A Multimodal Information Fusion Model for Robot Action Recognition with Time Series

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Data set\fusion method</td><td class="align_center">Mean fusion</td><td class="align_center">Confidence fusion</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">NTU-RGB+D</td><td class="align_center">0.8524 ± 0.0346</td><td class="align_center">0.8683 ± 0.02154</td></tr><tr><td class="align_left">MSR action 3D</td><td class="align_center">0.9262 ± 0.0653</td><td class="align_center">0.9529 ± 0.03447</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Accuracy of action recognition with different fusion methods.</div>

Journal of Electrical and Computer Engineering

tab2

Table 2

Table 2: A Multimodal Information Fusion Model for Robot Action Recognition with Time Series 