Automatic Image Captioning Based on ResNet50 and LSTM with Soft Attention

<table class="table-group" id="tab1"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">CNN</td><td class="align_center">Number of parameters</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">VGG16</td><td class="align_center">138,357,544</td></tr><tr><td class="align_left">ResNet50</td><td class="align_center">23,587,712</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison of total number of VGG16 and ResNet50 parameters.</div>

Wireless Communications and Mobile Computing

tab1

Table 1

Table 1: Automatic Image Captioning Based on ResNet50 and LSTM with Soft Attention 