A Novel Shopping Protocol for Ubiquitous Commerce

Due to the prosperity of ubiquitous computing and mobile communication technologies, the traditional commerce will start changing drastically. A shopping model has shown how the customers make a purchase from before-shopping to post-shopping through a ubiquitous device. However, the ubiquitous computing system gathers the sensitive personal information such as location and credit card information. Therefore, security and privacy have become important issues which should be taken into account in the system. In order to solve these problems, this paper tries to design a helpful and secure ubiquitous shopping protocol which is combined with the shopping model to make it practical, secure, and convenient.     

一种新闻视频文本语义信息提取与分析的新方法

本文提出一种视频文本语义信息分析的新思路,即在文本区域提取后结合文种识别理论来提取新闻视频的来源和身份等高级语义信息,同时文种识别结果可为OCR的选择提供先验知识。主要工作包括:1)针对视频中的字幕,提出一种基于时-空分析的算法来检测视频中的字幕,然后对检测到的字幕通过投影分析进行定位、增强和二值化;2)对提取到的文本区域提出一种基于PCA和小波变换的文种识别算法。     

Next-Generation Multimedia Database Retrieval [review of Multimedia Database Retrieval: A Human-Centered Approach by Muneesawang, P. and Guan, L.; 2006]

The authors review a book that offers a human-centered approach on next-generation multimedia database retrieval.     

基于内容的多媒体信息检索

较系统地介绍了基于内容的多媒体检索技术。对于基于内容的视频检索技术，介绍了基于内容的视频处理、视频检索的方式和ML算法在视频检索中的应用。此外，还介绍了基于内容的压缩方法MPEG-4、MPEG-7、MPEG-21等。     

A Scheme for Intelligent Image Retrieval in Multimedia Databases

Storage and retrieval of visual data play an important role in multimedia systems. We have developed a content-based scheme for retrieving images from multimedia databases intelligently. The retrieval takes two stages. The first stage retrieves an image based on partial information. In the second stage, the system accumulates knowledge from the results of the first-stage retrieval. It analyzes the subspace of features from the resulting images and tries to understand the query request. It also makes full use of the entire index space, although queries can be made on partial information. The technology developed will find many applications in multimedia areas. It will also provide a tool for studying how humans rank the similarity of images and what information people use in visual perception, etc., and will help in the development of methods based on these human approaches.     

Mobile Real-Time Collaboration for Semantic Multimedia

Advanced mobile applications that enable new ways of interaction with digital objects become increasingly important for on-site professional communities. These new ways of interaction, e.g. in Mobile Augmented Reality (MAR) via position and 3D movement, are real needs for fieldwork domains such as cultural heritage management and the construction industry. In addition, on-site professional communities generate shared knowledge bases with multimedia content and semantic annotations through collaboration. However, current MAR applications lack real-time collaboration features. In practice, blending multimedia semantics in mobile real-time collaboration is challenging due to the limitations of mobile devices, the lack of mature dedicated designed communication infrastructures and the constraints of the remote environments. This paper presents a mobile real-time collaboration system for semantic multimedia annotations with augmented reality features. We use XMPP as a real-time protocol for the secure, scalable and interoperable processing of XML-based semantic multimedia metadata described in MPEG-7. Our prototype was evaluated in the digital documentation of historical sites for cultural heritage management. The evaluation results indicate potential for increased productivity and enhanced mutual awareness in on-site professional communities.     

Active Learning for Interactive Multimedia Retrieval

As the first decade of the 21st century comes to a close, growth in multimedia delivery infrastructure and public demand for applications built on this backbone are converging like never before. The push towards reaching truly interactive multimedia technologies becomes stronger as our media consumption paradigms continue to change. In this paper, we profile a technology leading the way in this revolution: active learning. Active learning is a strategy that helps alleviate challenges inherent in multimedia information retrieval through user interaction. We show how active learning is ideally suited for the multimedia information retrieval problem by giving an overview of the paradigm and component technologies used with special attention given to the application scenarios in which these technologies are useful. Finally, we give insight into the future of this growing field and how it fits into the larger context of multimedia information retrieval.     

A Semantic Service Discovery Network for Large‐Scale Ubiquitous Computing Environments

This paper presents an efficient semantic service discovery scheme called UbiSearch for a large‐scale ubiquitous computing environment. A semantic service discovery network in the semantic vector space is proposed where services that are semantically close to each other are mapped to nearby positions so that the similar services are registered in a cluster of resolvers. Using this mapping technique, the search space for a query is efficiently confined within a minimized cluster region while maintaining high accuracy in comparison to the centralized scheme. The proposed semantic service discovery network provides a number of novel features to evenly distribute service indexes to the resolvers and reduce the number of resolvers to visit. Our simulation study shows that UbiSearch provides good semantic searchability as compared to the centralized indexing system. At the same time, it supports scalable semantic queries with low communication overhead, balanced load distribution among resolvers for service registration and query processing, and personalized semantic matching.     

A Human-Centered Multiple Instance Learning Framework for Semantic Video Retrieval

This paper proposes a human-centered interactive framework for automatically mining and retrieving semantic events in videos. After preprocessing, the object trajectories and event models are fed into the core components of the framework for learning and retrieval. As trajectories are spatiotemporal in nature, the learning component is designed to analyze time series data. The human feedback to the retrieval results provides progressive guidance for the retrieval component in the framework. The retrieval results are in the form of video sequences instead of contained trajectories for user convenience. Thus, the trajectories are not directly labeled by the feedback as required by the training algorithm. A mapping between semantic video retrieval and multiple instance learning (MIL) is established in order to solve this problem. The effectiveness of the algorithm is demonstrated by experiments on real-life transportation surveillance videos.      

语义检索技术研究

语义检索是信息检索的一个新的研究方向,已逐渐成为许多领域的有用工具。在介绍语义检索的基本特点以及语义检索的意义的基础上,对现有语义检索的主要思想方法进行了总结,最后对语义检索的发展方向进行了展望。     

A Novel Multiaccess Strategy for Multimedia Wireless LANs

The main focus of the research presented in thispaper is to evaluate how efficiently a commoncommunication medium such as broadcast radio can beshared by a large number of network devices in anin-building environment. The goal is to recommend anoptimal method to fulfil the demanding requirementsdictated by broadband multimedia applications operatingin wireless local area networks. To this end, apractical and efficient multiaccess scheme calledreserved polling is proposed and analyzed.It is shown that the new method is able to handle anintegrated mix of multimedia traffic and operaterobustly in an unreliable wireless transport medium. Ananalytical approach based on queueing theory is employedto gain some insight into the complex behavior of theprotocol. This approach appears to be accurate in predicting its performance for both bursty andperiodic traffic types. The analytical results areverified by network simulation.     

Utilizing Semantic Knowledge for Access Control in Pervasive and Ubiquitous Systems

Controlling access in pervasive environments is crucial and a significant challenge because users and devices can connect from anywhere which results in users and resources becoming available at any point of time and location depending on the situation. Access control policies for this type of environment are required to conform to high-level business notions. In pervasive environments, these high-level notions refer to contexts of the situation which can change unpredictably and must be interpreted semantically to maintain proper access control. Therefore, it is necessary to have a formal representation that represents semantics of the contexts, reflects the change of the situation, and can be shared and understood by a policy system. This paper addresses these issues by introducing a context management system that uses a semantic web approach as an underlying mechanism to model and represent semantics of the contexts. The system stores current contexts in a semantic knowledge base which is used by a semantic access control system in order to form access control policies and evaluate policies at run time. The approach is validated through a proof of concept implementation that includes performance results of the context management system as it responds to a change of the situation.     

Infoshare : Design and Implementation of Scalable Multimedia Signage Architecture for Wireless Ubiquitous Environments

Digital signage systems have found many interesting applications in the realms of advertising, entertainment and education. One of the most prevalent challenging issues faced by current Local Area Network (LAN) based Digital signage network architectures is that their difficulty in porting to wireless ubiquitous environments. While popularity of wireless LANs promotes such architectural improvement, Traditional thin/thick client based architectures suffer inefficiency and scalability issues introduced by use of proprietary signage content formats. Use of such content formats to store signage contents is less optimal since it could lead to content redundancy, difficulty in creating, managing signage contents and scalability issues. As a solution for this issue we propose a Smart Client based digital signage architecture that uses XAML (an XML based declarative GUI language) contents for expressing its signage displays. While Smart Clients can better tolerate communication disruptions which are quite frequent in wireless environments, use of XAML based open content format promotes use of simple tools and variety of devices for signage content creation and management over the Internet in a ubiquitous environment. We successfully applied this generic architecture to a prototype digital signage system called Infoshare and report its robustness in withstanding network disruptions. We evaluate the easiness of editing XAML based signage contents by comparing Infoshare with a popular LAN based digital signage system which uses proprietary content formats. We demonstrate scalability of Infoshare signage service in terms of hardware resources by deploying it in different hardware platforms.     

基于统计机器翻译模型的查询扩展

在搜索引擎等实际的信息检索应用中,用户提交的查询请求通常都只包含很少的几个关键词,这会引起相关文档与用户查询之间的词不匹配问题,对检索性能有较严重的负面影响。该文在分析了查询产生模型的基础上,提出了一种新的基于统计机器翻译的查询扩展方法。通过统计机器翻译模型提取文档集中与查询词相关联的词,用以进行查询扩展。在TREC数据集上的试验结果表明:基于统计翻译的查询扩展方法不仅比不扩展的语言模型方法始终有12%～17%的提高,而且比流行的查询扩展方法-伪反馈也具有可比的平均准确率。     

A Novel Web Image Retrieval Method

Traditional image retrieval methods, make use of color, shape and texture features, are based on local image database. But in the condition of which much more images are available on the internet, so big an image database includes various types of image information. In this paper, we introduce an intellectualized image retrieval method based on internet, which can grasp images on Internet automatically using web crawler and build the feature vector in local host. The method involves three parts: the capture-node, the manage-node, and the calculate-node. The calculate-node has two functions: feature extract and similarity measurement. According to the results of our experiments, we found the proposed method is simple to realization and has higher processing speed and accuracy.     

一种基于区域的动态分块图象检索方法

本文提出一种新颖的基于内容和图像检索方法，基于运动子块分割并根据视觉特性对不同区域做不同的加权，比较各子块相似度，分析相似度矩阵，并检索查询物体。通过将图象分割细化，充分利用了原图的颜色位置信息，通过实验，实现了对特定物体进行检索。该物体检索方法可进一步发展，为特定的后续处理奠定基础，如在人脸识别等功能中发挥重要作用。     

VideOlympics: Real-Time Evaluation of Multimedia Retrieval Systems

The first VideOlympics brings content-based analysis to the archive and allows for many-to- many communication between video search engines and their audience It was a great Success. The VideOlympics provided the excitement of a competition without the associated stress on the participants. For the first time, the audience was able to compare different multimedia retrieval systems on the same tasks and see how they performed with unrehearsed topics. Many audience members felt they understood the technology's capabilities after seeing it in live action and in several system variations.     

A Novel Probability-Based Handoff Strategy for Multimedia LEO Satellite Communications

A novel bandwidth allocation strategy and a connection admission control technique arc proposed to improve the utilization of network resource and provide the network with better quality of service （QoS） guarantees in multimedia low earth orbit （LEO） satellite networks. Our connection admission control scheme, we call the probability based dynamic channel reservation strategy （PDR）, dynamically reserves bandwidth for real-time services based on their handoff probability. And the reserved bandwidth for real-time handoff connection can also be used by new connections under a certain probability determined by the mobility characteristics and bandwidth usage of the system. Simulation results show that our scheme not only lowers the call dropping probability （CDP） for Class I real-time service but also maintains the call blocking probability （CBP） to certain degree. Consequently, the scheme can offer very low CDP for rcal-time connections while keeping resource utilization high.