Template co-updating in multi-modal human activity recognition systems
Annalisa Franco, Antonio Magnani, Dario Maio · 2020
Multi-modal systems are quite common in the context of human activity recognition since widely used RGB-D sensors give access to parallel data streams (RGB, depth, skeleton). This paper is aimed at defining a general framework for unsupervised template updating in multi-modal systems, where the different data sources can provide complementary information, increasing the effectiveness of the updating procedure and reducing at the same time the probability of incorrect template modifications.