Table 9 CT evaluation of the MARNN-FRFICP method on MSCOCO dataset with existing approaches.

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

MSCOCO Dataset

Technique

CT (sec)

QPULM

19.45

YOLOv8

11.13

ResNet-50

19.44

Google NIC

11.82

Soft-Attention

21.95

m-RNN

19.07

SCA-CNN-VGG

13.27

GCN-LSTM

23.92

Injection-Tag

17.29

AIC-SSAIDL

8.64

MARNN-FRFICP

5.71

Back to article page