An Adversarial Framework For Op En-Set Human Action Recognition Using Skeleton Data

Human action recognition is a fundamental problem which is applied in various domains, and it is widely studied in the literature. Majority of the studies model action recognition as a closed-set problem. However, in real-life applications it usually arises as an op en-set problem where a set of actions are not available during training but are introduced to the system during testing. In this study, we propose an op en-set action recognition system, human action recognition and novel action detection system (HARNAD), which consists of two stages and uses only 3D skeleton information. In the first stage, HARNAD recognizes a given action and in the second stage it decides whether the action really belongs to one of the a priori known classes or if it is a novel action. We evaluate the performance of the system experimentally both in terms of recognition and novelty detection. We also compare the system performance with state-of-the-art op en-set recognition methods. Our experiments show that HARNAD is compatible with state-of-the-art methods in novelty detection, while it is superior to those methods in recognition.