English

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

Computer Vision and Pattern Recognition 2016-04-12 v1 Information Retrieval Multimedia

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.

Keywords

Cite

@article{arxiv.1604.02546,
  title  = {Scene-driven Retrieval in Edited Videos using Aesthetic and Semantic Deep Features},
  author = {Lorenzo Baraldi and Costantino Grana and Rita Cucchiara},
  journal= {arXiv preprint arXiv:1604.02546},
  year   = {2016}
}

Comments

ICMR 2016

R2 v1 2026-06-22T13:28:32.557Z