pith. sign in

arxiv: 1604.02546 · v1 · pith:IHRMWZIGnew · submitted 2016-04-09 · 💻 cs.CV · cs.IR· cs.MM

Scene-driven Retrieval in Edited Videos using Aesthetic and Semantic Deep Features

classification 💻 cs.CV cs.IRcs.MM
keywords deepeditedretrievalvideosfeaturesqueryretrievescenes
0
0 comments X
read the original abstract

This paper presents a novel retrieval pipeline for video collections, which aims to retrieve the most significant parts of an edited video for a given query, and represent them with thumbnails which are at the same time semantically meaningful and aesthetically remarkable. Videos are first segmented into coherent and story-telling scenes, then a retrieval algorithm based on deep learning is proposed to retrieve the most significant scenes for a textual query. A ranking strategy based on deep features is finally used to tackle the problem of visualizing the best thumbnail. Qualitative and quantitative experiments are conducted on a collection of edited videos to demonstrate the effectiveness of our approach.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.