Ecole d'ingénieur et centre de recherche en Sciences du numérique

Multimedia maximal marginal relevance for multi-video summarization

Li, Yingbo; Merialdo, Bernard

Multimedia Tools and Applications, January 2016, Vol. 75, N°1, ISSN: 1380-7501

In this paper we propose several novel algorithms for multi-video summarization. The first and essential 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. 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 and suitable for summarizing various video genres in multi-video set by using multimodal information. Our series of MMR algorithms for multi-video summarization are proved to be effective by the large-scale subjective and objective evaluation.

Document Doi Bibtex

Titre:Multimedia maximal marginal relevance for multi-video summarization
Mots Clés:Multi-video summarization, Video summaries, MMR, Video-MMR, AV-MMR, Balanced AV-MMR
Type:Journal
Langue:English
Ville:
Date:
Département:Data Science
Eurecom ref:4416
Copyright: © Springer. Personal use of this material is permitted. The definitive version of this paper was published in Multimedia Tools and Applications, January 2016, Vol. 75, N°1, ISSN: 1380-7501 and is available at : http://dx.doi.org/10.1007/s11042-014-2287-5
Bibtex: @article{EURECOM+4416, doi = {http://dx.doi.org/10.1007/s11042-014-2287-5}, year = {2016}, month = {01}, title = {{M}ultimedia maximal marginal relevance for multi-video summarization}, author = {{L}i, {Y}ingbo and {M}erialdo, {B}ernard}, journal = {{M}ultimedia {T}ools and {A}pplications, {J}anuary 2016, {V}ol. 75, {N}°1, {ISSN}: 1380-7501}, url = {http://www.eurecom.fr/publication/4416} }
Voir aussi: