Hierarchically Learned View-Invariant Representations for Cross-View Action Recognition

TL;DR

This paper introduces a hierarchical method combining joint sparse representation and distribution adaptation to learn view-invariant features for cross-view action recognition, effectively handling large view differences.

Contribution

It proposes a novel hierarchical approach with joint sparse representation and distribution adaptation for robust cross-view action recognition.

Findings

Outperforms state-of-the-art methods on four multiview datasets.

Effectively reduces distribution differences across views.

Learns view-invariant features robust to large view variations.

Abstract

Recognizing human actions from varied views is challenging due to huge appearance variations in different views. The key to this problem is to learn discriminant view-invariant representations generalizing well across views. In this paper, we address this problem by learning view-invariant representations hierarchically using a novel method, referred to as Joint Sparse Representation and Distribution Adaptation (JSRDA). To obtain robust and informative feature representations, we first incorporate a sample-affinity matrix into the marginalized stacked denoising Autoencoder (mSDA) to obtain shared features, which are then combined with the private features. In order to make the feature representations of videos across views transferable, we then learn a transferable dictionary pair simultaneously from pairs of videos taken at different views to encourage each action video across views to have the same sparse representation. However, the distribution difference across views still exists because a unified subspace where the sparse representations of one action across views are the same may not exist when the view difference is large. Therefore, we propose a novel unsupervised distribution adaptation method that learns a set of projections that project the source and target views data into respective low-dimensional subspaces where the marginal and conditional distribution differences are reduced simultaneously. Therefore, the finally learned feature representation is view-invariant and robust for substantial distribution difference across views even the view difference is large. Experimental results on four multiview datasets show that our approach outperforms the state-ofthe-art approaches.