My research focuses on multimedia content understanding, machine learning, and affective computing. I am passionate about building systems that can engage users with multimedia. In view of that the aforementioned issue relies heavily on the association between visual and auditory, my research efforts also take this perspective into account in designing machine learning techniques, ranging from low-level to high-level, to more appropriately bridge the relationship between video and audio. Recently, I have expanded my research focus to include 3D human mesh reconstruction and generation, aiming to gain deeper insights into human behavior. Creating a system capable of engaging users with multiple signals is my research goal.