DISSERTATION DEFENSE PRESENTATION

https://txstate.zoom.us/my/keshav.phd.defense

Activity recognition is one of the popular fields in computer vision research. Though recent development in deep learning-based methodologies has shown tremendous progress in traditional video-based activity recognition, 360-degree activity recognition is still in its infancy. 360-degree-based activity recognition imposes challenges like lack of datasets, domain-specific frameworks, and motion understanding in 360-degree videos. This research focuses on two critical aspects of activity recognition in 360-degree videos from an egocentric perspective, (i) Egocentric activity recognition and (ii) Motion understanding in 360-degree videos. We will discuss several challenges in these areas and propose a representation learning-based framework for activity recognition and motion understanding in 360-degree videos.