DSpace Repository

Video Summarization Using Deep Semantic Features

Show simple item record

dc.contributor.author Otani, Mayu en
dc.contributor.author Nakashima, Yuta en
dc.contributor.author Rahtu, Esa en
dc.contributor.author Heikkila, Janne en
dc.contributor.author Yokoya, Naokazu en
dc.date.accessioned 2018-03-28T05:33:58Z en
dc.date.available 2018-03-28T05:33:58Z en
dc.date.issued 2016-11 en
dc.identifier.isbn 978-3-319-54193-8 en
dc.identifier.uri http://hdl.handle.net/10061/12233 en
dc.description Computer Vision - ACCV 2016: 13th Asian Conference on Computer Vision, Nov 20-24, 2016, Taipei, Taiwan en
dc.description.abstract This paper presents a video summarization technique for an Internet video to provide a quick way to overview its content. This is a challenging problem because finding important or informative parts of the original video requires to understand its content. Furthermore the content of Internet videos is very diverse, ranging from home videos to documentaries, which makes video summarization much more tough as prior knowledge is almost not available. To tackle this problem, we propose to use deep video features that can encode various levels of content semantics, including objects, actions, and scenes, improving the efficiency of standard video summarization techniques. For this, we design a deep neural network that maps videos as well as descriptions to a common semantic space and jointly trained it with associated pairs of videos and descriptions. To generate a video summary, we extract the deep features from each segment of the original video and apply a clustering-based summarization technique to them. We evaluate our video summaries using the SumMe dataset as well as baseline approaches. The results demonstrated the advantages of incorporating our deep semantic features in a video summarization technique. en
dc.language.iso en en
dc.publisher Springer International Publishing en
dc.rights Copyright c 2017 Springer International Publishing ja
dc.title Video Summarization Using Deep Semantic Features en
dc.type.nii Conference Paper en
dc.textversion author en
dc.identifier.spage 361 en
dc.identifier.epage 377 en
dc.relation.doi 10.1007/978-3-319-54193-8_23 en
dc.identifier.NAIST-ID 73298663 en
dc.identifier.NAIST-ID 73292286 en


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account