The aim of this workshop is to bring together researchers in computer vision and machine learning to share ideas and propose solutions on how to address the many aspects of activity recognition, and present new datasets that introduces new challenges in the field. Activity recognition is one of the core problems in computer vision. Recently it has attracted the attention of many researchers in the field. It is significant to many vision related applications such as surveillance, video search, human-computer interaction, and human-human, or social, interactions. Recent advances in feature representations, modeling, and inference techniques led to a significant progress in the field. Motivated by the rich and complex temporal, spatial, and social structure of human activities, activity recognition today features several new challenges, including modeling group activities, complex temporal reasoning, activity hierarchies, human-object interactions and human-scene interactions. These new challenges aim to answer questions regarding the semantic understanding and high-level reasoning of image and video content. At this level, other classical problems in computer vision, like object detection and tracking, not only impact, but are often intertwined with activity recognition. This inherent complexity prompts more time and thought to be spent on developing solutions to tackle auxiliary problems to the human activity recognition problem. Some of the fundamental questions that we propose are: How can we model human behavior on a spatio-temporal level for both individuals and groups? How can we successfully represent interactions between group activities and individual activities? Can inter-individual and inter-group interactions be modeled? How would they affect human behavior and improve activity recognition? How do we leverage tracks and identities to improve the performance of activity recognition? What can the scene layout (indoors, street, field, etc.) tell us about the individual actions? How can we combine kinematic models and object detectors to model human-object interactions? How can hierarchical representations of actions (sub-actions, attributes, etc.) help improve recognition performance? How do we apply logic programming and knowledge bases to recognize activities? Can we model social interactions between people and groups?