Skip to main content

Table 3 Performance results of the proposed method for different number of decomposition levels on MSCOCO dataset

From: Image caption generation using Visual Attention Prediction and Contextual Spatial Relation Extraction

Decomposition levels

MSCOCO

 

B@4

MT

CD

1-level

52.87

35.14

90.39

2-level

53.64

36.53

91.71

3-level

53.69

36.90

91.89