Conference paper Open Access

Concept Language Models and Event-based Concept Number Selection for Zero-example Event Detection

Galanopoulos, Damianos; Markatopoulou, Foteini; Mezaris, Vasileios; Patras, Ioannis


JSON-LD (schema.org) Export

{
  "description": "<p>Zero-example event detection is a problem where, given an event query as input but no example videos for training a detector, the system retrieves the most closely related videos. In this paper we present a fully-automatic zero-example event detection method that is based on translating the event description to a predefined set of concepts for which previously trained visual concept detectors are available. We adopt the use of Concept Language Models (CLMs), which is a method of augmenting semantic concept definition, and we propose a new concept-selection method for deciding on the appropriate number of the concepts needed to describe an event query. The proposed system achieves state-of-the-art performance in automatic zero-example event detection.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Information Technologies Institute (ITI) - Centre for Research and Technology Hellas (CERTH)", 
      "@type": "Person", 
      "name": "Galanopoulos, Damianos"
    }, 
    {
      "affiliation": "Information Technologies Institute (ITI) - Centre for Research and Technology Hellas (CERTH)", 
      "@type": "Person", 
      "name": "Markatopoulou, Foteini"
    }, 
    {
      "affiliation": "Information Technologies Institute (ITI) - Centre for Research and Technology Hellas (CERTH)", 
      "@type": "Person", 
      "name": "Mezaris, Vasileios"
    }, 
    {
      "affiliation": "Queen Mary University of London", 
      "@type": "Person", 
      "name": "Patras, Ioannis"
    }
  ], 
  "headline": "Concept Language Models and Event-based Concept Number Selection for Zero-example Event Detection", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2017-06-08", 
  "url": "https://zenodo.org/record/809680", 
  "keywords": [
    "Zero-example multimedia event detection", 
    "Video search", 
    "Query representation"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.1145/3078971.3079043", 
  "@id": "https://doi.org/10.1145/3078971.3079043", 
  "@type": "ScholarlyArticle", 
  "name": "Concept Language Models and Event-based Concept Number Selection for Zero-example Event Detection"
}
117
66
views
downloads
Views 117
Downloads 66
Data volume 80.1 MB
Unique views 110
Unique downloads 66

Share

Cite as