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

Eurecom-Polito at TRECVID 2016: Hyperlinking task

Huet, Benoît; Baralis, Elena; Garza, Paolo; Kavoosifar, Mohammad Reza

TRECVID 2016, 20th International Workshop on Video Retrieval Evaluation, 14-16 Novembre 2016, Gaithersburg, Ma, USA

In this paper, we describe the system we used to address the Hyperlinking task at TRECVID 2016 and the achieved results. Our system combines several features (textual and visual) in order to consider the different facets of the input videos. Specifically, we combined automatically generated transcripts, visual concepts, and the text extracted by means of an OCR tool. We also exploited WordNet to find synonyms which are used to apply a simple query expansion technique. The four submitted runs aimed at analyzing the impact of the considered features on the quality of the retrieved hyperlinks.

Document Bibtex

Titre:Eurecom-Polito at TRECVID 2016: Hyperlinking task
Type:Conférence
Langue:English
Ville:Gaithersburg
Pays:ÉTATS-UNIS
Date:
Département:Data Science
Eurecom ref:5163
Copyright: © NIST. Personal use of this material is permitted. The definitive version of this paper was published in TRECVID 2016, 20th International Workshop on Video Retrieval Evaluation, 14-16 Novembre 2016, Gaithersburg, Ma, USA and is available at :
Bibtex: @inproceedings{EURECOM+5163, year = {2016}, title = {{E}urecom-{P}olito at {TRECVID} 2016: {H}yperlinking task}, author = {{H}uet, {B}eno{\^i}t and {B}aralis, {E}lena and {G}arza, {P}aolo and {K}avoosifar, {M}ohammad {R}eza}, booktitle = {{TRECVID} 2016, 20th {I}nternational {W}orkshop on {V}ideo {R}etrieval {E}valuation, 14-16 {N}ovembre 2016, {G}aithersburg, {M}a, {USA} }, address = {{G}aithersburg, {\'{E}}{TATS}-{UNIS}}, month = {11}, url = {http://www.eurecom.fr/publication/5163} }
Voir aussi: