Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning
This work addresses the problem of efficient and effective action recognition for applications requiring continual learning, representing an incremental advance in a domain-specific area.
The paper tackles skeleton-based action recognition in continual learning by introducing CHARON, which uses techniques like uniform sampling, interpolation, and masking to maintain consistent performance with improved accuracy and minimized computational overhead, achieving new benchmarks on Split NTU-60 and Split NTU-120 datasets.
The use of skeletal data allows deep learning models to perform action recognition efficiently and effectively. Herein, we believe that exploring this problem within the context of Continual Learning is crucial. While numerous studies focus on skeleton-based action recognition from a traditional offline perspective, only a handful venture into online approaches. In this respect, we introduce CHARON (Continual Human Action Recognition On skeletoNs), which maintains consistent performance while operating within an efficient framework. Through techniques like uniform sampling, interpolation, and a memory-efficient training stage based on masking, we achieve improved recognition accuracy while minimizing computational overhead. Our experiments on Split NTU-60 and the proposed Split NTU-120 datasets demonstrate that CHARON sets a new benchmark in this domain. The code is available at https://github.com/Sperimental3/CHARON.