Skip to main content
EURASIP Journal on Advances in Signal Processing

Table 3 Results of CAs in the Focus, CBS, SPP, and CSPA on RAF-DB dataset

From: Research on real-time teachers’ facial expression recognition based on YOLOv5 and attention mechanisms

Method

Model size

Parameters

Accuracy (%)

mAP@0.5 (%)

Time (ms)

SA

91.827 M

46.853 M

74.9

82.1

18

FA

91.827 M

46.853 M

75.3

82.3

18

CBSA

92.490 M

47.884 M

75.7

82.5

22

CSPA

94.601 M

49.974 M

77.1

83.4

25

  1. Bold meant the best performance of tampering detection in the same experimental setting
Back to article page