Extraction of Motion Change Points Based on the Physical Characteristics of Objects
Extraction of Motion Change Points Based on the Physical Characteristics of Objects
复制标题
DOI：
10.1109/prml59573.2023.10348369
复制
发表时间：
2023-08
期刊：
影响因子：
--
通讯作者：
Eri Kuroda;Ichiro Kobayashi
中科院分区：
文献类型：
--
作者：
Eri Kuroda;Ichiro Kobayashi
最近，人工智能通过直觉物理的能力来理解现实世界变得越来越重要，直觉物理是我们天生的理解现实世界的能力。以往许多旨在理解真实世界的研究都是基于图像推理来识别真实世界，通常是基于图像特征的推理或图像中物体的识别。相比之下，我们提出了一个模型来获取和预测现实世界运动的变化点，该变化点由图嵌入表示的观察对象的物理关系的潜在层次结构表示。我们在cleverer数据集[1]上进行了运动变化点检测和预测变化点提取的实验，发现所提出的模型被正确训练为预测变化点提取模型。
Recently, it has become increasingly important for artificial intelligence to understand the real world through the ability of intuitive physics, which is our innate ability to understand the real world. Many previous studies aiming at real-world understanding have based image inference for real world recognition, usually based on inference from image features or recognition of objects in an image. In contrast, we propose a model to obtain and predict the change points of real-world motions represented by the potential hierarchical structure of the physical relations of the observed objects represented by graph embeddings. We conducted experiments on the CLEVRER dataset [1] to detect motion change points and extract predictive change points, and found that the proposed model is correctly trained as a predictive change point extraction model.