Hierarchical Attention-Based Multimodal Fusion Network for Video Emotion Recognition

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="8"><hr/></td></tr><tr class="thead"><td class="align_left">Category</td><td class="align_center">Anger</td><td class="align_center">Disgust</td><td class="align_center">Fear</td><td class="align_center">Joy</td><td class="align_center">Sadness</td><td class="align_center">Surprise</td><td class="align_center">Total</td></tr><tr><td class="thead-hr" colspan="8"><hr/></td></tr><tr><td class="align_left">Number</td><td class="align_center">145</td><td class="align_center">157</td><td class="align_center">137</td><td class="align_center">220</td><td class="align_center">226</td><td class="align_center">181</td><td class="align_center">1066</td></tr><tr><td class="align_left">Average duration(s)</td><td class="align_center">14.62</td><td class="align_center">8.98</td><td class="align_center">16.57</td><td class="align_center">12.43</td><td class="align_center">27.60</td><td class="align_center">12.11</td><td class="align_center">15.76</td></tr><tr class="table-tr"><td colspan="8"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The number of videos per category in MHED dataset.</div>

Computational Intelligence and Neuroscience

tab2

Table 2

Table 2: Hierarchical Attention-Based Multimodal Fusion Network for Video Emotion Recognition 