An Unsupervised Framework for Action Recognition Using Actemes

Abstract. In speech recognition, phonemes have demonstrated their efficacy to model the words of a language. While they are well defined for languages, their extension to human actions is not straightforward. In this paper, we study such an extension and propose an unsupervised framework to find phoneme-like units for actions, which we call actemes, using 3D data and without any prior assumptions. To this purpose, build on an earlier proposed framework in speech literature to automatically find actemes in the training data. We experimentally show that actions defined in terms of actemes and actions defined by whole units give similar recognition results. We define actions out of the training set in terms of these actemes to see whether the actemes generalize to unseen actions. The results show that although the acteme definitions of the actions are not always semantically meaningful, they yield optimal recognition accuracy and constitute a promising direction of research for action mod...

• Type: Journal
• Year: 2010
• Where: ACCV
• Authors: Kaustubh Kulkarni, Edmond Boyer, Radu Horaud, Amit Kale
• Keywords: ACCV 2010, Computer Vision, Earlier Proposed Framework, Human Actions, Optimal Recognition Accuracy