Werner Bailer

May 082012
 

After a successful first event at  MMM 2012 in Klagenfurt, Austria, TOSCA-MP is again co-organising this live video browsing competition in 2013.  The aim of the Video Browser Showdown is to evaluate video browsing tools for their efficiency at “Known Item Search” (KIS) tasks with a well-defined data set in direct comparison with other tools. For each KIS task the searchers need to interactively find a short video clip in a one-hour video file within a specific time limit.

Draft guidelines based on those from 2012 are published and we request feedback until June 15, 2012.  The call for submissions can be found on the MMM 2013 pages.

May 042012
 

Call for Journal Papers: Content Analysis and Indexing for Distributed Multimedia Search & Retrieval in Broadcasting

Multimedia Tools and Applications (Special Issue)

The transition to digital broadcasting and the concomitant raise of new media channels has meant
a significant increase in communication potential for media publishers, which can now leverage
the advantages of online digital technologies to increase the value and attractiveness of their
services, thus gaining renewed value from content.

A side effect of such abundance of content is that consumers are overwhelmed with “information
overload”. In fact, while digital and Internet services are in principle more appealing due to
opportunity they offer to increase the number of thematic channels, the richness of distributed
content and the possibility for the users to interact, on the other side share and contribute as well
as the accessibility of such content still remain mostly unresolved problems.

On the media production side, professionals often experience dual problems in content selection
and organisation for cross-media and interactive productions. The organization of content into
searchable units through the use of flexible and scalable indexing techniques is seen as one
solution to these problems. In addition, it is of paramount importance to develop the ability to
generate, represent and distribute such informational units (e.g., indexes) in a way that is
consumable and manageable by a wide range of end user terminals, and seamlessly integrated
with web services and mobile apps. The implementation of this scenario would give birth to a
new paradigm which would radically overcome the traditional notion of multimedia indexing,
search and retrieval based on bidirectional interactions between users and index servers, paving
the way to an ecosystem in which users of content can at the same time have the role of indexers
and publishers, and where the universe of accessible objects is dynamically changing to meet
usage trends.

We therefore encourage the submission of works addressing single or several components of a
system for the scenario described above. Submissions should discuss one of the following topics,
with a particular emphasis on illustrating the context of the work in such a scenario.

  • Distributed multimedia feature extraction, clustering and classification
  • Distributed architectures for multimedia search
  • Topic and concept detection, categorization, multimedia genre / format characterisation
  • Natural query interfaces (e.g., based on speech or gesture input)
  • Content segmentation and summarization
  • Low complexity algorithms for acoustic, visual, and multimodal indexing
  • Multimodal personality identification (i.e. leveraging multiple sources of information)
  • Visual and acoustic event detection in multimedia
  • Crowd-assisted news production and material selection
  • Context based retrieval and indexing of news content
  • Efficient indexing of live multimedia streams
  • Automated trust estimation, crowd opinion mining
  • Analysis of social network activity about multimedia
  • Multimedia ontologies and tagging
  • HCI for efficient annotation and retrieval
  • Automated cross-media and cross-device linking (incl. multiple screens and control devices)
  • User studies, requirements & trends, standardization
  • Advanced user experience with multimedia

Tentative schedule

Manuscript Due: July 1st, 2012
First Round of Reviews: October 1st, 2012

Editors

Alberto Messina, RAI – Centre for Research and Technological Innovation, Italy; a.messina@rai.it
Andrea Basso, AT&T Labs – Research, USA; basso@research.att.com
Werner Bailer, JOANNEUM RESEARCH, DIGITAL – Institute for Information and Communication Technologies, Austria; werner.bailer@joanneum.at

Mar 072012
 

TOSCA-MP has published a questionnaire to gather information on tasks in media production and their properties. Professionals working in media production are invited to complete the short questionnaire at: http://tosca-mp.eu/tasksurvey/

In order to build models of tasks in the audiovisual media production workflow, we collect information on key tasks in this workflow. The list of tasks is not final, so you are free to add tasks you consider relevant, and describe their properties. The collected information will be used to develop content analysis and search tools that support these tasks and to research benchmarking that assess such tools for their performance in these real-world tasks rather than lab setups.

Jan 312012
 

FIMS (Framework for Interoperable Media Service) is a joint effort of AMWA and the EBU to define an interoperable service oriented architecture for media production. Recently, FIMS has asked for submissions of use cases for phase 2 of FIMS. TOSCA-MP has contributed three use cases:

  • Automated metadata extraction services
  • Media query and search services
  • Benchmarking services for automated metadata extraction and search

The documents submitted to FIMS can be found here.

Jan 152012
 

Participants of Video Browser Showdown at MMM 2012

The Video Browser Showdown (held as a separate session of MMM 2012 in Klagenfurt, Austria) is a live video browsing competition where international researchers, working in the field of interactive video search, evaluate and demonstrate the efficiency of their tools in presence of the audience. The aim of the Video Browser Showdown is to evaluate video browsing tools for their efficiency at “Known Item Search” (KIS) tasks with a well-defined data set in direct comparison with other tools. For each KIS task the searchers need to interactively find a short video clip in a one-hour video file within a specific time limit.

TOSCA-MP provided content collected by its archive partners on the MAMMIE platform and helped running the competition. The two rounds of the competition – one with expert users, the other one with novice users from the audience – brought interesting insights in which types of browsing and interactive search approaches work for which type of content and user.

© 2019 TOSCA-MP - Task-Oriented Search and Content Annotation for Media Production
The research leading to the presented results has received funding from the European Union's
Seventh Framework Programme (FP7/2007-2013) under grant agreement n° 287532. - Imprint