Artificial Intelligence was originally devised with a clear purpose in mind: replicate human abilities into computational systems. To achieve this goal, systems need to be provided with the means to sense and act, perceive, and understand. Acting has been faced from the agency model field, sensing from a more technological field in seeking for devices capable of replicating human senses, and finally perceiving and understanding have been faced from the knowledge management and reasoning field. This workshop on Sensing, Understanding and Modeling for the Smart City is intended to explore the recent advances in any of these three fields of knowledge, although from the specific perspective of solutions for perceiving and understanding human actions. Comprehensive solutions devoted to fields such as Ubiquitous Computing, Ambient Assisted Living, Ambient Intelligence and special Smart City spaces are encouraged.