A New Algorithm for Sketch-Based Fashion Image Retrieval Based on Cross-Domain Transformation

<table class="table-group" id="tab1"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Single-modal datasets</td><td class="align_center">Number of images</td></tr><tr><td class="align_center" colspan="2"><hr/></td></tr><tr><td class="align_left">DDAN [<a href="/journals/wcmc/2021/5577735/#B28" target="_blank">28</a>]</td><td class="align_center">341,021 photos</td></tr><tr><td class="align_left">WTBI [<a href="/journals/wcmc/2021/5577735/#B4" target="_blank">4</a>]</td><td class="align_center">78,958 photos</td></tr><tr><td class="align_left">DeepFashion [<a href="/journals/wcmc/2021/5577735/#B2" target="_blank">2</a>]</td><td class="align_center">Over 800,000 photos</td></tr><tr><td class="align_center" colspan="2"><hr/></td></tr><tr><td class="align_left">Multi-modal datasets</td><td class="align_center">Number of images</td></tr><tr><td class="align_center" colspan="2"><hr/></td></tr><tr><td class="align_left">QMUL-shoe [<a href="/journals/wcmc/2021/5577735/#B8" target="_blank">8</a>]</td><td class="align_center">419 sketches, 419 photos</td></tr><tr><td class="align_left">Our Fashion Image dataset</td><td class="align_center">36,074 sketches, 36,074 photos</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The comparison of our dataset with existing datasets.</div>

Wireless Communications and Mobile Computing

tab1

Table 1

Table 1: A New Algorithm for Sketch-Based Fashion Image Retrieval Based on Cross-Domain Transformation 