Access Restriction

Author Shi, Feng ♦ Petriu, Emil ♦ Laganière, Robert
Source CiteSeerX
Content type Text
File Format PDF
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Real-time Action Recognition ♦ Pattern Recognition Sampling Strategy ♦ Computer Vision ♦ Ieee Conference ♦ Action Recognition ♦ Local Spatio-temporal Feature ♦ New Method ♦ Fast Random ♦ High Accuracy ♦ Local Part Model ♦ Many Method ♦ Histogram Intersection Kernel ♦ Challenging Real-world Datasets ♦ Dense Feature Set ♦ Sparse Interest Point Detector ♦ Dense Grid ♦ Recent Trend ♦ Different Descriptor ♦ Computational Efficiency ♦ Dense Sampling ♦ Simple Kth Dataset ♦ Real-time Action Recognition System ♦ Multiple Channel ♦ High Density ♦ Bag-of-features Representation
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. 1.
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study