检索结果-内蒙古大学图书馆

Robust lip segmentation based on complexion mixture model 1

17th Pacific-Rim Conference on Multimedia, PCM 2016

作者： Hu, Yangyang Lu, Hong Cheng, Jinhua Zhang, Wenqiang Li, Fufeng Zhang, Weifei Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China School of Computer Science Shanghai Engineering Research Center for Video Technology and System Fudan University Shanghai China Shanghai University of Traditional Chinese Medicine Shanghai201203 China

ISBN: (数字)9783319488905

ISBN: (纸本)9783319488899

Lip image analysis plays a vital role in Traditional Chinese Medicine (TCM) and other visual and speech recognition applications. However, if the lip images contain weak color difference with background parts or the background is complicated, most of the current methods are difficult to robustly and accurately segment the lip regions. In this paper, we propose a lip segmentation method based on complexion mixture model to resolve this problem. Specifically, we use the pixels’ color of the upper (lip-free) part of the face as training data to build a corresponding complexion Gaussian Mixture Model (GMM) for each face image in lab color space. Then by iteratively removing the complexion pixels not belonging to the lip region in the lower part of the face based on the GMM, an initial lip can be obtained. We further build GMMs on the initial lip and non-lip regions, respectively. The background probability map can be obtained based on the GMMs. Finally, we extract the optimal lip contour via a smooth operation. Experiments are performed on our dataset with 1000 face images. Experimental results demonstrate the efficacy of the proposed method compared with the state-of-art lip segmentation methods. © Springer International Publishing AG 2016.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Analyzing linguistic knowledge in sequential model of sentence

Analyzing linguistic knowledge in sequential model of senten...

引用

2016 Conference on Empirical Methods in Natural Language processing, EMNLP 2016

作者： Qian, Peng Qiu, Xipeng Huang, Xuanjing Shanghai Key Laboratory of Intelligent Information Processing Fudan University School of Computer Science Fudan University 825 Zhangheng Road Shanghai China

ISBN: (纸本)9781945626258

Sentence modelling is a fundamental topic in computational linguistics. Recently, deep learning-based sequential models of sentence, such as recurrent neural network, have proved to be effective in dealing with the non- sequential properties of human language. However, little is known about how a recurrent neural network captures linguistic knowledge. Here we propose to correlate the neuron activation pattern of a LSTM language model with rich language features at sequential, lexical and compositional level. Qualitative visualization as well as quantitative analysis under multilingual perspective reveals the effectiveness of gate neurons and indicates that LSTM learns to allow different neurons selectively respond to linguistic knowledge at different levels. Cross-language evidence shows that the model captures different aspects of linguistic properties for different languages due to the variance of syntactic complexity. Additionally, we analyze the influence of modelling strategy on linguistic knowledge encoded implicitly in different sequential models. © 2016 Association for Computational Linguistics

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Bridging LSTM architecture and the neural dynamics during reading 25

Bridging LSTM architecture and the neural dynamics during re...

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

Recently, the long short-term memory neural network (LSTM) has attracted wide interest due to its success in many tasks. LSTM architecture consists of a memory cell and three gates, which looks similar to the neuronal networks in the brain. However, there still lacks the evidence of the cognitive plausibility of LSTM architecture as well as its working mechanism. In this paper, we study the cognitive plausibility of LSTM by aligning its internal architecture with the brain activity observed via fMRI when the subjects read a story. Experiment results show that the artificial memory vector in LSTM can accurately predict the observed sequential brain activities, indicating the correlation between LSTM architecture and the cognitive process of story reading.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Modelling interaction of sentence pair with coupled-LSTMs

Modelling interaction of sentence pair with coupled-LSTMs

引用

2016 Conference on Empirical Methods in Natural Language processing, EMNLP 2016

作者： Liu, Pengfei Qiu, Xipeng Zhou, Yaqian Chen, Jifan Huang, Xuanjing Shanghai Key Laboratory of Intelligent Information Processing Fudan University School of Computer Science Fudan University 825 Zhangheng Road Shanghai China

ISBN: (纸本)9781945626258

Recently, there is rising interest in modelling the interactions of two sentences with deep neural networks. However, most of the existing methods encode two sequences with separate encoders, in which a sentence is encoded with little or no information from the other sentence. In this paper, we propose a deep architecture to model the strong interaction of sentence pair with two coupled-LSTMs. Specifically, we introduce two coupled ways to model the interdependences of two LSTMs, coupling the local contextualized interactions of two sentences. We then aggregate these interactions and use a dynamic pooling to select the most informative features. Experiments on two very large datasets demonstrate the efficacy of our proposed architectures. © 2016 Association for Computational Linguistics

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep multi-task learning with shared memory

Deep multi-task learning with shared memory

引用

2016 Conference on Empirical Methods in Natural Language processing, EMNLP 2016

作者： Liu, Pengfei Qiu, Xipeng Huang, Xuanjing Shanghai Key Laboratory of Intelligent Information Processing Fudan University School of Computer Science Fudan University 825 Zhangheng Road Shanghai China

ISBN: (纸本)9781945626258

Neural network based models have achieved impressive results on various specific tasks. However, in previous works, most models are learned separately based on single-task supervised objectives, which often suffer from insufficient training data. In this paper, we propose two deep architectures which can be trained jointly on multiple related tasks. More specifically, we augment neural model with an external memory, which is shared by several tasks. Experiments on two groups of text classification tasks show that our proposed architectures can improve the performance of a task with the help of other related tasks. © 2016 Association for Computational Linguistics

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Sketch-based image retrieval with a novel BoVW representation 22nd

Sketch-based image retrieval with a novel BoVW representatio...

引用

22nd International Conference on MultiMedia Modeling, MMM 2016

作者： Jin, Cheng Li, Chenjie Wang, Zheming Zhang, Yuejie Zhang, Tao School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China School of Information Management and Engineering Shanghai University of Finance and Economics Shanghai200433 China

ISBN: (纸本)9783319276700

A novel Bag-of-Visual-Word (BoVW) based approach is developed in this paper to facilitate more effective Sketch-based Image Retrieval (SBIR). We focus on constructing the visual vocabulary based on the BoVW representation with both the spatial distribution and inter-relationship of descriptors. To optimize the sketch-image matching, the weighting quantization is created by integrating both the neighbor and spatial feature information to quantify features as visual words. We emphasize on an inverted indexing by converting an image to a trigram representation with visual words and their spatial information. Our experiments have obtained very positive results. © Springer International Publishing Switzerland 2016.

关键词： Indexing (of information)

来源：评论

学校读者我要写书评

暂无评论

Exact evaluation of the causal spectrum and localization properties of electronic states on a scale-free network

arXiv

引用

arXiv 2017年

作者： Xie, Pinchen Yang, Bingjia Zhang, Zhongzhi Andrade, Roberto F.S. Department of Physics Fudan University Shanghai200433 China Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai200433 China School of Computer Science Fudan University Shanghai200433 China Instituto de Fisica Universidade Federal da Bahia Salvador40210-210 Brazil

A nearest-neighbor tight-binding model on a tree structure is investigated. The full energy spectrum of the normalized Hamiltonian can be expressed in terms of successively increasing number of contributions at any finite step of construction of the tree, resulting in a causal chain. The degree of quantum localization of any eigenstate, measured by the inverse participation ratio (IPR), is also analytically expressed by means of terms in corresponding eigenvalue chain. The resulting IPR scaling behavior is expressed by the tails of eigenvalue chains as well. Copyright © 2017, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral light field stereo matching

arXiv

引用

arXiv 2017年

作者： Zhu, Kang Xue, Yujia Fu, Qiang Kang, Sing Bing Chen, Xilin Yu, Jingyi School of Information Science and Technology ShanghaiTech University Shanghai China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Plex-VR Inc. Shanghai Microsoft Research RedmondWA United States Department of Computer and Information Sciences University of Delaware NewarkDE United States

In this paper, we describe how scene depth can be extracted using a hyperspectral light field capture (H-LF) system. Our H-LF system consists of a 5 × 6 array of cameras, with each camera sampling a different narrow band in the visible spectrum. There are two parts to extracting scene depth. The first part is our novel cross-spectral pairwise matching technique, which involves a new spectral-invariant feature descriptor and its companion matching metric we call bidirectional weighted normalized cross correlation (BWNCC). The second part, namely, H-LF stereo matching, uses a combination of spectral-dependent correspondence and defocus cues that rely on BWNCC. These two new cost terms are integrated into a Markov Random Field (MRF) for disparity estimation. Experiments on synthetic and real H-LF data show that our approach can produce high-quality disparity maps. We also show that these results can be used to produce the complete plenoptic cube in addition to synthesizing all-focus and defocused color images under different sensor spectral responses. Copyright © 2017, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Low-power voltage multiplier synthesis tool for preliminary topology identification 11

Low-power voltage multiplier synthesis tool for preliminary ...

引用

11th International Conference on Open Source Systems and Technologies, ICOSST 2017

作者： Dell'Anna, Francesco G. Dong, Tao Li, Ping Yumei, Wen Azadmehr, Mehdi Berg, Yngvar Institute of Applied Micro-nano Science and Technology Chongqing Key Lab of Micro-Nanosystems Technology and Smart Transducing National Research Base of Intelligent Manufacturing Service Chongqing Technology and Business University CTBU Chongqing China Department of Microsystems Faculty of Technology Natural Sciences and Maritime Sciences University College of Southeast Norway USN Kongsberg3603 Norway Department of Instrumentation School of Electronic Information and Electric Engineering Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9781538616581

This paper introduces a synthesis tool designed for low-power voltage multipliers. Voltage multipliers are rectifiers employed to generate a constant output voltage, which exceeds the peak-to-peak amplitude voltage of the input signal. At low power levels the attained performance of conventional voltage multipliers is strictly related to the transistor threshold voltage in the multiplication chain, which, at low voltage levels (tens of mV), are operated primarily in the subthreshold region or in cutoff mode. To improve the power conversion efficiency of voltage multipliers at low power levels, this paper introduces a novel passive threshold compensation technique to enhance the transistor conductivity, providing a static bias voltage at the gate of the transistors. Furthermore, a CAD oriented synthesis tool for the presented threshold compensation technique is proposed. The synthesis tool gives a preliminary indication on the rectifier topology (number of stages and compensation order) given target environmental conditions, target output performance, and adopted components in the rectification chain. The core algorithm is based trial and error simulator for the simplified rectifier model, which is employed to speed up the computations pertaining the voltage multiplier synthesis. © 2017 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Regional Gating Neural Networks for Multi-label Image Classification 27

Regional Gating Neural Networks for Multi-label Image Classi...

引用

27th British Machine Vision Conference, BMVC 2016

作者： Zhao, Rui-Wei Li, Jianguo Chen, Yurong Liu, Jia-Ming Jiang, Yu-Gang Xue, Xiangyang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Intel Labs China Beijing China Department of Control Science and Engineering Tongji University Shanghai China

This paper proposes a novel deep learning framework for multi-label image classification, namely regional gating neural networks (RGNN). The motivation is two folds. First, global image features (including CNN based features) ignore the underlying context information among different objects in an image. Consequently, people attempt to use information from objectness regions. However, current objectness region proposal algorithms usually produce several thousand region candidates, including many classification irrelevant or even noisy regions. This leads to the second problem: how to select useful contextual regions for image classification. RGNN is an end-to-end deep learning framework that can automatically select contextual region features with specially designed gate units, which are then fused for classification. Because the gate units and the classifier are integrated in the same deep neural network pipeline, we can learn parameters of the network simultaneously. We evaluate the proposed method on PASCAL VOC 2007/2012 and MS-COCO benchmarks, and results show that RGNN is superior to existing state-of-the-art methods. © 2016. The copyright of this document resides with its authors.

关键词： Image classification

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：