Skip to main content

Advertisement

Table 1 Comparisons of recognition accuracies on KTH dataset

From: Recognizing flu-like symptoms from videos

Method Brief description Acc. %
ICPR’04 [22] HOGHOF + SVM 71.7
CVPR’07 [36] cuboid + WX-SVM 91.6
BMVC’09 [35] cuboid + BoW+ χ2 89.1
  HOGHOF + BoW + χ2 91.8
ECCV’10 [37] convolutional nets 90.0
In this paper cuboid + BoW + χ2 (baseline) 88.2
  cuboid + AMK I U c S=2 91.7
  cuboid + AMK I U b S=8 93.0
  cuboid + AMK I B S=7 92.7
  cuboid + AMK II 93.2
  HOGHOF + BoW + χ2 (baseline) 88.5
  HOGHOF + AMK I U c S=3 91.1
  HOGHOF + AMK I U b S=27 95.2
  HOGHOF + AMK I B S=5 92.3
  HOGHOF + AMK II 93.5
  1. Comparisons of recognition accuracies on KTH dataset. Here shorthands of AMK I and II are used for AMK type I and type II kernels, respectively. U c (U b ) refers to the concentric (block) partition scheme in unary extension. B is for binary extension.