Table 6 CT analysis of the MARNN-FRFICP approach on Flickr30K dataset with existing models.

From: An innovative multi-head attention mechanism-driven recurrent neural network model with feature representation fusion for enhanced image captioning to assist individuals with visual impairments

Flickr30K Dataset

Technique

CT (sec)

QPULM

19.72

YOLOv8

23.70

ResNet-50

12.19

Google NIC

17.19

Soft-Attention

16.38

m-RNN

24.71

SCA-CNN-VGG

15.32

GCN-LSTM

18.01

Injection-Tag

9.43

AIC-SSAIDL

14.07

MARNN-FRFICP

6.38

Back to article page