论文标题
人类行为建模中的持续性二元性
Persistent-Transient Duality in Human Behavior Modeling
论文作者
论文摘要
我们建议使用亲子多频道神经网络对人类行为的持续性二元性进行建模，该神经网络具有父母持久的通道，该通道可以管理全局动力学和儿童瞬态通道，这些通道被启动并按需终止以处理详细的交互式动作。短寿命的瞬态会话由建议的瞬态开关管理。对神经框架进行了训练，可以自动发现双重性的结构。我们的模型在人类对象相互作用运动预测中显示出卓越的性能。
We propose to model the persistent-transient duality in human behavior using a parent-child multi-channel neural network, which features a parent persistent channel that manages the global dynamics and children transient channels that are initiated and terminated on-demand to handle detailed interactive actions. The short-lived transient sessions are managed by a proposed Transient Switch. The neural framework is trained to discover the structure of the duality automatically. Our model shows superior performances in human-object interaction motion prediction.
