Abstract. Can we discover audio-visually consistent events from videos in a totally unsupervised manner? And, how to mine videos with different genres? In this paper we present our...
We present a new method for automatically filling in gaps of textural sounds. Our approach is to transform the signal to the time-frequency space, fill in the gap, and apply the i...
Recognition of human gestures is important for analysis and indexing of video. To recognize human gestures on video, generally a large number of training examples for each individu...
A key aspect of semantic image segmentation is to integrate local and global features for the prediction of local segment labels. We present an approach to multi-class segmentatio...
To find how many clusters in a sample set is an old yet unsolved problem in unsupervised clustering. Many segmentation methods require the user to specify the number of regions in...