Skip to main content

Table 6 Comparative analysis of competitive methods with a proposed method on the Holidays dataset

From: BoVW model based on adaptive local and global visual words modeling and log-based relevance feedback for semantic retrieval of the images

Performance parameters

Proposed method

MTBCD [13]

BMM-FV CNN [17]

Modified VLAD [29]

Att. features+Fisher vectors [30]

Fisher kernel-GMM [31]

mAP (%)

72.85

67.09

54.70

65.80

69.90

70.50

Avg. recall (R)

14.57

13.41

10.94

13.16

13.98

14.10

Avg. F-measure (F)

24.28

22.35

18.23

21.93

23.30

23.50