Interactive components for visual exploration of multimedia archives

Abstract

With the increase of online resources, one main challenge for multimedia content providers is to provide efficient and user friendly tools for a deep and shallow navigation adapted to large scale audiovisual content. This paper describes a generic framework to build visual interactive applications the objectives of which are to enhance the understanding and to allow easy access to multimedia resources and management. Visual Maps are built on multi-modal similarity matrices computed from automatically extracted descriptors and use graph clustering and layout methods. Active relevance feedback methods are applied to allow users to control the maps evolution according to their needs. The First results of users' evaluation are presented for one of our tools.

Towards interactive, intelligent, and integrated multimedia analytics

“…Intermediate Advanced I-SI [85] Newdle [93] sVisit [56] Informedia [33] Canopy [8] Similiarity browser [61] INA browser [81] MediaTable [19] [20] semantic gap pragmatic gap Fig. 8.…”

“…This approach employs a similarity space browser through which the user directly manipulates the similarity space, with the machine recomputing the used similarity and rearranging the items based on the interactions. The last example of an early adopter is the multimedia browser developed for the French Audiovisual Institute (INA) by Viaud et al [81] This approach combines a similarity space browser, visual summary techniques, and active learning for interactive exploration of the French TV archives.…”

Ten Research Questions for Scalable Multimedia Analytics

“…This applies both to the model described above, as well as to the pioneer systems conceived so far (e.g., [1,11]). As Figure 4(a) indicates, data is only present in main memory, which limits the scale of the systems both in data volume and duration and makes the data processing ad hoc for each respective multimedia analytics system.…”

Video Interaction Tools

“…For a news video this results in a visualization where the whole news show is presented via keyframes from left to right and each news story is presented as vertical loop of keyframes. This idea was already proposed by the same authors in an earlier work [Viaud et al 2008], which already includes first ideas for the Collection Explorer that was further extended in Viaud et al [2010]. This tool visualizes the whole video collection as a clustered map based on graph models that consider the manual annotations of all videos in the collection.…”