Domain and View-point Agnostic Hand Action Recognition
share
Hand action recognition is a special case of human action recognition with applications in human robot interaction, virtual reality or life-logging systems. Building action classifiers that are useful to recognize such heterogeneous set of activities 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. We demonstrate the performance of our proposed motion representation model both working for a single specific domain (intra-domain action classification) and working for different unseen domains (cross-domain action classification). For the intra-domain case, our approach gets better or similar performance than current state-of-the-art methods on well-known hand action recognition benchmarks. And when performing cross-domain hand action recognition (i.e., training our motion representation model in frontal-view recordings and testing it both for egocentric and third-person views), our approach achieves comparable results to the state-of-the-art methods that are trained intra-domain.
READ FULL TEXT