research data . Dataset . 2017

Concept detection scores for the IACC.3 dataset (TRECVID AVS Task)

Markatopoulou, Foteini; Mezaris, Vasileios;
Open Access
  • Published: 17 Feb 2017
  • Publisher: Zenodo
Abstract
<p>We provide concept detection scores for the IACC.3 dataset (600 hr internet archive videos), which is used in the TRECVID Ad-hoc Video Search (AVS) task [1]. Concept detection scores for 1345 concepts (1000 ImageNet concepts provided for the ILSVRC challenge [2] and 345 TRECVID SIN concepts [3]) have been generated as follows:<br> 1) To generate scores for the ImageNet concepts, 5 pre-trained ImageNet networks were applied on the IACC.3 dataset and their output was fused in terms of arithmetic mean.<br> 2) To generate scores for the TRECVID SIN concepts, two pre-trained ImageNet networks were fine-tuned on these concepts using a combination of our methods pre...
Subjects
free text keywords: concept detection, ad-hoc video search, TRECVID AVS task, video analysis, Medicine, Biotechnology, Sociology, Science Policy, 69999 Biological Sciences not elsewhere classified, 80699 Information Systems not elsewhere classified
Funded by
EC| InVID
Project
InVID
In Video Veritas – Verification of Social Media Video Content for the News Industry
  • Funder: European Commission (EC)
  • Project Code: 687786
  • Funding stream: H2020 | IA
Communities
Science and Innovation Policy Studies
Download fromView all 4 versions
Zenodo
Dataset . 2017
Provider: Zenodo
Zenodo
Dataset . 2017
Provider: Datacite
Zenodo
Dataset . 2017
Provider: Datacite
figshare
Dataset . 2017
Provider: figshare
Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue
research data . Dataset . 2017

Concept detection scores for the IACC.3 dataset (TRECVID AVS Task)

Markatopoulou, Foteini; Mezaris, Vasileios;