Conference paper Open Access

ITI-CERTH participation in TRECVID 2019

Konstantinos Gkountakos; Konstantinos Ioannidis; Stefanos Vrochidis; Ioannis Kompatsiaris


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.4452098", 
  "language": "eng", 
  "title": "ITI-CERTH participation in TRECVID 2019", 
  "issued": {
    "date-parts": [
      [
        2020, 
        3, 
        1
      ]
    ]
  }, 
  "abstract": "<p>In this work, an overview of the submitted run to TRECVID 2019 by ITI-CERTH is presented and more specifically, for the task of Activities in Extended Video (ActEV). Towards this objective, we deployed a state-of-the-art architecture for the human action recognition problem and with the application of an encoder-decoder model, we extract a threshold for every activity in order for the framework not only to recognize activities but also to identify them in extended videos.</p>", 
  "author": [
    {
      "family": "Konstantinos Gkountakos"
    }, 
    {
      "family": "Konstantinos Ioannidis"
    }, 
    {
      "family": "Stefanos Vrochidis"
    }, 
    {
      "family": "Ioannis Kompatsiaris"
    }
  ], 
  "type": "paper-conference", 
  "id": "4452098"
}
133
44
views
downloads
All versions This version
Views 133133
Downloads 4444
Data volume 58.5 MB58.5 MB
Unique views 109109
Unique downloads 3838

Share

Cite as