Sampling Strategies for Real-Time Action Recognition

Citations Over TimeTop 1% of 2013 papers

Abstract

Local spatio-temporal features and bag-of-features representations have become popular for action recognition. A recent trend is to use dense sampling for better performance. While many methods claimed to use dense feature sets, most of them are just denser than approaches based on sparse interest point detectors. In this paper, we explore sampling with high density on action recognition. We also investigate the impact of random sampling over dense grid for computational efficiency. We present a real-time action recognition system which integrates fast random sampling method with local spatio-temporal features extracted from a Local Part Model. A new method based on histogram intersection kernel is proposed to combine multiple channels of different descriptors. Our technique shows high accuracy on the simple KTH dataset, and achieves state-of-the-art on two very challenging real-world datasets, namely, 93% on KTH, 83.3% on UCF50 and 47.6% on HMDB51.

Related Papers

• → Plant Leaf Recognition Using Zernike Moments and Histogram of Oriented Gradients(2014)61 cited
• → Scene Text Recognition Using Co-occurrence of Histogram of Oriented Gradients(2013)56 cited
• → Human detection based on integral Histograms of Oriented Gradients and SVM(2011)28 cited
• → Pedestrian detection using mixed partial derivative based histogram of oriented gradients(2014)20 cited
• → Human Action Recognition Based on Dense Trajectories Analysis and Random Forest(2016)1 cited