Structured Models for Human Activity Recognition

人类活动识别的结构化模型

• 批准号: RGPIN-2016-05474
• 负责人: Mori, Gregory
• 金额: $ 4.41万
• 依托单位: Simon Fraser University
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2020
• 资助国家: 加拿大
• 起止时间: 2020-01-01 至 2021-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=708620
• 关键词: Structured; Models; Human; Activity; Recognition

Great strides have been made within computer vision in recent years. Accuracy and capacity for automatic interpretation on a variety of recognition problems -- e.g. object recognition, human action recognition -- have improved dramatically. This progress has been driven by novel problem definitions and representations, the resurgence of powerful machine learning algorithms, and access to large quantities of labeled training data. However, current algorithms lack the capability to produce accurate structured representations that permit detailed scene understanding. For example, reasoning about groups of people in a scene or spatio-temporal relations within a video sequence remain challenging. We propose research to push the state of the art in this area by focusing on: (1) novel deep structured models for recognition and (2) active learning algorithms for facilitating data collection and pushing performance toward 100% correct computer vision.

近年来，计算机视觉领域取得了长足的进步。 自动解释各种识别问题的准确性和能力——例如物体识别、人类动作识别——都得到了显着改善。 这一进步是由新颖的问题定义和表示、强大的机器学习算法的复兴以及对大量标记训练数据的访问推动的。 然而，当前的算法缺乏产生允许详细场景理解的精确结构化表示的能力。 例如，推理场景中的人群或视频序列中的时空关系仍然具有挑战性。 我们提出研究，通过重点关注以下方面来推动该领域的最新技术发展：(1) 用于识别的新颖的深层结构化模型，以及 (2) 用于促进数据收集并将性能推向 100% 正确的计算机视觉的主动学习算法。