BPI-MVQA: a bi-branch model for medical visual question answering

BMC Medical Imaging

Table 13 Experimental comparison of BPI-MVQA with other state-of-the-art methods on the ImageCLEF2018 VQA-Med dataset

Model	WBSS	BLEU
ResNet152+LSTM+MFB [20]	0.186	0.158
Inception-Resnet-v2+BiLstm [22]	0.174	0.135
VGG16+SAN(Stacked attention)+LSTM [25]	0.174	0.121
VGG16+BiLSTM+Decision tree classifier [49]	0.053	0.100
BPI-MVQA(Our model)	0.188	0.162

ISSN: 1471-2342