| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Representing Visual Appearance by Video Brownian Covariance Descriptor for Human Action Recognition
Abstract : This paper addresses a problem of recognizing human actions in video sequences. Recent studies have shown that methods which use bag-of-features and space-time features achieve high recognition accuracy. Such methods extract both appearance-based and motion-based features. This paper focuses only on appearance features. We proposeto model relationships between different pixel-level appearance features such as intensity and gradient using Brownian covariance, which is a natural extension of classical covariance measure. While classical covariance can model only linear relationships, Brownian covariance models all kinds of possible relationships. We propose a method to compute Brownian covariance on space-time volume of a video sequence. We show that proposed Video Brownian Covariance (VBC) descriptor carries complementary information to the Histogram of Oriented Gradients (HOG) descriptor. The fusion of these two descriptors gives a significant improvement in performance on three challenging action recognition datasets.
Keywords :
computer visiosn
action recognition
Cited literature [22 references]
https://hal.inria.fr/hal-01054943
Contributor : Michal Koperski <>
Submitted on : Thursday, November 6, 2014 - 3:00:51 PM
Last modification on : Thursday, March 5, 2020 - 5:34:19 PM
Long-term archiving on: : Friday, April 14, 2017 - 3:02:39 PM
Contributor : Michal Koperski <>
Submitted on : Thursday, November 6, 2014 - 3:00:51 PM
Last modification on : Thursday, March 5, 2020 - 5:34:19 PM
Long-term archiving on: : Friday, April 14, 2017 - 3:02:39 PM
File
Bilinski-VideoBrownianCovarian...
Files produced by the author(s)