检索结果-内蒙古大学图书馆

Naturally combined shape-color moment invariants under affine transformationsi

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Gong, Ming Hao, You Mo, Hanlin Li, Hua Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China CAI & Research Group Microsoft Search Technology Center Asia Beijing China

We proposed a kind of naturally combined shape-color affine moment invariants (SCAMI), which consider both shape and color affine transformations simultaneously in one single system. In the real scene, color and shape deformations always exist in images simultaneously. Simple shape invariants or color invariants can not be qualified for this situation. The conventional method is just to make a simple linear combination of the two factors. Meanwhile, the manual selection of weights is a complex issue. Our construction method is based on the multiple integration framework. The integral kernel is assigned as the continued product of the shape and color invariant cores. It is the first time to directly derive an invariant to dual affine transformations of shape and color. The manual selection of weights is no longer necessary, and both the shape and color transformations are extended to affine transformation group. With the various of invariant cores, a set of lower-order invariants are constructed and the completeness and independence are discussed detailedly. A set of SCAMIs, which called SCAMI24, are recommended, and the effectiveness and robustness have been evaluated on both synthetic and real datasets. Copyright © 2017, The Authors. All rights reserved.

关键词： Color

Viewpoint selection for photographing architectures

学校读者我要写书评

暂无评论

arXiv 2017年

作者： He, Jingwu Wang, Linbo Zhou, Wenzhe Zhang, Hongjie Cui, Xiufen Guo, Yanwen National Key Lab for Novel Software Technology Nanjing University NanJing210023 China MOE Key Laboratory of Intelligent Computing and Signal Processing Institute of Media Computing Anhui University HeFei230039 China Samsung Electronics R&D China

—This paper studies the problem of how to choose good viewpoints for taking photographs of architectures. We achieve this by learning from professional photographs of world famous landmarks that are availab.e on the Internet. Unlike previous efforts devoted to photo quality assessment which mainly rely on 2D image features, we show in this paper combining 2D image features extracted from images with 3D geometric features computed on the 3D models can result in more reliable evaluation of viewpoint quality. Specifically, we collect a set of photographs for each of 15 world famous architectures as well as their 3D models from the Internet. Viewpoint recovery for images is carried out through an image-model registration process, after which a newly proposed viewpoint clustering strategy is exploited to validate users’ viewpoint preferences when photographing landmarks. Finally, we extract a number of 2D and 3D features for each image based on multiple visual and geometric cues and perform viewpoint recommendation by learning from both 2D and 3D features using a specifically designed SVM-2K multi-view learner, achieving superior performance over using solely 2D or 3D features. We show the effectiveness of the proposed approach through extensive experiments. The experiments also demonstrate that our system can be used to recommend viewpoints for rendering textured 3D models of buildings for the use of architectural design, in addition to viewpoint evaluation of photographs and recommendation of viewpoints for photographing architectures in practice. Copyright © 2017, The Authors. All rights reserved.

关键词： Photography

A deep relevance matching model for ad-hoc retrieval

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Guo, Jiafeng Fan, Yixing Ai, Qingyao Bruce Croft, W. CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China Center for Intelligent Information Retrieval University of Massachusetts Amherst MA United States

In recent years, deep neural networks have led to exciting breakthroughs in speech recognition, computer vision, and natural language processing (NLP) tasks. However, there have been few positive results of deep models on ad-hoc retrieval tasks. This is partially due to the fact that many important characteristics of the ad-hoc retrieval task have not been well addressed in deep models yet. Typically, the ad-hoc retrieval task is formalized as a matching problem between two pieces of text in existing work using deep models, and treated equivalent to many NLP tasks such as paraphrase identification, question answering and automatic conversation. However, we argue that the ad-hoc retrieval task is mainly about relevance matching while most NLP matching tasks concern semantic matching, and there are some fundamental differences between these two matching tasks. Successful relevance matching requires proper handling of the exact matching signals, query term importance, and diverse matching requirements. In this paper, we propose a novel deep relevance matching model (DRMM) for ad-hoc retrieval. Specifically, our model employs a joint deep architecture at the query term level for relevance matching. By using matching histogram mapping, a feed forward matching network, and a term gating network, we can effectively deal with the three relevance matching factors mentioned above. Experimental results on two representative benchmark collections show that our model can significantly outperform some well-known retrieval models as well as state-of-the-art deep matching models. Copyright © 2017, The Authors. All rights reserved.

关键词： Natural language processing systems

Is local window essential for neural network based chinese word segmentation? 15th

学校读者我要写书评

暂无评论

Is local window essential for neural network based chinese w...

15th China National Conference on Chinese Computational Linguistics, CCL 2016 and 4th International Symposium on Natural Language processing Based on Naturally Annotated Big Data, NLP-NABD 2016

作者： Zhang, Jinchao Meng, Fandong Wang, Mingxuan Zheng, Daqi Jiang, Wenbin Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China ADAPT Centre School of Computing Dublin City University Dublin Ireland

ISBN: (纸本)9783319476735

Neural network based Chinese Word Segmentation (CWS) approaches can bypass the burdensome feature engineering comparing with the conventional ones. All previous neural network based approaches rely on a local window in character sequence lab.lling process. It can hardly exploit the outer context and may preserve indifferent inner context. Moreover, the size of local window is a toilsome manual-tuned hyper-parameter that has significant influence on model performance. We are wondering if the local window can be discarded in neural network based CWS. In this paper, we present a window-free Bi-directional Long Short-term Memory (Bi-LSTM) neural network based Chinese word segmentation model. The model takes the whole sentence under consideration to generate reasonable word sequence. The experiments show that the Bi-LSTM can learn sufficient context for CWS without the local window. © Springer International Publishing AG 2016.

关键词： Long short-term memory

Cloud service resource allocation with particle swarm optimization algorithm 12th

学校读者我要写书评

暂无评论

Cloud service resource allocation with particle swarm optimi...

12th International Conference on Bio-Inspired computing: Theories and Applications, BIC-TA 2017

作者： Cheng, Shi Guo, Lantian Yang, Tao Feng, Jiqiang Sun, Yifei Shao, Chang Duan, Qiqi School of Computer Science Shaanxi Normal University Xi’an China Shenzhen Research Institute Northwestern Polytechnical University Shenzhen China School of Automation Northwestern Polytechnical University Xi’an China Institute of Intelligent Computing Science Shenzhen University Shenzhen China School of Physics and Information Technology Shaanxi Normal University Xi’an China Shenzhen Key Lab of Computational Intelligence Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

ISBN: (纸本)9789811071782

Cloud service resource allocation is an essential task in cloud computing. The cloud service resource allocation problem is modeled as an optimization problem, and is solved via different particle swarm optimization (PSO) variants in this paper. The aim of our method is to minimize the delay and the price at the same time. Based on the experimental results, it could be conducted that the good performance could be achieved via PSO algorithms. The future research is to utilize PSO algorithms on solving more real-world problems, especially with other quality of service problems. © Springer Nature Singapore Pte Ltd 2017.

关键词： Swarm intelligence

Neural matching models for question retrieval and next question prediction in conversation

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Yang, Liu Zamani, Hamed Zhang, Yongfeng Guo, Jiafeng Bruce Croft, W. Center for Intelligent Information Retrieval University of Massachusetts Amherst AmherstMA United States CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

The recent boom of AI has seen the emergence of many human-computer conversation systems such as Google Assistant, Microsoft Cortana, Amazon Echo and Apple Siri. We introduce and formalize the task of predicting questions in conversations, where the goal is to predict the new question that the user will ask, given the past conversational context. This task can be modeled as a "sequence matching" problem, where two sequences are given and the aim is to learn a model that maps any pair of sequences to a matching probability. Neural matching models, which adopt deep neural networks to learn sequence representations and matching scores, have attracted immense research interests of information retrieval and natural language processing communities. In this paper, we first study neural matching models for the question retrieval task that has been widely explored in the literature, whereas the effectiveness of neural models for this task is relatively unstudied. We further evaluate the neural matching models in the next question prediction task in conversations. We have used the publicly availab.e Quora data and Ubuntu chat logs in our experiments. Our evaluations investigate the potential of neural matching models with representation learning for question retrieval and next question prediction in conversations. Experimental results show that neural matching models perform well for both tasks. Copyright © 2017, The Authors. All rights reserved.

关键词： Forecasting

Memory-enhanced Decoder for neural machine translation

学校读者我要写书评

暂无评论

Memory-enhanced Decoder for neural machine translation

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

作者： Wang, Mingxuan Lu, Zhengdong Li, Hang Liu, Qun Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Noah's Ark Lab Huawei Technologies ADAPT Centre School of Computing Dublin City University Ireland

ISBN: (纸本)9781945626258

We propose to enhance the RNN decoder in a neural machine translator (NMT) with external memory, as a natural but powerful extension to the state in the decoding RNN. This memory-enhanced RNN decoder is called MEMDEC. At each time during decoding, MEMDEC will read from this memory and write to this memory once, both with content-based addressing. Unlike the unbounded memory in previous work(Bahdanau et al., 2014) to store the representation of source sentence, the memory in MEMDEC is a matrix with predetermined size designed to better capture the information important for the decoding process at each time step. Our empirical study on Chinese-English translation shows that it can improve by 4.8 BLEU upon Groundhog and 5.3 BLEU upon on Moses, yielding the best performance achieved with the same training set. © 2016 Association for Computational Linguistics

关键词： Neural machine translation

A visual awareness pathway in cognitive model ABGP

学校读者我要写书评

暂无评论

High technology Letters 2016年第4期22卷 395-403页

作者：马刚 Yang Xi Lu Chengxiang Zhang Bo Shi Zhongzhi The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 P. R. China University of Chinese Academy of Sciences Beijing 100190 P. R. China

The cognitive model ABGP is a special model for agents,which consists of awareness,beliefs,goals and plans. The ABGP agents obtain the knowledge directly from the natural scenes only through some single preestablished rules like most agent architectures. Inspired by the biological visual cortex( V1) and the higher brain areas perceiving the visual feature,deep convolution neural networks( CNN) are introduced as a visual pathway into ABGP to build a novel visual awareness module. Then a rat-robot maze search simulation platform is constructed to validate that CNN can be used for the awareness module of ABGP. According to the simulation results,the rat-robot implemented by the ABGP with the CNN awareness module reaches the excellent performance of recognizing guideposts,which directly enhances the capability of the communication between the agent and the natural scenes and improves the ability to recognize the real world,which successfully demonstrates that an agent can independently plan its path in terms of the natural scenes.

关键词： ABGP visual cortex(V1) convolution neural networks(CNN) awareness visual pathway

A Novel Soft Switching Two-Stage Heating Power Supply Topology for Silicon Growth Furnace 35

学校读者我要写书评

暂无评论

A Novel Soft Switching Two-Stage Heating Power Supply Topolo...

第35届中国控制会议

作者： GUO Xin REN Hai-Peng LIU Ding SUO Jun PENG Shu-Tao School of Automation and Information Engineering Xi'an University of Technology Shaanxi Key Lab.of Complex System Control and Intelligent Information Processing Shaanxi Electric Power Research Institute

ISBN: (纸本)9781509009107

Mono-crystalline silicon is widely applied in the photovoltaic and the integrated circuit *** power supply,as the key element of the mono-crystalline silicon growth furnace,plays an important role in the performance of the whole *** this paper,we propose a new kind of two-stage silicon growth furnace heating power supply topology *** first stage three phase rectifier employs the compound active clamp zero voltage soft switching(CACZVS) three-phase power factor correction(PFC) converter to achieve unity power factor and DC bus voltage regulation,and the second stage DC/DC converter employs phase shifted full bridge zero voltage and zero current soft switching converter(FB-ZVZCS) to regulate the output *** with the heating power supply of non-controlled rectifier type or three-phase power factor correction circuit using hard switching,the proposed two-stage converter structure can achieve high power factor,high efficiency and more flexibility of *** simulation results show the correctness of the analysis.

关键词： Silicon Growth Furnace Heating Power Supply CACZVS three phase PFC converter FB-ZVZCS converter