Showing papers in "IEEE MultiMedia in 2002"
TL;DR: Technologies and applications for video-content analysis and retrieval are surveyed and specific examples of how to manage multimedia data are given.
Abstract: Managing multimedia data requires more than collecting the data into storage archives and delivering it via networks to homes or offices. We survey technologies and applications for video-content analysis and retrieval. We also give specific examples.
342 citations
TL;DR: The article provides a comprehensive overview of MPEG-7's motivation, objectives, scope, and components.
Abstract: The recently completed ISO/IEC, International Standard 15938, formally called the Multimedia Content Description Interface (but better known as MPEG-7), provides a rich set of tools for completely describing multimedia content. The standard wasn't just designed from a content management viewpoint (classical archival information). It includes an innovative description of the media's content, which we can extract via content analysis and processing. MPEG-7 also isn't aimed at any one application; rather, the elements that MPEG-7 standardizes support as broad a range of applications as possible. This is one of the key differences between MPEG-7 and other metadata standards; it aims to be generic, not targeted to a specific application or application domain. The article provides a comprehensive overview of MPEG-7's motivation, objectives, scope, and components.
308 citations
TL;DR: Using WebQEM, a quantitative evaluation strategy to assess Web site and application quality, and an e-commerce case study illustrates the methodology's utility in systematically assessing attributes that influence product quality.
Abstract: This article discusses using WebQEM, a quantitative evaluation strategy to assess Web site and application quality. Defining and measuring quality indicators can help stakeholders understand and improve Web products. An e-commerce case study illustrates the methodology's utility in systematically assessing attributes that influence product quality.
265 citations
TL;DR: A seamless joint querying and relevance feedback scheme based on keywords and lowlevel visual content, incorporating keyword similarities, is used based on a developed algorithm for a learned word similarity matrix.
Abstract: We're interested in using keywords and visual content together in image retrieval. We used a seamless joint querying and relevance feedback scheme based on keywords and lowlevel visual content, incorporating keyword similarities. We developed an algorithm for a learned word similarity matrix and conducted experiments that validated our approach.
191 citations
TL;DR: This work decomposes each shot into its visual and graphic content elements and, by combining several different low-level visual primitives, captures the semantic content at a higher level of significance.
Abstract: Taking into consideration the unique qualities of sports videos, we propose a system that semantically annotates them at different layers of semantic significance, using different elements of visual content. We decompose each shot into its visual and graphic content elements and, by combining several different low-level visual primitives, capture the semantic content at a higher level of significance.
163 citations
TL;DR: In order to evaluate content-based research methodologies, the article considers intended users and whether alternative solutions exist and areas of research.
Abstract: Tools and systems for content-based access to multimedia and-image., video, audio, graphics, text, and any number of combinations-has increased in the last decade. We've seen a common theme of developing automatic analysis techniques for deriving metadata (data describing information in the content at both syntactic and semantic levels). Such metadata facilitates developing innovative tools and systems for multimedia information retrieval, summarization, delivery, and manipulation. Many interesting demonstrations of potential applications and services have emerged-finding images visually similar to a chosen picture (or sketch); summarizing videos with thumbnails of keyframes; finding video clips of a specific event, story, or person; and producing a two-minute skim of an hour-long program. In order to evaluate content-based research methodologies, the article considers intended users and whether alternative solutions exist and areas of research.
113 citations
95 citations
TL;DR: This work bases the first approach on a finite-state machine using low-level motion indices extracted from an MPEG compressed bitstream and innovatively performs semantic indexing through Hidden Markov Models.
Abstract: We propose two approaches for semantic indexing of audio-visual documents, based on bottom-up and top-down strategies. We base the first approach on a finite-state machine using low-level motion indices extracted from an MPEG compressed bitstream. The second approach innovatively performs semantic indexing through Hidden Markov Models.
94 citations
TL;DR: Concept nonperceivable Interpretation perceivable - the role of language and language in decision-making and its applications in science and medicine are studied.
Abstract: ion nonperceivable Interpretation perceivable
74 citations
56 citations
TL;DR: In this article, a virtual orchestra of musicians is used to play with virtual copies of themselves, as if they were there, but without their physical presence, to express their own musical intentions.
Abstract: Playing with musicians, as if they were there, but without their physical presence, is an old and strong fantasy. Indeed, wouldn’t it be nice if you could play with your favorite – but inaccessible Jazz musician? If you could play with him, or rather, like him, but still expressing your own musical intentions? Why not play with a virtual orchestra of musicians? Going further or closer -, what about playing with virtual copies of yourself?
TL;DR: This article focuses on SMIL's textual structure in its various implementation profiles and compares SMIL with other multimedia formats.
Abstract: For pt. 1 see ibid., vol. 8 , no. 4, p. 82-88 (2001). The article is the second part of a two-part series on SMIL 2.0, the newest version of the World Wide Web Consortium's Synchronized Multimedia Integration Language. Part 1 looked in detail at various aspects of the SMIL specification and the underlying SMIL timing model. This part looks at simple and complex examples of SMIL 2.0's use and compares SMIL with other multimedia formats. We focus on SMIL's textual structure in its various implementation profiles.
Journal Article•
TL;DR: This work presents the design and implementation of NetMedia, a middleware that supports client-server distributed multimedia applications that has transmission support strategies and robust software systems at both server and client ends.
Abstract: We present the design and implementation of NetMedia, a middleware that supports client-server distributed multimedia applications. In NetMedia, individual clients may access multiple servers to retrieve customized multimedia presentations. Each server simultaneously supports multiple clients. NetMedia has transmission support strategies and robust software systems at both server and client ends.
TL;DR: A collaborative teaching environment that lets students work through lab-based tutorials with access to a remotely located lecturer via Webcams, email, discussion forums, and chat rooms is presented.
Abstract: This article presents a collaborative teaching environment that lets students work through lab-based tutorials with access to a remotely located lecturer via Webcams, email, discussion forums, and chat rooms. Remote-control software also lets lecturers take control of the students' lab computers to troubleshoot problems. This project aims to facilitate knowledge transfer between students and lecturers.
TL;DR: At the Ars Electronica Festival, a leading confluence of artists, computer scientists, and scientists, people from around the world came to explore the concept of takeover: who is making the Art of tomorrow?
Abstract: At the Ars Electronica Festival, a leading confluence of artists, computer scientists, and scientists, people from around the world came to explore the concept of takeover: who is making the Art of tomorrow? While the implied question wasn't decided in any substantial way, there's no question that the art of tomorrow will often be based on interfaces between humans and computers. If only one irrefutable truth emerged from the often tangled ideas presented, it's that the interface of tomorrow will be substantially different to what we're accustomed to.
TL;DR: A top-down approach to overcome some of the problems of e-commerce data integration and a combined yo-yo approach aims to exploit both strategies' benefits.
Abstract: To make them flexible, scalable, and useable, e-commerce applications require systematic development, including data integration. Traditionally, the integration proceeds in a bottom-up way. This article discusses the problems and proposes a top-down approach to overcome some of the problems. A combined yo-yo approach aims to exploit both strategies' benefits.
TL;DR: Web E-Speak facilitates engineering Web-based e-services by taking into account their requirements for dynamic ad-hoc discovery, secure interaction, and global accessibility.
Abstract: E-Speak, Hewlett-Packard's e-services initiative, is an open, distributed platform that lets e-services dynamically and securely advertise, discover, and interoperate with each other. Web E-Speak, the gateway to E-Speak on the Web, facilitates engineering Web-based e-services by taking into account their requirements for dynamic ad-hoc discovery, secure interaction, and global accessibility.
TL;DR: A case study involving development of a retail sales Web application uses a design model based on object-oriented interface design methods and cognitive science to enhance usability and meet user requirements.
Abstract: Applying software engineering principles to Web application development can improve application quality. A case study involving development of a retail sales Web application uses a design model based on object-oriented interface design methods and cognitive science to enhance usability and meet user requirements.
TL;DR: This GUI-based toolset, in conjunction with an extension of HTML, provides for early usability testing at the onset of Web specification and design activities.
Abstract: The rapid application design and testing (RAD-T) process greatly advances time-driven development of Web applications without sacrificing usability. Our GUI-based toolset, in conjunction with an extension of HTML, provides for early usability testing at the onset of Web specification and design activities.
TL;DR: A multimodal real-time monitoring system called MMM is presented that describes server activity by multi-level representation and supplements traditional ways of conveying sonification and peripheral information to Webmasters.
Abstract: We present a multimodal real-time monitoring system called MMM that describes server activity by multimodal representation and supplements traditional ways of conveying sonification and peripheral information to Webmasters. We also describe a prototype and plug-in that MMM's three-level distributed architecture implements.
TL;DR: This work addresses the systematic development of user interfaces based on 3D graphics and their possible extension to other media and demonstrates their use by describing a virtual training environment called VECWIT (Virtual Environments for Construction Workers' Instruction and Training) that was developed to test the suitability of a VE as a complementary tool supporting education and training for construction workers' safety.
Abstract: Advances in graphic engines and software tools have facilitated the development of visual interfaces based on 3D virtual environments (VEs). These interfaces use interactive 3D graphics to represent visual and spatial information and allow natural interaction with direct object manipulation. Particularly in the training field, interactive 3D graphics offers effective, near-real-world representations, supporting learning-by-doing and case-based reasoning approaches. Although researchers have proposed and practiced many development guidelines on 2D graphical user interfaces, few contributions have addressed the systematic development of user interfaces based on 3D graphics and their possible extension to other media. We've addressed this problem in the construction of several VEs and we've organized our experience in a set of guidelines. We demonstrate their use by describing a virtual training environment called VECWIT (Virtual Environments for Construction Workers' Instruction and Training) that we developed to test the suitability of a VE as a complementary tool supporting education and training for construction workers' safety.
TL;DR: This work presents a low-level estimation method based on simple features tracking as a first step to indexing audio-visual video sequences and uses scale-space blobs to track distinctive tokens, giving priority to temporal structure instead of spatial segmentation.
Abstract: We present a low-level estimation method based on simple features tracking as a first step to indexing audio-visual video sequences. Our method for video motion characterization uses scale-space blobs to track distinctive tokens, giving priority to temporal structure instead of spatial segmentation.
TL;DR: The hypothesis was that these adaptations would let users complete tasks in a shorter time and that this effect would occur whether the adaptations were used individually or together and statistical analysis suggests that there's significant support from the experimental data for the hypothesis.
Abstract: An adaptive Web site molds itself to the user, creating a unique interaction, providing a more enjoyable experience, and increasing the success of an interaction. We studied the effect of Web page adaptations on information-finding tasks. Although many user interface components, such as page content and Web links, can be altered to produce adaptations, we limited our work exclusively to altering color and layout. The hypothesis we studied in our research was that these adaptations would let users complete tasks in a shorter time and that this effect would occur whether the adaptations were used individually or together. We designed a Web-based experiment that required each subject to answer three questions. The subjects could find the answer for each by searching through a local copy of a portion of IBM's 2000 Sydney Olympics Web site. Our experiments involved 128 student participants from WPI. To focus on the effects of the adaptations, we used predetermined adaptations, creating a set of static Web sites containing all the adaptations we planned to study. To reduce the potential effects of learning and to compensate for adaptation order, we kept the experiment brief and used a balanced experimental design. Statistical analysis suggests that there's significant support from the experimental data for the hypothesis.
TL;DR: This work proposes an abstract model for information sharing and integration and uses it to develop an architecture for building open, component-based, interoperable systems.
Abstract: The volume and number of data sets about Earth are rapidly growing. However, sharing and integrating them is difficult due to incompatible data formats and platforms. We propose an abstract model for information sharing and integration and use it to develop an architecture for building open, component-based, interoperable systems.
TL;DR: This work focuses on the copyright management of Secure MultiMediaCards (SecureMMCs) to handle users' access to digital copyrighted data in a unique scheme called Super Distribution, which can build legitimate peer-to-peer systems where copyrighted data are freely copied and exchanged, but users must obtain the right to use the data.
Abstract: We need a robust method to assure secure storage, retrieval, and transmission of such digital data, especially for mobile devices. This has become more apparent after hearing the high-profile story of Napster. This new type of music delivery service brought up issues of how to protect copyrighted data, particularly in the new generation of peer-to-peer distribution schemes. Furthermore, the rapid penetration of mobile phones worldwide suggests that downloading copyrighted data onto these portable devices is possible around the clock at any place. I primarily focus on the copyright management of Secure MultiMediaCards (SecureMMCs) to handle users' access to digital copyrighted data in a unique scheme called Super Distribution. Using SecureMMCs, Super Distribution technology can build legitimate peer-to-peer systems where copyrighted data are freely copied and exchanged, but users must obtain the right to use the data. Users may then be charged to reimburse the copyright holders. I also discuss Keltaide-Music, a mobile phone music distribution service using SecureMMCs.
TL;DR: This work studies the link validity of a Web site's navigational structure to enhance Web quality by employing the principle of statistical usage testing to develop an efficient and effective testing mechanism.
Abstract: We study the link validity of a Web site's navigational structure to enhance Web quality. Our approach employs the principle of statistical usage testing to develop an efficient and effective testing mechanism. Some advantages of our approach include generating test scripts systematically, providing coverage metrics, and executing hyperlinks only once.