Evaluating multimedia features and fusion for example-based event detection (Open Access-Publisher's Version)
Abstract
Multimedia event detection (MED) is a challenging problem because of the heterogeneous content and variable quality found in large collections of Internet videos. To study the value of multimedia features and fusion for representing and learning events from a set of example video clips, we created SESAME, a system for video SEarch with Speed and Accuracy for Multimedia Events. SESAME includes multiple bag-of-words event classifiers based on single data types: low-level visual, motion, and audio features; high-level semantic visual concepts; and automatic speech recognition. Event detection performance was evaluated for each event classifier. The performance of low-level visual and motion features was improved by the use of difference coding. The accuracy of the visual concepts was nearly as strong as that of the low-level visual features. Experiments with a number of fusion methods for combining the event detection scores from these classifiers revealed that simple fusion methods, such as arithmetic mean, perform as well as or better than other, more complex fusion methods. SESAMEs performance in the 2012 TRECVID MED evaluation was one of the best reported.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 23, 2013
- Accession Number
- AD1037288
Entities
People
- Amirhossein Habibian
- Arnold W. Smeulders
- Cees G. Snoek
- Chen Sun
- Dennis C. Koelma
- Gregory K. Myers
- Julien Van Hout
- Koen E. Van De Sande
- Ramakant Nevatia
- Ramesh Nallapati
- Stephanie Pancoast
Organizations
- SRI International