Conference Paper

MobiCon: integrated capture, annotation, and sharing of video clips with mobile phones.

DOI: 10.1145/1101149.1101321 Conference: Proceedings of the 13th ACM International Conference on Multimedia, Singapore, November 6-11, 2005
Source: DBLP

ABSTRACT This paper presents MobiCon, a video production tool for mobile camera phones. MobiCon integrates video clip capture with context-aware, personalized clip annotation -- supporting automatic annotation suggestions based on context data and efficient manual annotation with user-specific ontologies and keywords -- and clip sharing secured by digital rights management techniques. Thus, MobiCon allows users to inexpensively create metadata-annotated video clips for a better management of their clip collections and keeps them in control of the clips they share.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Beeldmateriaal speelt een steeds grotere rol in onze cultuur, maar ook in de wetenschap en in het onderwijs. Zoeken in grote collecties beeldmateriaal blijft echter een moeizaam proces. Het kost een eindgebruiker veel tijd en moeite om juist dat ene beeld te vinden. Daarom zijn er efficiënte zoekmethoden nodig om de groeiende collecties doorzoekbaar te maken en te houden. Laura Hollink onderzoekt de problemen bij het zoeken naar beeldmateriaal en de mogelijke oplossingen daarvoor, in drie uiteenlopende collecties: schilderijen, foto’s van organische cellen en nieuwsuitzendingen.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this work we present a novel video annotation and media enrichment methodology for enhanced visual communication among first responders (FRs) and their command centers complementing voice communications in order to overcome current shortcomings of the latter. For this purpose, an initial taxonomy of emergency cases and sub-cases handled by a variety of FR teams has been defined along with a core set of associated rich media annotation templates to enrich captured video footage with commonly-agreed alert signs and messages. The primary aim is to define a fully-functional, extensible and self-descriptive visual language for fast and self-explanatory emergency communication. FRs on site equipped with mobile devices (PDAs) are able to quickly author content enriched video alerts to effectively communicate the arisen situation to their Command centers using the subsequently proposed video annotation prototype. Both qualitative and quantitative system evaluation in lab tests and field trials with the participation of real end users prove the effectiveness of the proposed system.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The increasing ubiquity of networked mobile computing devices such as cell phones and PDAs has created opportunities for the transmission and display of multimedia content. However, such mobile devices have inherent resource constraints: low network bandwidth, small screen size, limited input methods and low commitment viewing. Therefore, a mobile platform requires systems and applications for information display and access to mitigate these various constraints and further complicates their design. To facilitate access to news video on mobile devices, a coordinated design approach is taken, considering various system perspectives. The goal is to provide a cognitively palatable stream of videos and a seamless and low latency user experience through the use of an adaptive mixed- initiative interface to solicit user relevance feedback, and content retrieval integrated with client-side content aware prefetching. These various components are otherwise usually considered independently in the system design. The experiments suggest that this approach is helpful for recommending news video content on a mobile device, and areas for future investigation are outlined. The contributions of this paper are: (1) a mixed-initiative user interface design for small devices integrated with a content recommendation strategy that harnesses user relevance feedback; (2) coupled with the design and implementation of a content-aware prefetching scheme for videos, using the abovementioned feedback to lower the user perceived latency on the client-end; and (3) overall coordinated system design, with a quantitative evaluation of the tradeoffs between bandwidth, semantic relevance and user perceived latency.
    Southeastcon, 2009. SOUTHEASTCON '09. IEEE; 04/2009

Full-text (2 Sources)

Available from
May 21, 2014