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.

Scene-driven Retrieval in Edited Videos using Aesthetic and Semantic Deep Features / Baraldi, Lorenzo; Grana, Costantino; Cucchiara, Rita. - (2016), pp. 23-29. (Intervento presentato al convegno 6th ACM on International Conference on Multimedia Retrieval tenutosi a New York, USA nel 6-9 Giugno 2016) [10.1145/2911996.2912012].

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

BARALDI, LORENZO;GRANA, Costantino;CUCCHIARA, Rita
2016

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.
2016
6th ACM on International Conference on Multimedia Retrieval
New York, USA
6-9 Giugno 2016
23
29
Baraldi, Lorenzo; Grana, Costantino; Cucchiara, Rita
Scene-driven Retrieval in Edited Videos using Aesthetic and Semantic Deep Features / Baraldi, Lorenzo; Grana, Costantino; Cucchiara, Rita. - (2016), pp. 23-29. (Intervento presentato al convegno 6th ACM on International Conference on Multimedia Retrieval tenutosi a New York, USA nel 6-9 Giugno 2016) [10.1145/2911996.2912012].
File in questo prodotto:
File Dimensione Formato  
main.pdf

Open access

Tipologia: Versione originale dell'autore proposta per la pubblicazione
Dimensione 1.2 MB
Formato Adobe PDF
1.2 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1096865
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 8
social impact