Skip to main content

Table 3 Recognition accuracy (%) of various approaches on the Youtube-LQ dataset

From: Exploiting textures for better action recognition in low-quality videos

Method

YouTube-LQ

Method

YouTube-LQ

STIP (baseline)

67.57

iDT (Baseline)

74.04

STIP+LBP-TOP

70.69

iDT+LBP-TOP

75.59

STIP+LPQ-TOP

69.13

iDT+LPQ-TOP

76.02

STIP+BSIF-TOP

76.05

iDT+BSIF-TOP

80.45

STIP+deep object [35]

85.37

iDT+deep object [35]

85.36