API World + AI DevWorld

With a rapid increase in the number of cars and other vehicles in the urban transportation system, autonomous driving (or robot-assisted driving) has emerged as one of the predominant research areas in artificial intelligence. Within it, human activity recognition is the important part for ride-hailing and human behavior analysis. Human actions in video sequences are three-dimensional (3D) spatio-temporal signals characterizing both the instantaneous visual appearance and the motion dynamics. This talk will cover several new deep architectures to handle video signals efficiently and effectively.