Jun
13
New publications on video analysis research advances in LinkedTV
Leave a comment »
The LinkedTV workpackage on Media Analysis recently reported a number of advances in video analysis technologies. These include the development of elaborate general-purpose dimensionality reduction and machine learning techniques, their application to the problems of video event detection and recounting, the development of new ways for compactly representing video content and their use towards more accurate video concept detection, and the development of a fast and accurate technique for re-detecting known objects in video.
These advances are presented in detailed in several new papers published or accepted in different international journals and conferences, in particular at ICIP 2013 and ICME 2013:
- Nikolaos Gkalelis, Vasileios Mezaris, Ioannis Kompatsiaris, T. Stathaki, “Video event recounting using mixture subclass discriminant analysis”, Proc. IEEE International Conference on Image Processing (ICIP 2013), Melbourne, Australia, September 2013.
- Panagiotis Sidiropoulos, Vasileios Mezaris, Ioannis Kompatsiaris, “Enhancing video concept detection with the use of tomographs”, Proc. IEEE International Conference on Image Processing (ICIP 2013), Melbourne, Australia, September 2013.
- Evlampios Apostolidis, Vasileios Mezaris, Ioannis Kompatsiaris, “Fast object re-detection and localization in video for spatio-temporal fragment creation”, Proc. 1st Int. Workshop on Media Fragment Creation and reMIXing (MMIX’13) at the IEEE Int. Conf. on Multimedia and Expo (ICME 2013), San Jose, CA, USA, 15-19 July 2013.
- Nikolaos Gkalelis, Vasileios Mezaris, Michail Dimopoulos, Ioannis Kompatsiaris, Tania Stathaki, “Video event detection using a subclass recoding error-correcting output codes framework”, Proc. IEEE Int. Conf. on Multimedia and Expo (ICME 2013), San Jose, CA, USA, 15-19 July 2013.
LinkedTV is proud to support, through the EU’s 7th Framework Programme funding, these research advances which contribute greatly to the projects goal of reducing the cost and effort for video owners to conceptually annotate audiovisual material, at increasing scales as faced by broadcasters, archives and many other institutions today.
