1183440
doi
10.5281/zenodo.1183440
oai:zenodo.org:1183440
user-invid-h2020
user-emma-h2020
user-eu
Moumtzidou, Anastasia
Information Technologies Institute/Centre for Research and Technology Hellas
Galanopoulos, Damianos
Information Technologies Institute/Centre for Research and Technology Hellas
Avgerinakis, Konstantinos
Information Technologies Institute/Centre for Research and Technology Hellas
Andreadis, Stelios
Information Technologies Institute/Centre for Research and Technology Hellas
Gialampoukidis, Ilias
Information Technologies Institute/Centre for Research and Technology Hellas
Tachos, Stavros
Information Technologies Institute/Centre for Research and Technology Hellas
Vrochidis, Stefanos
Information Technologies Institute/Centre for Research and Technology Hellas
Mezaris, Vasileios
Information Technologies Institute/Centre for Research and Technology Hellas
Kompatsiaris, Ioannis
Information Technologies Institute/Centre for Research and Technology Hellas
Patras, Ioannis
Queen Mary University of London
ITI-CERTH participation in TRECVID 2017
Markatopoulou, Foteini
Information Technologies Institute/Centre for Research and Technology Hellas
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
<p>This paper provides an overview of the runs submitted to TRECVID 2017 by ITI-CERTH. ITI-CERTH participated in the Ad-hoc Video Search (AVS), Multimedia Event Detection (MED), Instance Search (INS) and Surveillance Event Detection (SED) tasks. Our AVS task participation is based on a method that combines the linguistic analysis of the query with concept-based and semantic-embedding representations of video fragments. Regarding the MED task, this year we participate on Pre-Specied and Ah-Hoc sub-tasks exploiting both motion-based as well as DCNN-based features. The INS task is performed by employing VERGE, which is an interactive retrieval application that integrates retrieval functionalities that consider mainly visual information. For the SED task, we deploy a novel activity detection algorithm that is based on human detection in video frames, goal descriptors, dense trajectories, Fisher vectors and a discriminative action segmentation scheme.</p>
Zenodo
2018-02-23
info:eu-repo/semantics/conferencePaper
1183439
user-invid-h2020
user-emma-h2020
user-eu
award_title=Enhancing decision support and management services in extreme weather climate events; award_number=700475; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/700475; funder_id=00k4n6c32; funder_name=European Commission;
award_title=Retrieval and Analysis of Heterogeneous Online Content for Terrorist Activity Recognition; award_number=700024; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/700024; funder_id=00k4n6c32; funder_name=European Commission;
award_title=In Video Veritas – Verification of Social Media Video Content for the News Industry; award_number=687786; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/687786; funder_id=00k4n6c32; funder_name=European Commission;
award_title=Enriching Market solutions for content Management and publishing with state of the art multimedia Analysis techniques; award_number=732665; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/732665; funder_id=00k4n6c32; funder_name=European Commission;
1579541220.531863
4657322
md5:1cb8b54ab9e6dd8eacb18d8a22311974
https://zenodo.org/records/1183440/files/trecvid2017.pdf
public
10.5281/zenodo.1183439
isVersionOf
doi