Abstract. Recently researchers have proposed activity recognition methods based on adapting activity knowledge obtained in previous spaces to a new space. Adapting activity knowled...
We design an edge adaptive predictor for lossless image coding. The predictor adaptively weights four directional predictor together with an adaptive linear predictor based on inf...
In this paper we propose a novel general framework for unsupervised model adaptation. Our method is based on entropy which has been used previously as a regularizer in semi-superv...
Ariya Rastrow, Frederick Jelinek, Abhinav Sethy, B...
Polarity lexicons have been a valuable resource for sentiment analysis and opinion mining. There are a number of such lexical resources available, but it is often suboptimal to us...
In this paper we present an algorithm which uses adaptive selection of low-level features for main subject detection. The algorithm first computes low-level features such as contr...