Graduate School and Research Center in Digital Sciences

Eurecom-Polito at TRECVID 2017: Hyperlinking task

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

TRECVID 2017, 21th International Workshop on Video Retrieval Evaluation, November 13-15, 2017, Gaithersburg, USA

This paper describes the system we designed to address the Hyperlinking task at TRECVID 2017 and the achieved results. Our contribution explores the potential of a solution based on the combination of textual and visual features in order to consider the di erent facets of the input videos. In particular, our approaches combined automatically generated transcripts (LIMSI), visual concepts, Meta-data, the text extracted by means of a Name Entity Recognition technique and a concept mapping tool. The four submitted runs aimed at analyzing the impact of the considered features on the quality of the retrieved hyperlinks.

Document Bibtex

Title:Eurecom-Polito at TRECVID 2017: Hyperlinking task
Type:Conference
Language:English
City:Gaithersburg
Country:UNITED STATES
Date:
Department:Data Science
Eurecom ref:5381
Copyright: © NIST. Personal use of this material is permitted. The definitive version of this paper was published in TRECVID 2017, 21th International Workshop on Video Retrieval Evaluation, November 13-15, 2017, Gaithersburg, USA and is available at :
Bibtex: @inproceedings{EURECOM+5381, year = {2017}, title = {{E}urecom-{P}olito at {TRECVID} 2017: {H}yperlinking task}, author = {{H}uet, {B}enoit and {B}aralis, {E}lena and {G}arza, {P}aolo and {R}eza {K}avoosifar, {M}ohammad}, booktitle = {{TRECVID} 2017, 21th {I}nternational {W}orkshop on {V}ideo {R}etrieval {E}valuation, {N}ovember 13-15, 2017, {G}aithersburg, {USA}}, address = {{G}aithersburg, {UNITED} {STATES}}, month = {11}, url = {http://www.eurecom.fr/publication/5381} }
See also: