Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
If you haven’t received the email, please:
|
|
There are 233 papers published in subject: > since this site started. |
Select Subject |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
1. A Dialog Robot Based on WeChat | |||
Xiaoyi Chen,Jing Wang,Qiwei Shen,Qi Qi,Jingyu Wang | |||
Computer Science and Technology 12 November 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:WeChat is one of the most popular instant messaging applications in the world. It has now become an important access to variety business systems for billions of users. so the vast majority of companies want to provide their business services onto WeChat in order to gain advantage in fierce market competitions. However, as far as we know, today it is not easy to access WeChat with business service. In this paper, we propose a framework to integrate business services and WeChat. On the basis of this framework, companies or entrepreneurs can provide their business services on WeChat easily. Finally, we use a case study to demonstrate how our service can be used in helping tickets sells and statistical analysis. | |||
TO cite this article:Xiaoyi Chen,Jing Wang,Qiwei Shen, et al. A Dialog Robot Based on WeChat[OL].[12 November 2017] http://en.paper.edu.cn/en_releasepaper/content/4741918 |
2. Visual Word Based Similar Image Retrieval \Optimization By Hamming Distance | |||
ZHUANG Huang, WEI Yi-Fei, SONG Mei | |||
Computer Science and Technology 11 May 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In this paper we present a new method for visual word based similar image retrieval by comparing content of a query image with images stored in a database. The retrieval consists of three main steps: feature extraction, indexing and query optimization. The feature extraction step is based on SURF algorithm. For indexing, we use the K-Means algorithm and the Bag-of-Visual-Words model. The last step is very significant and we associate TF-IDF with Hamming Distance to query. Our method is tested on the highly diverse opening images and has proved a better retrieval accuracy based on the experimental results. | |||
TO cite this article:ZHUANG Huang, WEI Yi-Fei, SONG Mei. Visual Word Based Similar Image Retrieval \Optimization By Hamming Distance[OL].[11 May 2017] http://en.paper.edu.cn/en_releasepaper/content/4734318 |
3. Audio Visual Speech Recognition with Multimodal Recurrent Neural Networks | |||
Weijiang Feng, Naiyang Guan, Yuan Li, Xiang Zhang, Zhigang Luo | |||
Computer Science and Technology 04 May 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Studies on nowadays human-machine interface have demonstrated that visual information can enhance speech recognition accuracy especially in noisy environments. Deep learning has been widely used to tackle such audio visual speech recognition (AVSR) problem due to its astonishing achievements in both speech recognition and image recognition. Although existing deep learning models succeed to incorporate visual information into speech recognition, none of them simultaneously considers sequential characteristics of both audio and visual modalities. To overcome this deficiency, we proposed a multimodal recurrent neural network (multimodal RNN) model to take into account the sequential characteristics of both audio and visual modalities for AVSR. In particular, multimodal RNN includes three components, i.e., audio part, visual part, and fusion part, where the audio part and visual part capture the sequential characteristics of audio and visual modalities, respectively, and the fusion part combines the outputs of both modalities. Here we modelled the audio modality by using a LSTM RNN, and modelled the visual modality by using a convolutional neural network (CNN) plus a LSTM RNN, and combined both models by a multimodal layer in the fusion part. We validated the effectiveness of the proposed multimodal RNN model on a multi-speaker AVSR benchmark dataset termed AVletters. The experimental results show the performance improvements comparing to the known highest audio visual recognition accuracies on AVletters, and confirm the robustness of our multimodal RNN model. | |||
TO cite this article:Weijiang Feng, Naiyang Guan, Yuan Li, et al. Audio Visual Speech Recognition with Multimodal Recurrent Neural Networks[OL].[ 4 May 2017] http://en.paper.edu.cn/en_releasepaper/content/4732586 |
4. A User Interest Recommendation Model Based on Topic Network and Social Graph | |||
TANG Zhirong,TIAN Ye,WANG Wendong | |||
Computer Science and Technology 02 May 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Detecting user interested topics is one of the most important issues in a recommender system. A topic recommendation model is proposed in this paper, which utilizes the topic network and the social graph to recommend topics that are interesting to the user. The model could be applied to a social Q&A (Question and Answering) system. First, all the topics in the social Q&A system are organized as a topic network. By analyzing the topics that the users have followed and the topic distribution in the topic network, we explore the most relevant topics for users. Secondly, we observe that the topics which attract the majority of our friends or the topics that our best friends are concerned about, might be prospective interesting topics for us. Therefore, we consider these two kinds of scenarios simultaneously to design the topic recommendation algorithm. Based on the data set derived from the Quora website, the experimental results demonstrate that our algorithm outperforms the standard Collaborative Filtering (CF) in the accuracy. | |||
TO cite this article:TANG Zhirong,TIAN Ye,WANG Wendong. A User Interest Recommendation Model Based on Topic Network and Social Graph[OL].[ 2 May 2017] http://en.paper.edu.cn/en_releasepaper/content/4731619 |
5. Video Emotion Recognition Using Subtitles Semantics, Audio and Visual Features | |||
LI Chao,CHENG Gong,HAN Junwei | |||
Computer Science and Technology 24 April 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Recognizing the emotion embedded in the video provides another way to classify media and supplies accurate videos that users really want. Hence, effective techniques for video emotion recognition are highly required. This paper proposes a novel framework for video emotion recognition by integrating textual feature extracted from video subtitles, audio and visual features embedded in video content. Firstly, high-level dialogic semantic features are extracted from video subtitles via Natural Language Processing (NLP) technology. These semantic features can represent emotion information by analyzing the concept of video dialogs rather that simple analysis of words. It is also more practical to extract high-level features from large number of video than to extract physiological signals in implicit tagging from participants. Secondly, a multimodal Deep Boltzmann Machine (DBM) is adopted to learn a joint representation from audio feature, visual feature and textual semantics feature. Considering some dialogs or subtitles may be absent in some videos, this model has ability to predict the joint representation without textual semantics. Finally, the joint representations are inputted into Support Vector Machine (SVM) for video emotion classification and regression. Our experimental results on the open database show the effectiveness of our framework. | |||
TO cite this article:LI Chao,CHENG Gong,HAN Junwei. Video Emotion Recognition Using Subtitles Semantics, Audio and Visual Features[OL].[24 April 2017] http://en.paper.edu.cn/en_releasepaper/content/4728732 |
6. Design and Implementation of Big Data Processing Platform Based on SCA and Spark | |||
Zhou Yongjiang,Zhang Yang | |||
Computer Science and Technology 27 December 2016 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the rapid development of computer technology, electronic information technology and network technology, the traditional data processing method based on web service has become difficult to meet the demand of big data. On the other hand, big data software needs to be reconstructed, They can`t reuse the existing business logic. Apache Spark is an open source cluster computing technology specifically designed for large scale data processing. Tuscany is a framework of SCA. The paper introduces a system to combine Spark and Tuscany to calculate the complex logic fleetly. At the same time, the system provide a friendly user interface to data analysis. | |||
TO cite this article:Zhou Yongjiang,Zhang Yang. Design and Implementation of Big Data Processing Platform Based on SCA and Spark[OL].[27 December 2016] http://en.paper.edu.cn/en_releasepaper/content/4713662 |
7. Smart-phone-assisted Human Motion Recognition Based on Wavelet Transform | |||
Tian Yaning,Yin Sixing,Qu zhaowei | |||
Computer Science and Technology 03 November 2016 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Human motion recognition is becoming a research upsurge, which aims at understanding human behavior, and plays an increasingly important role in a number of applications, such as health care and smart home. In this paper, we collect datasets by using the built-in sensors of a mobile phone and propose an approach to extract features based on wavelet transform. In contrast to the existing related works, our work intends to recognize the physical activities when the phone's orientation and position are varying. The activities' true acceleration is inferred by using the phone's pitch, yaw and roll angles. After preprocessing, the continuous original time series data is segmented into discrete training samples by the sliding windows of proper size. Then statistical features such as wavelet coefficients are extracted through the wavelet transform. Support Vector Machine (SVM) is employed as classifier to recognize five types of motion: jumping, walking, running, stepping upstairs and stepping downstairs. We find a proper wavelet basis function to extract the features and achieve an average recognition accuracy of 90.71%. We can distinguish the five kinds of motion clearly, so the results show that it is feasible to use wavelet transform to extract features in human motion recognition. | |||
TO cite this article:Tian Yaning,Yin Sixing,Qu zhaowei. Smart-phone-assisted Human Motion Recognition Based on Wavelet Transform[OL].[ 3 November 2016] http://en.paper.edu.cn/en_releasepaper/content/4708069 |
8. Adaptive Clustering Algorithm based small Group Detection and Tracking | |||
CHENG Zhongbin,ZOU Qi,TIAN Mei | |||
Computer Science and Technology 02 September 2016 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:We propose to detect and track small groups of individuals who are traveling together in surveiuance videos. Coherent groups are dynamically updated through merge and split events. To handle these challenges, we propose to discover groups by adaptive clustering (AGD). Experiments on challenging videos (FM dataset) which have complex motions and occlusions show that the proposed method based on trajectory-level similarity can correctly discover dynamic changes of groups. The effectiveness of the proposed approach is shown through comparison with classical methods. | |||
TO cite this article:CHENG Zhongbin,ZOU Qi,TIAN Mei. Adaptive Clustering Algorithm based small Group Detection and Tracking[OL].[ 2 September 2016] http://en.paper.edu.cn/en_releasepaper/content/4703372 |
9. THE SPARSE REPRESENTATION OF POINT CLOUD AND ITS APPLICATIONS | |||
ZHANG Yong,NI Ping,WU Xin | |||
Computer Science and Technology 13 June 2016 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Point cloud is one of the most important tools for representing geometry in computer vision and computer graphics. In order to represent geometry with high accuracy, point cloud usually has large size and complicated structures, which result in great difficulties in storage, processing and transmission on limited bandwidth. This paper proposes a way to sparsely represent point cloud, consisting of a cluster-based point cloud normalization procedure, dictionary learning under the context of sparse point clouds, and compressing and reconstructing point clouds based on the compressive sensing theory. The method paves the way to effectively represent point clouds. The experimental results not only show feasibility of sparse representation of point clouds but also demonstrate competitive performance in terms of accurate reconstruction. | |||
TO cite this article:ZHANG Yong,NI Ping,WU Xin. THE SPARSE REPRESENTATION OF POINT CLOUD AND ITS APPLICATIONS[OL].[13 June 2016] http://en.paper.edu.cn/en_releasepaper/content/4696958 |
10. A Framework PRAQ of Primitive Shape Extraction for Objects in Point Clouds | |||
Ning Xiaojuan,Li Fan | |||
Computer Science and Technology 05 June 2016 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Shape plays an important role in object recognition and shape modeling. In this paper, we presented a framework to analyze and implement crucial primitive shape extraction including line, plane, cylinder and sphere. In the framework, PCA analysis, RANSAC, Alpha-shape and Quadrants-based methods are investigated and applied to point cloud data, and we could obtain reasonable primitive shape features for further shape modeling. Experimental results demonstrate that our method could deal with different objects with various shapes. | |||
TO cite this article:Ning Xiaojuan,Li Fan. A Framework PRAQ of Primitive Shape Extraction for Objects in Point Clouds[OL].[ 5 June 2016] http://en.paper.edu.cn/en_releasepaper/content/4697032 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
|
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated