EURASIP Journal on Image and Video Processing

Table 2 Recognition accuracy (%) of various iDT based approaches in comparison with other approaches on downsampled versions of the KTH dataset

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

Method	SD₂	SD₃	SD₄	TD₂	TD₃	TD₄
iDT (Baseline)	92.59	78.80	61.85	95.19	91.57	89.54
iDT+LBP-TOP	92.96	81.94	73.61	95.09	92.13	89.54
iDT+LPQ-TOP	92.96	78.61	79.91	95.09	91.67	88.89
iDT+BSIF-TOP	93.89	88.33	82.41	95.09	92.22	90.00
iDT+Deep object [35]	86.57	84.26	82.41	87.04	85.19	84.26
LTTS+DS model [34]	82.22	83.78	80.00	–	–	–

Back to article page