University of Amsterdam at THUMOS Challenge 2014

Open Access
Authors
Publication date 2014
Book title THUMOS Challenge 2014: notebook papers
Event 14th ECCV, THUMOS Challenge workshop (Zürich)
Publisher Orlando, FL: Center for Research in Computer Vision, University of Central Florida
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
Abstract This notebook paper describes our approach for the action classification task of the THUMOS Challenge 2014. We investigate and exploit the action-object relationship by capturing both motion and related objects. As local descriptors we use HOG, HOF and MBH computed along the improved dense trajectories. For video encoding we rely on Fisher vector. In addition, we employ deep net features learned from object attributes to capture action context. All actions are classified with a one-versus-rest linear SVM.
Document type Conference contribution
Language English
Published at http://crcv.ucf.edu/THUMOS14/papers/University%20of%20Amesterdam.pdf
Downloads
University of Amesterdam (Final published version)
Permalink to this page
Back