We introduce a new model for extracting classified structural segments, such as intro, verse, chorus, break and so forth, from recorded music. Our approach is to classify signal ...
Samer A. Abdallah, Katy Noland, Mark B. Sandler, M...
We present a method to automatically quantify the local asymmetries of bilateral structures in point clouds. The method relies on the robust computation of the approximate symmetr...
Designing the dialogue policy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a di...
Satinder P. Singh, Diane J. Litman, Michael J. Kea...
Abstract. In this paper we introduce a new representation for shapebased object class detection. This representation is based on very sparse and slightly flexible configurations of...
Aesthetic images evoke an emotional response that transcends mere visual appreciation. In this work we develop a novel computational means for evaluating the composition aesthetic...
Ligang G. Liu, Renjie J. Chen, Lior Wolf, Daniel C...