Human Action Anticipation: Deep Learning Approaches Across Diverse Domains

Human action anticipation holds fundamental importance across various domains and applications. Anticipating human actions enables proactive decision-making, enhancing efficiency, safety, and overall performance of many systems, including robotic assistance systems, advanced surveillance systems, and autonomous driving, where self-driving cars should be able to anticipate pedestrians' intentions and actions to guarantee people's safety. In this dissertation, our primary focus centers on anticipating human actions within two critical domains: In-kitchen activities and pedestrian actions. However, our research extends to cover the anticipation of the collective behavior patterns in traffic flows. Our investigation extended even further to tackle the domain of abnormal behaviors decoding and recognition.