A Review on Multimodal Fusion Method for Gesture Recognition

Recent research using deep learning has been actively conducted in various fields, including computer vision, reinforcement learning, classifiers, and more. AlphaGo, which learned to play Go and beat professional players, was developed based on reinforcement learning research. This paper focuses on computer vision in particular, which also has multiple subfields such as image restoration and image compression. This paper examines the use of deep learning with video data in computer vision. Video data can be divided into RGB and Depth, and the fusion of these two types of data will be used, referred to as multimodal fusion. By reviewing several papers, this method will be applied to gesture recognition research for potential improvements.