Timezone: »

Unsupervised Learning of View-invariant Action Representations
Junnan Li · Yongkang Wong · Qi Zhao · Mohan Kankanhalli

Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #122

The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data to achieve good performance. However, label collection is an expensive and time-consuming process. In this work, we propose an unsupervised learning framework, which exploits unlabeled data to learn video representations. Different from previous works in video representation learning, our unsupervised learning task is to predict 3D motion in multiple target views using video representation from a source view. By learning to extrapolate cross-view motions, the representation can capture view-invariant motion dynamics which is discriminative for the action. In addition, we propose a view-adversarial training method to enhance learning of view-invariant features. We demonstrate the effectiveness of the learned representations for action recognition on multiple datasets.

Author Information

Junnan Li (National University of Singapore)
Yongkang Wong (National University of Singapore)
Qi Zhao (University of Minnesota)
Mohan Kankanhalli (National University of Singapore,)

More from the Same Authors