Visualization

The visualization of the results of multimedia search engines assists the users significantly in exploring large multimedia datasets. With the abundance of multimedia content in the Internet, there is a growing need for effective techniques to visualize data collections, where the data items consist of multiple media types, or modalities: images, sounds, videos, text etc. Moreover, multiple contextual characteristics extracted from the media, such as ones assessing their accessibility regarding various sensory impairments, can be utilized to provide a personalized search experience. 

In this context, a core research area of the group is the visualization of multimodal data of multimedia datasets, with applications in multimodal search engines. The research includes graph-based visualization methods, combination of modalities using weighted-sum techniques and multi-objective optimization. On top of this, exploitation of user feedback via novel Pareto based approaches towards the learning of preferred trade-off among the modalities and the personalized preferences is achieved. Applications include visualization of multimedia datasets consisting of diverse data types, such as images, sounds and text, and visualization and re-ranking of search results, using accessibility features of the multimedia as modalities.

visualization

Visual Analytics in Multimodal Search

 

visualization

Visual Analytics in multimodal profile-based quering

 

Relevant Projects: Vis-SENSE (FP7), CUBRIK (FP7), NEMESYS (FP7)

Relevant publications:

  1. I.Kalamaras, A. Drosou, & D. Tzovaras, “Multi-objective optimization for multimodal visualization”. IEEE Transactions on Multimedia, accepted with minor corrections.
  2. I. Kalamaras, A. Mademlis, S. Malassiotis & D. Tzovaras. “A novel framework for retrieval and interactive visualization of multimodal data”, Electronic Letters on Computer Vision and Image Analysis, vol.12, no.2, pp. 28-39, 2013.
  3. I. Kalamaras, A. Mademlis, S. Malassiotis & D. Tzovaras, “A novel framework for multimodal retrieval and visualization of multimedia data”. Analysis (CCA), vol.4, no.5, 2012
  4. E. Biersack, Q. Jacquemart, F. Fischer, J. Fuchs, O. Thonnard, G. Theodoridis, D. Tzovaras, P.-A. Vervier, “Visual analytics for BGP monitoring and prefix hijacking identification”, Special Issue on Computer Network Visualization, IEEE Network Magazine, Nov. 2012
  5. O. Tsigkas, O. Thonnard &D. Tzovaras, “Visual Spam Campaigns Analysis Using Abstract Graphs Representation ", 9th Symposium on Visualization for Cyber Security (VizSec 2012).
  6. S. Papadopoulos, K. Moustakas, D. Tzovaras, ”Hierarchical Visualization of BGP Routing Changes Using Entropy Measures”, 8th International Symposium on Visual Computing, July 16- 18, 2012 
  7. S. Papadopoulos, K. Moustakas, D. Tzovaras, ”BGPViewer: Using Graph representations to explore BGP routing changes”, 18th International Conference on Digital Signal Processing (DSP), 1-3 July 2013 
  8. S. Papadopoulos, G. Theodoridis, D. Tzovaras, ”BGPfuse: Using visual feature fusion for the detection and attribution of BGP anomalies”, 10th Symposium on Visualization for Cyber Security (VizSec), October, 2013 
  9. S. Papadopoulos and D. Tzovaras, "Towards Visualizing Mobile Network Data", in Proc. 28th Int. Symp. on Computer and Information Sciences (ISCIS’13), Oct. 2013.

View Related Demos