Skip to main content
SpringerPlus

Table 1 Comparison of the proposed method with existing methods for the KTH dataset

From: Multi-surface analysis for human action recognition in video

Method

Accuracy (%)

3SMF + STIP + NBNN

96.50

STIP + NBNN algorithm (uniform distribution) (Zhang et al. 2013)

92.83

Yuan et al. (2011a)

94.00

Yan and Luo (2012)

93.98

Chakraborty et al. (2012)

96.35

Wang et al. (2014)

94.4

Weinland et al. (2010)

92.4

  1. Italic value mean the best results
Back to article page