||In this seminar, I will be presenting my doctoral thesis work on early human action detection. Early detection of human actions is essential in a wide spectrum of applications ranging from video surveillance to health-care. While human action recognition has been extensively studied, little attention is paid to the problem of detecting ongoing human action early, i.e. detecting an action as soon as it begins, but before it finishes. My doctoral study aims at training a detector to be capable of recognising a human action when only partial action sample is seen. In this talk, I will present the proposed methodology, share my research findings and provide insights on the potential future research.