检索结果-内蒙古大学图书馆

Off-the-shelf CNN features for 3D object retrieval

MULTIMEDIA TOOLS AND APPLICATIONS 2018年第15期77卷 19833-19849页

作者： Wang, Dong Wang, Bin Zhao, Sicheng Yao, Hongxun Liu, Hong Harbin Inst Technol Harbin Heilongjiang Peoples R China Harbin Inst Technol Dept Robot Res Inst Harbin Heilongjiang Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin Heilongjiang Peoples R China Harbin Inst Technol State Key Lab Robot & Syst Harbin Heilongjiang Peoples R China

Effective feature representation is crucial to view-based 3D object retrieval (V3OR). Most previous works employed hand-crafted features to represent the views of each object. Although deep learning based methods has shown its excellent performance in many vision tasks, it is hard to get excellent performance for unsupervised 3D object retrieval. In this paper, we propose to combine the off-the-shelf deep model and graph model to retrieve unseen objects. By employing the powerful deep classification models which are trained from millions of images, we obtain significant improvements compared with state of the art methods. We validate the effectiveness of the ready CNN from other domains that can greatly facilitate the representative ability of objects' views. In addition, we analyze the representative abilities of different fully connected layers for V3OR, and propose to employ multigraph learning to fuse the deep features of different layers. The autoencoder is then explored to improve the retrieval speed to a large extent. Experiments on two popular datasets are carried out to demonstrate the effectiveness of the proposed method.

关键词： 3D object retrieval Deep learning CNN autoencoder Multigraph learning Unseen objects

来源：评论

学校读者我要写书评

暂无评论

GRASS: Generative Recursive autoencoders for Shape Structures

引用

ACM TRANSACTIONS ON GRAPHICS 2017年第4期36卷 1-14页

作者： Li, Jun Xu, Kai Chaudhuri, Siddhartha Yumer, Ersin Zhang, Hao Guibas, Leonidas Natl Univ Def Technol Changsha Hunan Peoples R China Shenzhen Univ Shenzhen Peoples R China Shandong Univ Jinan Shandong Peoples R China Indian Inst Technol Bombay Maharashtra India Adobe Res San Jose CA USA Simon Fraser Univ Burnaby BC Canada Stanford Univ Stanford CA 94305 USA

We introduce a novel neural network architecture for encoding and synthesis of 3D shapes, particularly their structures. Our key insight is that 3D shapes are effectively characterized by their hierarchical organization of parts, which reflects fundamental intra-shape relationships such as adjacency and symmetry. We develop a recursive neural net (RvNN) based autoencoder to map a flat, unlabeled, arbitrary part layout to a compact code. The code effectively captures hierarchical structures of man-made 3D objects of varying structural complexities despite being fixed-dimensional: an associated decoder maps a code back to a full hierarchy. The learned bidirectional mapping is further tuned using an adversarial setup to yield a generative model of plausible structures, from which novel structures can be sampled. Finally, our structure synthesis framework is augmented by a second trained module that produces fine-grained part geometry, conditioned on global and local structural context, leading to a full generative pipeline for 3D shapes. We demonstrate that without supervision, our network learns meaningful structural hierarchies adhering to perceptual grouping principles, produces compact codes which enable applications such as shape classification and partial matching, and supports shape synthesis and interpolation with significant variations in topology and geometry.

关键词： analysis and synthesis of shape structures symmetry hierarchy recursive neural network autoencoder generative recursive autoencoder generative adversarial training

来源：评论

学校读者我要写书评

暂无评论

Machine learning entanglement freedom

引用

INTERNATIONAL JOURNAL OF QUANTUM INFORMATION 2018年第8期16卷

作者： Spillard, Samuel Turner, Christopher J. Meichanetzidis, Konstantinos Univ Leeds Sch Phys & Astron Leeds LS2 9JT W Yorkshire England

Quantum many-body systems realize many different phases of matter characterized by their exotic emergent phenomena. While some simple versions of these properties can occur in systems of free fermions, their occurrence generally implies that the physics is dictated by an interacting Hamiltonian. The interaction distance has been successfully used to quantify the effect of interactions in a variety of states of matter via the entanglement spectrum [C. J. Turner, K. Meichanetzidis, Z. Papic and J. K. Pachos, Nat. Commun. 8 (2017) 14926, Phys. Rev. B97 (2018) 125104]. The computation of the interaction distance reduces to a global optimization problem whose goal is to search for the free-fermion entanglement spectrum closest to the given entanglement spectrum. In this work, we employ techniques from machine learning in order to perform this same task. In a supervised learning setting, we use labeled data obtained by computing the interaction distance and predict its value via linear regression. Moving to a semi-supervised setting, we train an autoencoder to estimate an alternative measure to the interaction distance, and we show that it behaves in a similar manner.

关键词： Machine learning entanglement free fermions entanglement spectrum autoencoder topological phases

来源：评论

学校读者我要写书评

暂无评论

Deep appearance and motion learning for egocentric activity recognition

引用

NEUROCOMPUTING 2018年 275卷 438-447页

作者： Wang, Xuanhan Gao, Lianli Song, Jingkuan Zhen, Xiantong Sebe, Nicu Shen, Heng Tao Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Sichuan Peoples R China Columbia Univ Sch Engn & Appl Sci New York NY 10027 USA Univ Western Ontario Digital Imaging Grp London ON N6A 4V2 Canada Univ Trento Dept Informat Engn & Comp Sci I-38100 Trento Italy

Egocentric activity recognition has recently generated great popularity in computer vision due to its widespread applications in egocentric video analysis. However, it poses new challenges comparing to the conventional third-person activity recognition tasks, which are caused by significant body shaking, varied lengths, and poor recoding quality, etc. To handle these challenges, in this paper, we propose deep appearance and motion learning (DAML) for egocentric activity recognition, which leverages the great strength of deep learning networks in feature learning. In contrast to hand- crafted visual features or pre-trained convolutional neural network (CNN) features with limited generality to new egocentric videos, the proposed DAML is built on the deep autoencoder (DAE), and directly extracts appearance and motion feature, the main cue of activities, from egocentric videos. The DAML takes advantages of the great effectiveness and efficiency of the DAE in unsupervised feature learning, which provides a new representation learning framework of egocentric videos. The learned appearance and motion features by the DAML are seamlessly fused to accomplish a rich informative egocentric activity representation which can be readily fed into any supervised learning models for activity recognition. Experimental results on two challenging benchmark datasets show that the DAML achieves high performance on both short- and long-term egocentric activity recognition tasks, which is comparable to or even better than the state-of-the-art counterparts. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Multiple feature learning Deep learning autoencoder Egocentric video Activity recognition

来源：评论

学校读者我要写书评

暂无评论

A Study on Deep Neural Network-Based DC Offset Removal for Phase Estimation in Power Systems

引用

ENERGIES 2019年第9期12卷 1619页

作者： Kim, Sun-Bin Sok, Vattanak Kang, Sang-Hee Lee, Nam-Ho Nam, Soon-Ryul Myongji Univ Dept Elect Engn Yongin 17058 South Korea Korea Elect Power Res Inst Daejeon 34056 South Korea

The purpose of this paper is to remove the exponentially decaying DC offset in fault current waveforms using a deep neural network (DNN), even under harmonics and noise distortion. The DNN is implemented using the TensorFlow library based on Python. autoencoders are utilized to determine the number of neurons in each hidden layer. Then, the number of hidden layers is experimentally decided by comparing the performance of DNNs with different numbers of hidden layers. Once the optimal DNN size has been determined, intensive training is performed using both the supervised and unsupervised training methodologies. Through various case studies, it was verified that the DNN is immune to harmonics, noise distortion, and variation of the time constant of the DC offset. In addition, it was found that the DNN can be applied to power systems with different voltage levels.

关键词： autoencoder exponentially decaying DC offset deep neural networks (DNNs) optimal size supervised training Tensorflow unsupervised training

来源：评论

学校读者我要写书评

暂无评论

A survey on deep learning based face recognition

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2019年 189卷 102805-000页

作者： Guo, Guodong Zhang, Na North Univ China Sch Informat & Commun Engn Taiyuan Shanxi Peoples R China West Virginia Univ LCSEE Morgantown WV 26506 USA

Deep learning, in particular the deep convolutional neural networks, has received increasing interests in face recognition recently, and a number of deep learning methods have been proposed. This paper summarizes about 330 contributions in this area. It reviews major deep learning concepts pertinent to face image analysis and face recognition, and provides a concise overview of studies on specific face recognition problems, such as handling variations in pose, age, illumination, expression, and heterogeneous face matching. A summary of databases used for deep face recognition is given as well. Finally, some open challenges and directions are discussed for future research.

关键词： Deep learning Face recognition Artificial Neural Network Convolutional Neural Networks autoencoder Generative Adversarial Networks

来源：评论

学校读者我要写书评

暂无评论

Continuous-Time Relationship Prediction in Dynamic Heterogeneous Information Networks

引用

ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 2019年第4期13卷 44-44页

作者： Sajadmanesh, Sina Bazargani, Sogol Zhang, Jiawei Rabiee, Hamid R. Sharif Univ Technol Dept Comp Engn Azadi Ave Tehran *** Iran Florida State Univ Dept Comp Sci 1017 Acad Way Tallahassee FL 32304 USA

Online social networks, World Wide Web, media, and technological networks, and other types of so-called Information networks are ubiquitous nowadays. These information networks are inherently heterogeneous and dynamic. They are heterogeneous as they consist of multi-typed objects and relations, and they are dynamic as they are constantly evolving over time. One of the challenging issues in such heterogeneous and dynamic environments is to forecast those relationships in the network that will appear in the future. In this article, we try to solve the problem of continuous-time relationship prediction in dynamic and heterogeneous information networks. This implies predicting the time it takes for a relationship to appear in the future, given its features that have been extracted by considering both heterogeneity and temporal dynamics of the underlying network. To this end, we first introduce a feature extraction framework that combines the power of meta-path-based modeling and recurrent neural networks to effectively extract features suitable for relationship prediction regarding heterogeneity and dynamicity of the networks. Next, we propose a supervised non-parametric approach, called Non-Parametric Generalized Linear Model (NIP-GLM), which infers the hidden underlying probability distribution of the relationship building time given its features. We then present a learning algorithm to train NP-GLM and an inference method to answer time-related queries. Extensive experiments conducted on synthetic data and three real-world datasets, namely Delicious, MovieLens, and DBLP, demonstrate the effectiveness of NP-am in solving continuous-time relationship prediction problem vis-a-vis competitive baselines.

关键词： Link prediction social network analysis heterogeneous network non-parametric modeling recurrent neural network autoencoder

来源：评论

学校读者我要写书评

暂无评论

Classification of lung adenocarcinoma transcriptome subtypes from pathological images using deep convolutional networks

引用

INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY 2018年第12期13卷 1905-1913页

作者： Antonio, Victor Andrew A. Ono, Naoaki Saito, Akira Sato, Tetsuo Altaf-Ul-Amin, Md. Kanaya, Shigehiko Nara Inst Sci & Technol Grad Sch Sci & Technol Ikoma Japan Nara Inst Sci & Technol Data Sci Ctr Ikoma Japan Univ Tokyo Div Hlth Serv Promot Tokyo Japan Nara Inst Sci & Technol Grad Sch informat Sci Ikoma Japan

PurposeConvolutional neural networks have become rapidly popular for image recognition and image analysis because of its powerful potential. In this paper, we developed a method for classifying subtypes of lung adenocarcinoma from pathological images using neural network whose that can evaluate phenotypic features from wider area to consider cellular *** order to recognize the types of tumors, we need not only to detail features of cells, but also to incorporate statistical distribution of the different types of cells. Variants of autoencoders as building blocks of pre-trained convolutional layers of neural networks are implemented. A sparse deep autoencoder which minimizes local information entropy on the encoding layer is then proposed and applied to images of size . We applied this model for feature extraction from pathological images of lung adenocarcinoma, which is comprised of three transcriptome subtypes previously defined by the Cancer Genome Atlas network. Since the tumor tissue is composed of heterogeneous cell populations, recognition of tumor transcriptome subtypes requires more information than local pattern of cells. The parameters extracted using this approach will then be used in multiple reduction stages to perform classification on larger *** were able to demonstrate that these networks successfully recognize morphological features of lung adenocarcinoma. We also performed classification and reconstruction experiments to compare the outputs of the variants. The results showed that the larger input image that covers a certain area of the tissue is required to recognize transcriptome subtypes. The sparse autoencoder network with input provides a 98.9% classification *** study shows the potential of autoencoders as a feature extraction paradigm and paves the way for a whole slide image analysis tool to predict molecular subtypes of tumors from pathological features.

关键词： Deep learning Lung cancer Computer-aided diagnosis autoencoder Independent subspace analysis

来源：评论

学校读者我要写书评

暂无评论

Automatic Facial Expression Recognition System Using Deep Network-Based Data Fusion

引用

IEEE TRANSACTIONS ON CYBERNETICS 2018年第1期48卷 103-114页

作者： Majumder, Anima Behera, Laxmidhar Subramanian, Venkatesh K. Indian Inst Technol Dept Elect Engn Kanpur 208016 Uttar Pradesh India

This paper presents a novel automatic facial expressions recognition system (AFERS) using the deep network framework. The proposed AFERS consists of four steps: 1) geometric features extraction;2) regional local binary pattern (LBP) features extraction;3) fusion of both the features using autoencoders;and 4) classification using Kohonen self-organizing map (SOM)-based classifier. This paper makes three distinct contributions. The proposed deep network consisting of autoencoders and the SOM-based classifier is computationally more efficient and performance wise more accurate. The fusion of geometric features with LBP features using autoencoders provides better representation of facial expression. The SOM-based classifier proposed in this paper has been improved by making use of a soft-threshold logic and a better learning algorithm. The performance of the proposed approach is validated on two widely used databases (DBs): 1) MMI and 2) extended Cohn-Kanade (CK+). An average recognition accuracy of 97.55% in MMI DB and 98.95% in CK+ DB are obtained using the proposed algorithm. The recognition results obtained from fused features are found to be distinctly superior to both recognition using individual features as well as recognition with a direct concatenation of the individual feature vectors. Simulation results validate that the proposed AFERS is more efficient as compared to the existing approaches.

关键词： autoencoder deep network facial expression recognition system self-organizing map (SOM) support vector machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

Detection of Tennis Activities with Wearable Sensors

引用

SENSORS 2019年第22期19卷 5004-5004页

作者： Benages Pardo, Luis Buldain Perez, David Orrite Urunuela, Carlos Univ Zaragoza Aragon Inst Engn Res Zaragoza 50018 Spain

This paper aims to design and implement a system capable of distinguishing between different activities carried out during a tennis match. The goal is to achieve the correct classification of a set of tennis strokes. The system must exhibit robustness to the variability of the height, age or sex of any subject that performs the actions. A new database is developed to meet this objective. The system is based on two sensor nodes using Bluetooth Low Energy (BLE) wireless technology to communicate with a PC that acts as a central device to collect the information received by the sensors. The data provided by these sensors are processed to calculate their spectrograms. Through the application of innovative deep learning techniques with semi-supervised training, it is possible to carry out the extraction of characteristics and the classification of activities. Preliminary results obtained with a data set of eight players, four women and four men have shown that our approach is able to address the problem of the diversity of human constitutions, weight and sex of different players, providing accuracy greater than 96.5% to recognize the tennis strokes of a new player never seen before by the system.

关键词： gyroscopes accelerometers tennis strokes spectrograms autoencoder deep learning

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：