The purpose of this thesis is to propose swiveling behavior as a potential speech transitioning device and to discuss the methodology behind qualitative and quantitative analysis of swivels in relation to subjects’ partners. Due to the impacts of gaze and body orientation direction on speech transitioning, it is deduced that,...
Recognizing human actions in videos is a long-standing problem in computer vision with a wide range of applications including video surveillance, content retrieval, and sports analysis. This thesis focuses on addressing efficiency and robustness of video classification in unconstrained real-world settings. The thesis work can be broadly divided into four...