Double Mask R-CNN for Pedestrian Detection in a Crowd

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Methods</td><td class="align_center">MR (%)</td><td class="align_center">AP<sub>50</sub> (%)</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">Deconv</td><td class="align_center">39.69</td><td class="align_center">86.38</td></tr><tr><td class="align_left">Bilinear</td><td class="align_center"><b>39.07</b></td><td class="align_center"><b>86.80</b></td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison of different upsample methods.</div>

Mobile Information Systems

tab4

Table 4

Table 4: Double Mask R-CNN for Pedestrian Detection in a Crowd 