Material Detail

Visual Event Recognition in Videos by Learning from Web Data

Visual Event Recognition in Videos by Learning from Web Data

This video was recorded at 23rd IEEE Conference on Computer Vision and Pattern Recognition 2010 - San Francisco. We propose a visual event recognition framework for consumer domain videos by leveraging a large amount of loosely labeled web videos (e.g., from YouTube). First, we propose a new aligned space-time pyramid matching method to measure the distances between two video clips, where each video clip is divided into space-time volumes over multiple levels. We calculate the pair-wise distances between any two volumes and further integrate the information from different volumes with Integer-flow Earth Mover's Distance (EMD) to explicitly align the volumes. Second, we propose a new cross-domain learning method in order to 1) fuse the information from multiple pyramid levels and features... Show More

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Browse...

Disciplines with similar materials as Visual Event Recognition in Videos by Learning from Web Data

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.
hidden