RI: Small: Learning and Inference with And-Or Graphs for Image Understanding

RI：小：使用与或图进行学习和推理以实现图像理解

• 批准号: 1018751
• 负责人: Song-Chun Zhu
• 金额: $ 45万
• 依托单位: University of California-Los Angeles
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-08-01 至 2015-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1018751&HistoricalAwards=false
• 关键词: RI; Small; Learning; Inference; Graphs

In this project, the PIs and students study a probabilistic and graphical representation, called the And-or graph (AoG) for visual knowledge representation. This AoG model embodies hierarchical and contextual models for visual objects and scenes and is the key to robust object and scene recognition. More specifically, the project addresses two major technical challenges: (i) Learning the AoG for representing objects and scenes in an unsupervised way; and (ii) Developing effective inference algorithm by scheduling top-down and bottom-up processes to extract semantic contents in a parse graph under the guidance of the AoG. The extracted semantics include the hierarchical decomposition of the image from scene to objects, and parts, as well as the contextual relations. These contents are crucial for filling in the semantic gap in large scale image search and retrieval. The technologies studied in this project are key to a number of applications, such as image content extraction for security surveillance, information gathering, Internet image search, and situation awareness. One specific application studied in this project is autonomous driving assistant for designing safer vehicles and reducing car accidence. The project also supports the training of 3 graduate students over the three year period. Research results are disseminated through public publications in major computer vision conferences and journals, institutional webpages, and shared data sets and code in the Internet.

在这个项目中，PI和学生学习概率和图形表示，称为与或图（AoG）的视觉知识表示。 这个AoG模型体现了视觉对象和场景的层次和上下文模型，是鲁棒的对象和场景识别的关键。更具体地说，该项目解决了两个主要的技术挑战：（i）学习AoG以无监督的方式表示对象和场景;以及（ii）通过调度自顶向下和自底向上的过程来开发有效的推理算法，以在AoG的指导下提取解析图中的语义内容。提取的语义包括图像从场景到对象的层次分解，以及上下文关系。这些内容对于填补大规模图像搜索和检索中的语义空白至关重要。 在这个项目中研究的技术是关键的一些应用，如图像内容提取的安全监视，信息收集，互联网图像搜索和态势感知。该项目研究的一个具体应用是自动驾驶辅助，用于设计更安全的车辆和减少汽车事故。该项目还支持在三年期间培训3名研究生。研究成果通过主要计算机视觉会议和期刊上的公共出版物、机构网页以及互联网上的共享数据集和代码传播。