Conference paper Open Access

ONLINE MULTI-TASK LEARNING FOR SEMANTIC CONCEPT DETECTION IN VIDEO

Foteini Markatopoulou; Vasileios Mezaris; Ioannis Patras


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/8fb9b302-99ec-4a2f-b567-d5afa49e349f/icip16_1_preprint.pdf"
      }, 
      "checksum": "md5:2ea63812f644dee948985e9a549b2177", 
      "bucket": "8fb9b302-99ec-4a2f-b567-d5afa49e349f", 
      "key": "icip16_1_preprint.pdf", 
      "type": "pdf", 
      "size": 632906
    }
  ], 
  "owners": [
    22754
  ], 
  "doi": "10.1109/ICIP.2016.7532344", 
  "stats": {
    "version_unique_downloads": 19.0, 
    "unique_views": 36.0, 
    "views": 39.0, 
    "downloads": 19.0, 
    "unique_downloads": 19.0, 
    "version_unique_views": 36.0, 
    "volume": 12025214.0, 
    "version_downloads": 19.0, 
    "version_views": 39.0, 
    "version_volume": 12025214.0
  }, 
  "links": {
    "doi": "https://doi.org/10.1109/ICIP.2016.7532344", 
    "latest_html": "https://zenodo.org/record/159241", 
    "bucket": "https://zenodo.org/api/files/8fb9b302-99ec-4a2f-b567-d5afa49e349f", 
    "badge": "https://zenodo.org/badge/doi/10.1109/ICIP.2016.7532344.svg", 
    "html": "https://zenodo.org/record/159241", 
    "latest": "https://zenodo.org/api/records/159241"
  }, 
  "created": "2016-10-04T09:37:27.241803+00:00", 
  "updated": "2019-04-10T03:47:55.893305+00:00", 
  "conceptrecid": "653967", 
  "revision": 7, 
  "id": 159241, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.1109/ICIP.2016.7532344", 
    "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": {
      "id": "CC-BY-4.0"
    }, 
    "title": "ONLINE MULTI-TASK LEARNING FOR SEMANTIC CONCEPT DETECTION IN VIDEO", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "653967"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "159241"
          }
        }
      ]
    }, 
    "communities": [
      {
        "id": "ecfunded"
      }, 
      {
        "id": "invid-h2020"
      }
    ], 
    "grants": [
      {
        "code": "687786", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::687786"
        }, 
        "title": "In Video Veritas \u2013 Verification of Social Media Video Content for the News Industry", 
        "acronym": "InVID", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [
            "EC"
          ], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "keywords": [
      "Concept detection", 
      "Multi-task learning", 
      "Video"
    ], 
    "publication_date": "2016-09-25", 
    "creators": [
      {
        "affiliation": "Information Technologies Institute (ITI), CERTH, Queen Mary University of London", 
        "name": "Foteini Markatopoulou"
      }, 
      {
        "affiliation": "Information Technologies Institute (ITI), CERTH", 
        "name": "Vasileios Mezaris"
      }, 
      {
        "affiliation": "Queen Mary University of London", 
        "name": "Ioannis Patras"
      }
    ], 
    "meeting": {
      "acronym": "ICIP 2016", 
      "url": "http://2016.ieeeicip.org/", 
      "dates": "25-28 September 2016", 
      "place": "Phoenix Cinvention Center, Phoenix, Arizona 85004 USA", 
      "title": "IEEE International Conference on Image Processing"
    }, 
    "access_right": "open", 
    "resource_type": {
      "subtype": "conferencepaper", 
      "type": "publication", 
      "title": "Conference paper"
    }
  }
}
39
19
views
downloads
Views 39
Downloads 19
Data volume 12.0 MB
Unique views 36
Unique downloads 19

Share

Cite as