arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.06073cs.CV
收藏

动态场景中基于对象的扫视决策的模块化框架

A modular framework for object-based saccadic decisions in dynamic scenes

Exzellenzcluster Science of Intelligence(智能科学卓越集群);Technische Universität Berlin(柏林工业大学)

Nicolas Roth, Pia Bideau, Olaf Hellwich, Martin Rolfs, Klaus Obermayer

摘要:

视觉探索我们周围的世界不是一个被动的过程。相反,随着时间的推移,我们积极探索世界并获取视觉信息。在这里,我们提出了一个新的模型来模拟人类的眼动行为在动态的现实世界的场景。我们将这种主动场景探索建模为顺序决策过程。我们适应流行的漂移-扩散模型(DDM)的感知决策,并将其扩展到多个选项,定义存在于场景中的对象。对于每一个可能的选择,该模型随着时间的推移整合证据,并且一旦证据越过决策阈值就触发决策(扫视眼球运动)。在主动观看的背景下,在决策和基于对象的场景感知之间建立这种明确的联系是高度相关的,在主动观看的背景下,在与外部环境交互的同时不断做出决策。我们通过精心设计的消融研究验证了我们的模型,并探索了模型参数的影响。VidCom数据集上的比较支持所提出的方法的可扩展性。

英文摘要:

Visually exploring the world around us is not a passive process. Instead, we actively explore the world and acquire visual information over time. Here, we present a new model for simulating human eye-movement behavior in dynamic real-world scenes. We model this active scene exploration as a sequential decision making process. We adapt the popular drift-diffusion model (DDM) for perceptual decision making and extend it towards multiple options, defined by objects present in the scene. For each possible choice, the model integrates evidence over time and a decision (saccadic eye movement) is triggered as soon as evidence crosses a decision threshold. Drawing this explicit connection between decision making and object-based scene perception is highly relevant in the context of active viewing, where decisions are made continuously while interacting with an external environment. We validate our model with a carefully designed ablation study and explore influences of our model parameters. A comparison on the VidCom dataset supports the plausibility of the proposed approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑