Definition: High-level concept detection is the process within which the high-level concepts or objects which are presented in a multimedia document are determined. For example, given an image, a detection scheme would reply that it contains concepts such as “sky”, “sand”, “sea”, the image depicts an “outdoor” and more specifically a “beach” scene. In some cases, the actual position of concepts...

This paper discusses a new design of chattering reduction for sliding mode control. Conventionally, a boundary layer around the sliding surface is used to achieve smooth control signals. However, the boundary layer design become in-effective in chattering reduction when there is high-level measurement noise. To solve this problem, this paper proposes a dynamic sliding mode control, which, with ...

Problem Task: combining multiple types of features for music classification from raw audio signals • Whether-we need multiple features? • How-to combine different features? • What-is the best feature and combination scheme? Features Taxonomy of audio features • Timbre features capture the quality of the sound and has much to do with the instrumentation of the music. • Temporal features capture ...

" This thesis is dedicated to my parents, Erica and all my dear friends. It wouldn't be possible to finish it without all the love I have received. " Acknowledgements The author wishes to thank: (i) Prof. Luca Benini for his high-level supervision and continuous support, in that no knowledge is possible without a master to follow; (ii) Ing.tino Ruggiero for his sincere friendship; (iii) All the...

This paper proposes a method for extracting high-level rules for expository dialogue generation. The rules are extracted from dialogues that have been authored by expert dialogue writers. We examine the rules that can be extracted by this method, focusing on whether different dialogues and authors exhibit different dialogue styles.