Authors: Deeptha Girish, Vineeta Singh, Anca Ralescu Description: Action recognition in still images is closely related to various other computer vision tasks like pose estimation, object recognition, image retrieval, video action recognition and frame tagging in videos. This problem is focused on recognizing a person’s action or behavior using a single frame. Unlike action recognition in videos, which is a relatively very well established area of research, spatio-temporal features are not available to characterize actions in still images which makes a more challenging problem. In this work only actions that involve objects are considered. The complex action is broken down into components based on semantics. The importance of each of these components in action recognition is systematically studied.