Learning a Deep Model for Human Action Recognition from Novel Viewpoints

TL;DR

This paper introduces R-NKTM, a deep neural network that recognizes human actions from novel viewpoints by transferring knowledge from synthetic 3D models to real videos, without re-training for new actions.

Contribution

The paper presents a single, view-invariant deep model trained on synthetic data that generalizes to real videos for cross-view human action recognition without re-training.

Findings

Outperforms existing state-of-the-art methods on benchmark datasets.

Learns from synthetic data without requiring camera viewpoint information.

Scales efficiently to new action classes without re-training.

Abstract

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.