Conference paper Open Access

ONLINE MULTI-TASK LEARNING FOR SEMANTIC CONCEPT DETECTION IN VIDEO

Foteini Markatopoulou; Vasileios Mezaris; Ioannis Patras


JSON-LD (schema.org) Export

{
  "description": "<p>In this paper we propose an online multi-task learning algorithm for video concept detection. In particular, we extend the Efficient Lifelong Learning Algorithm (ELLA) in the following ways: a) we solve the objective function of ELLA using quadratic programming instead of solving the Lasso problem, b) we add a new label-based constraint that considers concept correlations, c) we use linear SVMs as base learners instead of logistic regression. Experimental results show improvement over both the single-task learning methods typically used in this problem and the original ELLA algorithm.</p>", 
  "license": "http://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Information Technologies Institute (ITI), CERTH, Queen Mary University of London", 
      "@type": "Person", 
      "name": "Foteini Markatopoulou"
    }, 
    {
      "affiliation": "Information Technologies Institute (ITI), CERTH", 
      "@type": "Person", 
      "name": "Vasileios Mezaris"
    }, 
    {
      "affiliation": "Queen Mary University of London", 
      "@type": "Person", 
      "name": "Ioannis Patras"
    }
  ], 
  "headline": "ONLINE MULTI-TASK LEARNING FOR SEMANTIC CONCEPT DETECTION IN VIDEO", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2016-09-25", 
  "url": "https://zenodo.org/record/159241", 
  "keywords": [
    "Concept detection", 
    "Multi-task learning", 
    "Video"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.1109/ICIP.2016.7532344", 
  "@id": "https://doi.org/10.1109/ICIP.2016.7532344", 
  "@type": "ScholarlyArticle", 
  "name": "ONLINE MULTI-TASK LEARNING FOR SEMANTIC CONCEPT DETECTION IN VIDEO"
}
38
19
views
downloads
Views 38
Downloads 19
Data volume 12.0 MB
Unique views 35
Unique downloads 19

Share

Cite as