arXiv cs.CL· Vivian Liu, Lydia Chilton·· 12 小时前AI 评分21
fog：通过代码分层函数组合为 Heider-Simmel 动画生成富有表现力的运动
fog: Generating Expressive Motion through Layered Function Composition of Code for Heider-Simmel Animation
AI 导读
fog 是一个分层函数组合框架，可生成用于 Heider-Simmel 风格动画的运动函数，帮助用户为动词、副词和情感生成函数，以刻画运动的轨迹、方式与感受。该框架配有动画编辑器，支持用户以标记、箭头和路径提供空间上下文。在 n=12 的混合方法用户研究中，fog 能通过传递用户标注和绘制的空间上下文，并给予用户更多控制维度来提供支持。
正文 · 原文
Abstract:Motion and emotion are core parts of intelligent, expressive behavior. In this paper, we introduce fog, a layered function composition framework for generating motion functions. We demonstrate how fog can be used to express motion and emotion in Heider-Simmel style animations. This code generation framework can help users generate functions for verbs, adverbs, and emotions to capture the trajectory, manner, and feeling of motion. It is complemented by an animation editor that helps users provide spatial context in the form of marks, arrows, and paths. We evaluate our approach with a technical evaluations investigating different function generation and composition setups. In a mixed-methods user study (n=12), we find that fog can support users can support users by relaying spatial context they mark and draw and giving them more dimensions for control.
| Subjects: | Human-Computer Interaction (cs.HC); Computation and Language (cs.CL) |
| Cite as: | arXiv:2607.07952 [cs.HC] |
| (or arXiv:2607.07952v2 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2607.07952 arXiv-issued DOI via DataCite |
Submission history
From: Vivian Liu [view email]
[v1]
Wed, 8 Jul 2026 22:09:03 UTC (890 KB)
[v2]
Fri, 30 Oct 2026 23:34:25 UTC (3,347 KB)
来源：arXiv cs.CL · arxiv.org