Systems Laboratory ETH Zurich Switzerland Institute of Advanced Computer Science Leiden University The Netherlands Software Competence Center Hagenberg Austria IBM Research - Haifa Israel IDEA Lab University of Sassari Italy IRIDA Labs Computer Vision Systems Greece

ISBN: (纸本)9781538681688;9781538681671

The use of Deep Learning (DL) algorithms is increasingly evolving in many application domains. Despite the rapid growing of algorithm size and complexity, performing DL inference at the edge is becoming a clear trend to cope with low latency, privacy and bandwidth constraints. Nevertheless, traditional implementation on low-energy computing nodes often requires experience-based manual intervention and trial-and-error iterations to get to a functional and effective solution. This work presents a computer-aided design (CAD) support for effective implementation of DL algorithms on embedded systems, aiming at automating different design steps and reducing cost. The proposed tool flow comprises capabilities to consider architecture-and hardware-related variables at very early stages of the development process, from pre-training hyperparameter optimization and algorithm configuration to deployment, and to adequately address security, power efficiency and adaptivity requirements. This paper also presents some preliminary results obtained by the first implementation of the optimization techniques supported by the tool flow.

关键词： Tools Inference algorithms Engines computer architecture Computational modeling Microelectronics Training

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：