Towards a Skeleton-Based Action Recognition For Realistic Scenarios
This addresses the gap between structured datasets and real-world applications for service robots, but it is incremental as it highlights limitations without proposing a new solution.
The paper tackled the problem of skeleton-based action recognition for service robots in realistic scenarios, finding that non-augmented and non-normalized data performs comparably on standard test splits but fails on manually collected datasets.
Understanding human actions is a crucial problem for service robots. However, the general trend in Action Recognition is developing and testing these systems on structured datasets. That's why this work presents a practical Skeleton-based Action Recognition framework which can be used in realistic scenarios. Our results show that although non-augmented and non-normalized data may yield comparable results on the test split of the dataset, it is far from being useful on another dataset which is a manually collected data.