Learning a Deep Model for Human Action Recognition from Novel Viewpoints
This addresses the challenge of viewpoint invariance in human action recognition for applications like surveillance and robotics, representing a novel method for a known bottleneck.
The paper tackles the problem of recognizing human actions from novel viewpoints by proposing a Robust Non-Linear Knowledge Transfer Model (R-NKTM), a deep neural network that transfers action knowledge to a shared virtual view without needing camera viewpoint information, and it outperforms state-of-the-art methods on three benchmark datasets.
Recognizing human actions from unknown and unseen (novel) views is a challenging problem. We propose a Robust Non-Linear Knowledge Transfer Model (R-NKTM) for human action recognition from novel views. The proposed R-NKTM is a deep fully-connected neural network that transfers knowledge of human actions from any unknown view to a shared high-level virtual view by finding a non-linear virtual path that connects the views. The R-NKTM is learned from dense trajectories of synthetic 3D human models fitted to real motion capture data and generalizes to real videos of human actions. The strength of our technique is that we learn a single R-NKTM for all actions and all viewpoints for knowledge transfer of any real human action video without the need for re-training or fine-tuning the model. Thus, R-NKTM can efficiently scale to incorporate new action classes. R-NKTM is learned with dummy labels and does not require knowledge of the camera viewpoint at any stage. Experiments on three benchmark cross-view human action datasets show that our method outperforms existing state-of-the-art.