Table 5 Comparative analysis of ECMVFD-FTLTDO method on VTD dataset42.

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

VTD Dataset

Methods

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

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

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

\({F1}_{score}\)

\(MCC\)

PatchMatch-DFAVCMDL

69.11

70.95

70.34

69.95

73.28

LSTM-EnDec

65.60

74.13

72.71

70.69

74.63

CRF-Layer Model

64.30

73.73

73.06

70.13

71.97

High-pass FCN

69.00

85.45

79.01

81.86

72.09

Dense Moment Extraction

78.34

78.18

86.85

83.27

82.26

VCMFD Method

82.99

75.11

70.90

70.81

81.18

CNN-CMVFD

81.87

82.75

91.84

91.60

77.35

ECMVFD-FTLTDO

92.67

93.50

92.67

92.83

86.16

Back to article page