Showing papers in "IEEE MultiMedia in 2010"
TL;DR: A visual attention index descriptor based on a visual attention model bridges the semantic gap between low-level descriptors used by computers and high-level concepts perceived by humans.
Abstract: A visual attention index descriptor based on a visual attention model bridges the semantic gap between low-level descriptors used by computers and high-level concepts perceived by humans.
84 citations
TL;DR: The query-by-keyword paradigm has emerged due to the desire to search multimedia content in terms of semantic concepts using keywords or sentences rather than low-level multimedia descriptors.
Abstract: Early prototype multimedia database management systems used the query-by-example paradigm to respond to user queries. Users needed to formulate their queries by providing examples or sketches. The query-by-keyword paradigm, on the other hand, has emerged due to the desire to search multimedia content in terms of semantic concepts using keywords or sentences rather than low-level multimedia descriptors. After all, it's much easier to formulate some queries by using keywords. However, some queries are still easier to formulate by examples or sketches-for example, the trajectory of a moving object.
72 citations
TL;DR: The query-by-keyword paradigm has emerged due to the desire to search multimedia content in terms of semantic concepts using keywords or sentences rather than low-level multimedia descriptors.
Abstract: Early prototype multimedia database management systems used the query-by-example paradigm to respond to user queries. Users needed to formulate their queries by providing examples or sketches. The query-by-keyword paradigm, on the other hand, has emerged due to the desire to search multimedia content in terms of semantic concepts using keywords or sentences rather than low-level multimedia descriptors. After all, it's much easier to formulate some queries by using keywords. However, some queries are still easier to formulate by examples or sketches-for example, the trajectory of a moving object.
70 citations
TL;DR: An approach for automatic annotation and retrieval of video content uses semantic concept classifiers and ontologies to permit expanded queries to synonyms and concept specializations.
Abstract: An approach for automatic annotation and retrieval of video content uses semantic concept classifiers and ontologies to permit expanded queries to synonyms and concept specializations.
70 citations
TL;DR: Improvements in haptic channels could lead to even more immersive experiences in high-definition 3D displays and multichannel audio systems.
Abstract: Viewer expectations for rich, immersive interaction with multimedia are driving new technologies- such as high-definition 3D displays and multichannel audio systems-to greater levels of sophistication. While researchers continue to study ways to develop new capabilities for visual and audio sensory channels, improvements in haptic channels could lead to even more immersive experiences.
64 citations
TL;DR: A first-generation, mobile, video-based reminder system offers memory support to those afflicted with mild-stage Alzheimer's disease.
Abstract: A first-generation, mobile, video-based reminder system offers memory support to those afflicted with mild-stage Alzheimer's disease.
47 citations
TL;DR: An ideal application designed to formulate and evaluate decision-making questions should contain realistic modeling, a host of geotagged and time-stamped data sets, and efficient presentation of a basic set of spatiotemporal queries on top of the information-rich virtual geolocation.
Abstract: There is a critical need for advanced geospatial decision-making tools for countless geospatial applications, such as urban planning, emergency response, military intelligence, simulator training, and serious gaming. With the abundance of available geospatial data - such as satellite and aerial imagery - the most effective approach to geospatial decision-making is through sophisticated virtualization. An ideal application designed to formulate and evaluate decision-making questions should contain realistic modeling, a host of geotagged and time-stamped data sets, and efficient presentation of a basic set of spatiotemporal queries on top of the information-rich virtual geolocation.
28 citations
TL;DR: This article presents the integration of an improved camera pose recovery method into a landmark-based visual navigation system for mobile devices.
Abstract: This article presents the integration of an improved camera pose recovery method into a landmark-based visual navigation system for mobile devices.
24 citations
TL;DR: The authors propose a method for embedding a multitone watermark using low computational complexity that can guard against reasonable cropping or print-and-scan attacks.
Abstract: The authors propose a method for embedding a multitone watermark using low computational complexity. The proposed approach can guard against reasonable cropping or print-and-scan attacks.
22 citations
TL;DR: Leveraging large collections of georeferenced, community-contributed photographs can help solve three knowledge-discovery problems: annotating novel images, annotating geographic locations, and performing geographic discovery.
Abstract: Leveraging large collections of georeferenced, community-contributed photographs can help solve three knowledge-discovery problems: annotating novel images, annotating geographic locations, and performing geographic discovery.
20 citations
TL;DR: It's the belief that both traditional and new resources can play an important role if combined successfully in understanding history and help to disseminate part of the authors' legacy by bringing together features from the past into present real-time visualization.
Abstract: Virtual and augmented realities allow creating synthetic worlds not only for simulation purposes, but also for building new environments directly taken from the imagination. Such applications can play an important role in understanding history and help to disseminate part of our legacy by bringing together features from the past into present real-time visualization. Our AR system is easy to use because it's based on simple physical navigation, which means it can be used by all kinds of people, including those who have little or no previous computer knowledge.Our experience shows that the use of such technology doesn't mean that traditional museum pieces and resources are dispensable. An exhibit consisting only of computer technologiesmight not be able to create strong feelings, sensations, and emotions for a particular theme. Guides and ethnographic elements can enrich a museum visit and contribute to more visitor involvement. Therefore, it's our belief that both traditional and new resources can play an important role if combined successfully.
TL;DR: The paper presents a novel solution to the online question-answering problem, and leverages community-contributed text and video answers on the Web.
Abstract: The paper presents a novel solution to the online question-answering problem, leverages community-contributed text and video answers on the Web.
TL;DR: This platform adopts several new approaches, such as combining the use of ontologies and lowlevel context to drive the adaptation decision process, and incorporating multifaceted adaptation tools to provide a wide range of on-the-fly and on-demand adaptation operations to suit various dynamic requirements.
Abstract: This article presents a scalable and modular platform for contextaware adaptation of multimedia content that is governed by digital rights management (DRM). This platform adopts several new approaches, such as (1) combining the use of ontologies and lowlevel context to drive the adaptation decision process, (2) verifying and enforcing usage rights within the adaptation operations, and (3) incorporating multifaceted adaptation tools to provide a wide range of on-the-fly and on-demand adaptation operations to suit various dynamic requirements.
TL;DR: This special issue presents a concise reference of state-of-the-art efforts in the attempts for knowledge discovery in large-scale community-contributed multimedia, and in particular the opportunities and challenges in this nascent arena.
Abstract: This special issue presents a concise reference of state-of-the-art efforts in the attempts for knowledge discovery in large-scale community-contributed multimedia, and in particular the opportunities and challenges in this nascent arena. The guest editors have selected five articles that represent ways to exploit the user-contributed photos and videos for several applications and that identify the theoretical challenges associated with managing such multimedia data.
TL;DR: Challenges addressed in the design of the Wireless Integrated Network Sensors application include issues associated with the data volume, latency, and data synchronization from individually clocked sensors.
Abstract: Editor's NoteResearchers at Kean University describe their experience developing and deploying a real-time environmental monitoring and visualization system using a mesh network of wireless sensors. Challenges they addressed in their design of the Wireless Integrated Network Sensors (WiNS) application include issues associated with the data volume, latency, and data synchronization from individually clocked sensors.-Doree Duncan Seligmann.
TL;DR: Social Surroundings is an application that uses smartphones and online social networks to help eliminate social barriers and encourage natural communication in public places.
Abstract: Social Surroundings is an application that uses smartphones and online social networks to help eliminate social barriers and encourage natural communication in public places.
TL;DR: This intelligent multimedia adaptation and delivery framework tailors to ubiquitous environments, so that users can experience multimedia content using multiple devices in various mobility situations.
Abstract: This intelligent multimedia adaptation and delivery framework tailors to ubiquitous environments, so that users can experience multimedia content using multiple devices in various mobility situations. Multidevice environments offer the potential to enhance the user experience in terms of flexibility and interactivity and will enable novel applications in education, entertainment, collaboration, and communication. We analyzed the different processing steps and defined related framework functionalities such as the generation of the presentation schedule, the computation of the presentation-environment matches, personalization through situation learning, and device(s)-tailored presentation delivery.
TL;DR: The authors point out that, rather than Mark Weiser's predictions of smart personal environments, what the authors have currently are personalized computational devices, for example, smart phones, tied to users rather than embedded in the environment.
Abstract: In this article, Chris Harrison, Jason Wiese, and Anind K. Dey discuss the predictions of Mark Weiser, the father of ubiquitous computing, who envisioned that we would have smart personal environments, with numerous computational devices embedded within each environment. The authors point out that, rather than this happening, what we have currently are personalized computational devices, for example, smart phones, tied to users rather than embedded in the environment. The interesting development of this observation is the crux of their article. Even though multimedia, per se, is not specifically addressed in the article, what the authors have to say is certainly relevant to our community, as smart computational devices and sensors of various sorts are certainly siblings under the skin.-William I. Grosky
TL;DR: A sensor-based camera system associates picture contents with the captured environment to enable semantic content retrieval, interaction, and visualization.
Abstract: A sensor-based camera system associates picture contents with the captured environment to enable semantic content retrieval, interaction, and visualization.
TL;DR: This article presents a system for texture based probabilistic classification and localization of 3D objects in 2D digital images and discusses selected applications.
Abstract: This article presents a system for texture based probabilistic classification and localization of 3D objects in 2D digital images and discusses selected applications.
TL;DR: How ubiquitous video streaming platform can let people enjoy continuous multimedia services at any time, in any location, and with any computing device is discussed.
Abstract: This article discusses how ubiquitous video streaming platform can let people enjoy continuous multimedia services at any time, in any location, and with any computing device. There are several technical challenges to be met in the process of achieving this goal. These challenges entail developing sophisticated session handoff control, session descriptions, communication signaling, and adaptive video streaming, among other factors.
TL;DR: This article outlines a concept based on combining multimedia content analysis and collaborative tagging to enable intuitive, nonlinear access to large video collections of soccer matches.
Abstract: This article outlines a concept based on combining multimedia content analysis and collaborative tagging to enable intuitive, nonlinear access to large video collections of soccer matches.
TL;DR: This article looks at the influence of augmented reality technology on the exploration of real locations through the help of experiential as well as mere informative metadata.
Abstract: This article looks at the influence of augmented reality technology on the exploration of real locations through the help of experiential as well as mere informative metadata.—Frank Nack
TL;DR: This article describes a technique that creates a 3D reconstruction of the ribcage without expensive scanners that could be combined with diagnosis software to help detect lung cancer, to generate 3D size estimates, and to improve visualization of affected regions.
Abstract: To avoid lung disease, regular preemptive screenings are an absolute necessity. This article describes a technique that creates a 3D reconstruction of the ribcage without expensive scanners. One of the major uses of this 3D reconstruction software would be as a medical visualization tool that would show the real shape of a ribcage. This 3D reconstruction method could be combined with diagnosis software to help detect lung cancer, to generate 3D size estimates, and to improve visualization of affected regions.
TL;DR: This article analyzes the present situation's main technological characteristics, its economic implications, and the industry's response-and outlines a possible solution to the problems.
Abstract: The production, distribution, and consumption of information goods have endured numerous challenges over the years. Most recently, the Internet and digital consumer technologies have severely disrupted established intellectual-property regimes, enabling the near costless reproduction and distribution of information commodities. In addition, sophisticated tools have enabled new collaborative spaces (such as blogs, social websites, and so forth) for media production and distribution, posing new challenges to traditional creatorproducer-consumer paradigms. This article analyzes the present situation's main technological characteristics, its economic implications, and the industry's response-and outlines a possible solution to the problems.
TL;DR: A method to estimate the peak signal-to-noise ratio of an image performs more accurately and has a smaller estimation bias and variance compared to the existing methods.
Abstract: A method to estimate the peak signal-to-noise ratio of an image performs more accurately and has a smaller estimation bias and variance compared to the existing methods.
TL;DR: A rate-allocation strategy based on a constrained optimization framework minimizes packet loss caused by wireless environments and network congestion in multihop, wireless ad hoc networks.
Abstract: A rate-allocation strategy based on a constrained optimization framework minimizes packet loss caused by wireless environments and network congestion in multihop, wireless ad hoc networks.
TL;DR: This article describes a standardized packaging format for digital media files that achieves archiving and preservation through a hierarchical file structure and rich contextual information, while preservation is realized by enabling portability in the structure and file attributes.
Abstract: This article describes a standardized packaging format for digital media files. Archiving is accomplished through a hierarchical file structure and rich contextual information, while preservation is realized by enabling portability in the structure and file attributes. Advanced functionality, such as usage governance, is supported by the packaging format.
TL;DR: This article explores near-duplicate Web video detection, video annotation, and video classification using a data-driven framework, by exploiting different aspects derived from contextual and social resources.
Abstract: In this article, we explore near-duplicate Web video detection, video annotation, and video classification using a data-driven framework, by exploiting different aspects derived from contextual and social resources.
[...]
IBM1
TL;DR: DARPA's network challenge to find ten red balloons is inspiring for the multimedia community to imagine the possibilities of automated image searching with real-world scene matching and geolocation capability at a massive scale.
Abstract: DARPA's network challenge to find ten red balloons is inspiring for the multimedia community to imagine the possibilities of automated image searching with real-world scene matching and geolocation capability at a massive scale.