Multimedia Knowledge and Social Media Analytics Laboratory

Interactive multimedia search and knowledge retrieval

Description:

Nowadays, the proliferation of content due to the internet penetration and the easy creation of user-generated content have raised the need for the research and development of efficient search and retrieval techniques. Depending on the application, there is a need for the research and development of information retrieval techniques that deal with browsing and search of heterogeneous multimedia, web search and crawling, multimodal fusion of information, as well as knowledge extraction.

In this context MKLab exhibits research in the following directions of information retrieval with a special emphasis on multimedia:

  • Implementation of interactive multimedia retrieval search engines with advanced visualization interfaces for exploratory search and browsing that combine content and visual concept-based retrieval methods. Applications on patent image search and generic content image and video retrieval.
  • Research and development of multimodal search techniques based on fusion of multiple modalities by employing supervised machine learning and reranking techniques.
  • Topic and event detection for indexing and retrieval based on machine learning techniques.
  • Research and development of domain-specific search techniques based on query rewriting, expansion, web crawling and supervised machine learning. Application on environmental and forensic data.
  • Research on question answering techniques based on passage retrieval and semantic knowledge extraction for the development of multilingual dialogue systems.
Key Publications: 

S. Vrochidis, I. Patras and I. Kompatsiaris, "Gaze Movement-driven Random Forests for Query Clustering in Automatic Video Annotation", Multimedia Tools and Applications, 2016.

T. Tsikrika, A. Moumtzidou, S. Vrochidis and I. Kompatsiaris, Focussed Crawling of Environmental Web Resources Based on the Combination of Multimedia Evidence, Multimedia Tools and Applications, May 2015, pp 1-25, doi: 10.1007/s11042-015-2624-3

L. Johansson, V. Epitropou, K. Karatzas, A. Karppinen, L. Wanner, S. Vrochidis, A. Bassoukos, J. Kukkonen, I. Kompatsiaris, "Fusion of meteorological and air quality data extracted from the web for personalized environmental information services", Environmental Modeling and Software Journal, 2015, Volume 64, February 2015, pp. 143–155, doi: 10.1016/j.envsoft.2014.11.021

G. Meditskos, S. Dasiopoulou, S. Vrochidis, L. Wanner, I. Kompatsiaris, "Question Answering over Pattern-Based User Models", In Proceedings of the 12th International Conference on Semantic Systems (SEMANTiCS 2016), pp. 153-160. ACM, New York, NY, USA, 2016 DOI: http://dx.doi.org/10.1145/2993318.2993331

C. Iliou, G. Kalpakis, T. Tsikrika, S. Vrochidis, I. Kompatsiaris, "Hybrid Focused Crawling for Homemade Explosives Discovery on Surface and Dark Web", 11th International Conference on Availability, Reliability and Security (ARES 2016), Salzburg, Austria, Aug 2016 (accepted for publication) 
 

G. Kalpakis, T. Tsikrika, C. Iliou, T. Mironidis, S. Vrochidis, J. Middleton, U. Williamson, I. Kompatsiaris, "Interactive Discovery and Retrieval of Web Resources Containing Home Made Explosive Recipes", 4th International Conference on Human Aspects of Information Security, Privacy and Trust, Toronto, Canada, 17 - 22 July 2016.

I. Gialampoukidis, S. Vrochidis, I. Kompatsiaris, "A Hybrid framework for news clustering based on the DBSCAN-Martingale and LDA." Machine Learning and Data Mining in Pattern Recognition, pp. 170-184, Springer International Publishing, 2016.

I. Gialampoukidis, A. Moumtzidou, T. Tsikrika, S. Vrochidis and I. Kompatsiaris, "Retrieval of Multimedia objects by Fusing Multiple Modalities", In Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval, pp. 359-362, ACM.

A. Moumtzidou, T. Mironidis, E. Apostolidis, F. Markatopoulou, A. Ioannidou, I. Gialampoukidis, K. Avgerinakis, S. Vrochidis, V. Mezaris, I. Kompatsiaris, I. Patras, "VERGE: A Multimodal Interactive Search Engine for Video Browsing and Retrieval", Proc. Video Browser Showdown (VBS'16) at the 22nd Int. Conf. on MultiMedia Modeling (MMM'16), Miami, USA, 4 January 2016.