|:: Fakulteta za elektrotehniko :: Laboratorij za digitalno obdelavo signalov, slik in videa|
|:: Andrej Košir :: Matevž Kunaver ::|
Recently, the fast growing capabilities of communication technologies (communication channel and storage capacities, displays, mobile terminals etc) have led to more and more complex products and services offered to the users. On the other hand, most users of communication devices are no longer communication experts. The focus of research community to tackle this problem is almost exclusively set to the concept of personalization based on a user modeling procedures. The major difficulty of user modeling procedures is the required input data about the modeled user. Studies and practical experiences show that, on one hand, the efficiency of user modeling relies on acquired data about the user, and on the other hand, it is extremely irritating for user to constantly provide such data about her or his feelings and behavior. Therefore there is a need for non-intrusive and non-irritating data collection about the user. Among other approaches such as distributed sensors, this can be achieved by a real time analysis of a video capturing the user behavior with the intention of identifying specific information about her or his behavior.
Our research focus on a design and implementation of new approaches in content based and colaborative user modeling procedures. We proposed to use affective parameters in a content-based recommender algorithm (CBR) for multimedia content. We proposed to model the end users with parameters describing the affective response of the user during content consumption.
|© copyright 2014 - Laboratorij za digitalno obdelavo signalov, slik in videa. Vse pravice pridržane.|
Laboratorij za digitalno obdelavo signalov, slik in videa, Fakulteta za elektrotehniko, Univerza v Ljubljani
Tržaška 25, SI-1000 Ljubljana, Slovenija, telefon: +386 1 4768 492, telefaks: +386 1 4768 855.