CVMar 3, 2021

Domain and View-point Agnostic Hand Action Recognition

arXiv:2103.02303v328 citations
AI Analysis

This work addresses the problem of robust hand action recognition for applications like human-robot interaction and virtual reality, though it appears incremental as it builds on existing skeleton-based methods.

The paper tackles the challenge of hand action recognition across heterogeneous domains and camera viewpoints by introducing a skeleton-based hand motion representation model, achieving comparable performance to state-of-the-art methods in cross-domain classification without domain-specific training.

Hand action recognition is a special case of action recognition with applications in human-robot interaction, virtual reality or life-logging systems. Building action classifiers able to work for such heterogeneous action domains is very challenging. There are very subtle changes across different actions from a given application but also large variations across domains (e.g. virtual reality vs life-logging). This work introduces a novel skeleton-based hand motion representation model that tackles this problem. The framework we propose is agnostic to the application domain or camera recording view-point. When working on a single domain (intra-domain action classification) our approach performs better or similar to current state-of-the-art methods on well-known hand action recognition benchmarks. And, more importantly, when performing hand action recognition for action domains and camera perspectives which our approach has not been trained for (cross-domain action classification), our proposed framework achieves comparable performance to intra-domain state-of-the-art methods. These experiments show the robustness and generalization capabilities of our framework.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes