| 研究実績の概要 |
We suggested the TRACE framework to automatically perform such a video segmentation based on a linguistic approach using Wikipedia texts. TRACE has two main contributions: 1. the extraction of a novel linguistic-based Wikipedia feature to segment lecture videos efficiently, and 2. the investigation of a late fusion of video segmentation results derived from state-of-the-art algorithms. This work has been published in ISM 2015 [3].
We proposed the Videopedia system that seamlessly integrates both the text-based blogs and online videos and recommends relevant videos for explaining the concepts given in a blog. Our algorithm uses content extracted from video transcripts generated by closed captions. We use Latent Dirichlet Allocation (LDA) to map videos and blogs in the common semantic space of topics. After matching videos and blogs in the space of topics, videos with high similarity values are recommended for the blogs. This work has been published in MMM 2016 [2].
We proposed a fuzzy clustering approach for lecture videos based on topic modeling. Our novel algorithm uses topic modeling on video transcripts generated by automatic captions to extract the contents of these videos. We choose representative text documents for each of the clusters from the Wikipedia. The results are plausible and confirm the effectiveness of the proposed scheme, which have been accepted by conference CBMI 2016 [1].
|
