<ul><li>Micro-Action Recognition (MAR) has gained attention for its role in non-verbal communication and emotion analysis.</li><li>A novel approach called Prototypical Calibrating Ambiguous Network (PCAN) is proposed to address the ambiguity in MAR.</li><li>PCAN employs a hierarchical action-tree to identify and categorize ambiguous samples into distinct sets.</li><li>Extensive experiments demonstrate the superior performance of PCAN compared to existing approaches.</li></ul>

Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition

Discover more