Reasoning about Object Affordances in a Knowledge Base Representation
Reasoning about Object Affordances in a Knowledge Base Representation
复制标题
DOI：
10.1007/978-3-319-10605-2_27
复制
发表时间：
2014-09
期刊：
影响因子：
--
通讯作者：
Yuke Zhu;A. Fathi;Li Fei-Fei-Li-Fei-Fei-48004138
中科院分区：
文献类型：
--
作者：
Yuke Zhu;A. Fathi;Li Fei-Fei-Li-Fei-Fei-48004138
关于物体及其启示的推理是视觉智能的一个基本问题。以前的大多数工作都将此问题视为分类任务，其中单独的分类器被训练来标记对象，识别属性或分配启示。在这项工作中，我们考虑使用知识库表示的对象启示推理的问题。对象的各种信息首先从图像和其他元数据源中获得。然后，我们使用马尔可夫逻辑网络（MLN）学习知识库（KB）。鉴于学习的知识库，我们表明，可以在这个统一的框架中完成各种各样的视觉推理任务，而无需训练单独的分类器，包括零杆启示预测和给定人类姿势的对象识别。
Reasoning about objects and their affordances is a fundamental problem for visual intelligence. Most of the previous work casts this problem as a classification task where separate classifiers are trained to label objects, recognize attributes, or assign affordances. In this work, we consider the problem of object affordance reasoning using a knowledge base representation. Diverse information of objects are first harvested from images and other meta-data sources. We then learn a knowledge base (KB) using a Markov Logic Network (MLN). Given the learned KB, we show that a diverse set of visual inference tasks can be done in this unified framework without training separate classifiers, including zero-shot affordance prediction and object recognition given human poses.