Accession Number:

AD1037277

Title:

Recognizing Activities via Bag of Words for Attribute Dynamics (Open Access)

Descriptive Note:

Journal Article

Corporate Author:

SRI International Sarnoff Princeton United States

Report Date:

2013-10-03

Pagination or Media Count:

8.0

Abstract:

In this work, we propose a novel video representation for activity recognition that models video dynamics with attributes of activities. A video sequence is decomposed into short-term segments, which are characterized by the dynamics of their attributes. These segments are modeled by a dictionary of attribute dynamics templates, which are implemented by a recently introduced generative model, the binary dynamic systemBDS. We propose methods for learning a dictionary of BDSs from a training corpus, and for quantizing attribute sequences extracted from videos into these BDS code words. This procedure produces a representation of the video as a histogram of BDS code words, which is denoted the bag-of-words for attribute dynamics BoWAD. An extensive experimental evaluation reveals that this representation outperforms other state-of-the-art approaches in temporal structure modeling for complex activity recognition.

Subject Categories:

  • Cybernetics
  • Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE