[2M1-OS-19a] 世界モデルと知能(1/4)

[2M1-OS-19a-02] A Study on Extraction of Motion Inflection Points Focusing on Objects in an Image

〇Eri Kuroda¹, Ichiro Kobayashi¹ (1. Ochanomizu University)

Keywords:Graph Structure, Physical Characteristics, World Model, Variational Temporal Abstraction

The use of machine learning to understand the real world has been one of the most important challenges in recent years. Variational Temporal Abstraction (VTA) is a model that extracts the latent structure of a changing environment from visual information. However, VTA extracts the structure of the changing points of image features, not the latent structure that represents the changing points based on the physical behavior of objects in the image. In this study, we improved VTA to extract the latent structure that represents the change point by expressing the physical relationship based on the behavior of the object in the image expressed as a graph structure. By doing so, we tried to realize world recognition based on the recognition of the physical behavior of objects, as humans do. We also verified the accuracy of judging collision, disappearance, stopping, etc. of objects represented as graphs using the proposed method.