A fast video event recognition system and its application to video search

  • Authors:

  • Yu-Gang Jiang;Qi Dai;Yingbin Zheng;Xiangyang Xue;Jie Liu;Dong Wang

  • Affiliations:

  • Fudan University, Shanghai, China;Fudan University, Shanghai, China;Fudan University, Shanghai, China;Fudan University, Shanghai, China;Huawei Technologies, Beijing, China;Huawei Technologies, Beijing, China

  • Venue:
  • Proceedings of the 20th ACM international conference on Multimedia
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Techniques for recognizing complex events in diverse Internet videos are important in many applications. State-of-the-art video event recognition approaches normally involve modules that demand extensive computation, which prevents their application to large scale problems. In this demonstration, we present a fast video event recognition system, which requires just a few seconds to process a general YouTube video with a few minutes of duration. The development of this system is grounded on several important findings from a large set of empirical studies, where we systematically evaluated many technical options for each critical module of a present-day video event recognition framework. Pooling the insights gained from this study leads to a speeded-up event recognition system that is 220-times faster than a decent baseline while still has a high degree of recognition accuracy. We also demonstrate the technical feasibility of using event recognition results as the sole clue for video search, where the similarity of videos is determined based on the consistency of the event recognition confidence scores. We showcase this capability using an Internet video dataset containing about 10 thousands of YouTube videos. Very promising results were observed.