In this paper we explore the idea of using high-level semantic concepts, also called attributes, to represent human actions from videos and argue that attributes enable the constr...
Citizen Energy is a novel, participatory citizen engagement with energy that is designed to extend our relationship with energy beyond existing producerconsumer models towards one...
This paper discusses a hybrid approach for the multi-channel source separation, where both a time-frequency (t-f) mask and a multichannel Wiener filter (WF) are utilized. T-f mas...
Conditional Random Fields (CRFs) have proven to perform well on natural language processing tasks like name transliteration, concept tagging or grapheme-to-phoneme (g2p) conversio...
This paper presents a new method for extracting orthogonal bases from AM-FM signals. Since AM-FM signals are non-stationary, appropriate basis functions are sought provided that i...