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

Multimodal video-to-video linking: Turning to the crowd for insight and evaluation

Eskevich, Maria; Jones, Gareth; Aly, Robin; Ordelman, Roeland; Huet, Benoit

MMM 2017, 23rd International Conference on Multimedia Modeling, January 4-6, 2017, Reykjavik, Iceland / Also published in LNCS, Vol.10133/2017

Video-to-video linking systems allow users to explore and exploit the content of a large-scale multimedia collection interactively and without the need to formulate specific queries. We present a short introduction to video-to-video linking (also called ‘video hyperlinking’), and describe the latest edition of the Video Hyperlinking (LNK) task at TRECVid 2016. The emphasis of the LNK task in 2016 is on multimodality as used by videomakers to communicate their intended message. Crowdsourcing makes three critical contributions to the LNK task. First, it allows us to verify the multimodal nature of the anchors (queries) used in the task. Second, it enables us to evaluate the performance of video-to-video linking systems at large scale. Third, it gives us insights into how people understand the relevance relationship between two linked video segments. These insights are valuable since the relationship between video segments can manifest itself at different levels of abstraction.

Doi Bibtex

Titre:Multimodal video-to-video linking: Turning to the crowd for insight and evaluation
Mots Clés:Crowdsourcing, Video-to-video linking, Link evaluation, Verbal-visual information
Type:Conférence
Langue:English
Ville:Reykjavik
Pays:ISLANDE
Date:
Département:Data Science
Eurecom ref:5037
Copyright: © Springer. Personal use of this material is permitted. The definitive version of this paper was published in MMM 2017, 23rd International Conference on Multimedia Modeling, January 4-6, 2017, Reykjavik, Iceland / Also published in LNCS, Vol.10133/2017 and is available at : http://dx.doi.org/10.1007/978-3-319-51814-5_24
Bibtex: @inproceedings{EURECOM+5037, doi = {http://dx.doi.org/10.1007/978-3-319-51814-5_24}, year = {2017}, title = {{M}ultimodal video-to-video linking: {T}urning to the crowd for insight and evaluation}, author = {{E}skevich, {M}aria and {J}ones, {G}areth and {A}ly, {R}obin and {O}rdelman, {R}oeland and {H}uet, {B}enoit}, booktitle = {{MMM} 2017, 23rd {I}nternational {C}onference on {M}ultimedia {M}odeling, {J}anuary 4-6, 2017, {R}eykjavik, {I}celand / {A}lso published in {LNCS}, {V}ol.10133/2017}, address = {{R}eykjavik, {ISLANDE}}, month = {01}, url = {http://www.eurecom.fr/publication/5037} }
Voir aussi: