162404
doi
10.1145/2964284.2967271
oai:zenodo.org:162404
user-moving-h2020
user-invid-h2020
user-eu
Mezaris, Vasileios
CERTH
Patras, Ioannis
QMUL
Deep Multi-task Learning with Label Correlation Constraint for Video Concept Detection
Markatopoulou, Foteini
CERTH
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
Concept detection; deep learning; video analysis
<p>In this work we propose a method that integrates multi-task learning (MTL) and deep learning. Our method appends a MTL-like loss to a deep convolutional neural network, in order to learn the relations between tasks together at the same time, and also incorporates the label correlations between pairs of tasks. We apply the proposed method on a transfer learning scenario, where our objective is to fine-tune the parameters of a network that has been originally trained on a large-scale image dataset for concept detection, so that it be applied on a target video dataset and a corresponding new set of target concepts. We evaluate the proposed method for the video concept detection problem on the TRECVID 2013 Semantic Indexing dataset. Our results show that the proposed algorithm leads to better concept-based video annotation than existing state-of-the-art methods.</p>
Zenodo
2016-10-17
info:eu-repo/semantics/conferencePaper
657412
user-moving-h2020
user-invid-h2020
user-eu
award_title=Training towards a society of data-savvy information professionals to enable open leadership innovation; award_number=693092; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/693092; 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;
1579539565.01468
433735
md5:a715e3e8d926a165019b1b350465caa1
https://zenodo.org/records/162404/files/mm16_1_preprint.pdf
public