Multimedia maximal marginal relevance for multi-video summarization

In this paper we propose several novel algorithms for multi-video summarization. The first and basic algorithm, Video Maximal Marginal Relevance (Video-MMR), mimics the principle of a classical algorithm of text summarization, Maximal Marginal Relevance (MMR). Video-MMR rewards relevant keyframes and penalizes redundant keyframes, only relying on visual features. We extend Video-MMR to Audio Video Maximal Marginal Relevance (AV-MMR) by exploiting audio features. Consequently, we also propose Balanced AV-MMR, which exploits additional semantic features, the balance between audio information and visual information, and the balance of temporal information in different videos of a set. The proposed algorithms are generic for various video genres, designed to summarize multi-video and using multimodal information in the video. Our series of MMR algorithms in video summarization are proved to be effective for summarizing multi-video by large-scale experiments. Keywords Video summarization...

• Type: Journal
• Year: 2016
• Where: MTA
• Authors: Yingbo Li, Bernard Mérialdo
• Keywords: Hardware, MTA 2016