A Novel Parameter Initialization Technique Using RBM-NN for Human Action Recognition

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Method type</td><td class="align_center">Average recognition rate(%)</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Reference with MFS detector [<a href="/journals/cin/2020/8852404/#B112" target="_blank">112</a>]</td><td class="align_center">81.82</td></tr><tr><td class="align_left">Reference with OpenCV detector 20 [<a href="/journals/cin/2020/8852404/#B112" target="_blank">112</a>]</td><td class="align_center">79.84</td></tr><tr><td class="align_left">Reference with OpenCV detector 25 [<a href="/journals/cin/2020/8852404/#B112" target="_blank">112</a>]</td><td class="align_center">73.61</td></tr><tr><td class="align_left">Proposed method d1</td><td class="align_center">99.14</td></tr><tr><td class="align_left">Proposed method d2</td><td class="align_center">99.28</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Average recognition rate for CAVIAR dataset.</div>

Computational Intelligence and Neuroscience

tab4

Table 4

Table 4: A Novel Parameter Initialization Technique Using RBM-NN for Human Action Recognition 