Table 4 Comparative analysis of ECMVFD-FTLTDO method on GRIP dataset42.

From: A multi-model feature fusion based transfer learning with heuristic search for copy-move video forgery detection

GRIP dataset

Methods

\(Acc{u}_{y}\)

\(Pre{c}_{n}\)

\(Rec{a}_{l}\)

\({F1}_{score}\)

\(MCC\)

PatchMatch-DFAVCMDL

73.60

69.13

73.82

73.61

74.96

LSTM-EnDec

69.40

69.87

72.45

70.70

74.63

CRF-Layer Model

63.20

73.59

77.22

72.45

74.47

High-pass FCN

74.90

72.32

71.86

71.54

76.51

Dense moment extraction

78.34

76.29

75.57

70.79

72.74

VCMFD Method

83.33

76.71

79.36

77.70

79.33

CNN-CMVFD

86.16

79.95

79.91

79.32

76.55

ECMVFD-FTLTDO

95.26

95.17

95.26

95.13

90.43

Back to article page