In music information retrieval (MIR), there are two main research directions, which are based either on a folder hierarchy and metadata, or on the actual acoustic content. We beli...
In this paper, a video segmentation algorithm based on Hidden Markov Model classifier with multimodal feature is proposed. By using Hidden Markov Model classifier with both audio a...
In the domain of candidly-captured student presentation videos, we examine and evaluate approaches for multimodal analysis and indexing of audio and video. We apply visual segment...
This paper investigates the semantic analysis of broadcast tennis footage. We consider the spatio-temporal behaviour of an object in the footage as being the embodiment of a seman...
Abstract. This paper presents Textable Movie, an open-ended interface that allows anyone to become "video-jockey." In the framework of computational storytelling, Textabl...