CAREER: Discriminative Spatiotemporal Models for Recognizing Humans, Objects, and their Interactions

职业：识别人类、物体及其交互的判别时空模型

• 批准号: 1551290
• 负责人: Deva Ramanan
• 金额: $ 10.6万
• 依托单位: Carnegie-Mellon University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-09-01 至 2016-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1551290&HistoricalAwards=false
• 关键词: CAREER; Discriminative; Spatiotemporal; Models; Recognizing

One of the goals of computer vision is to build a system that can see people and recognize their activities. Human actions are rarely performed in isolation -- the surrounding environment, nearby objects, and nearby humans affect the nature of the performed activity.Examples include actions such as "eating" and "shaking hands." The research goal of this project is to approach human performance in understanding videos of activities defined by human-object and human-human interactions.This project makes use of structured, contextual representations to make predictions given spatiotemporal data. It does so by extending recent successful work on object recognition to the space-time domain, introducing extensions for spatiotemporal grouping and contextual modeling. Video enables the extraction of additional dynamic cues absent in static images, but this poses additional computational burdens that are addressed through algorithmic innovations for approximate parsing and large-scale discriminative learning.To place activity recognition on firm quantitative ground, the proposed models are evaluated using concrete metrics based on activities of daily living (ADL) and human proxemic models from the medical and anthropological communities. Examples include systems for automated monitoring of stroke patients interacting with everyday objects and automated analysis of crisis response team interactions during emergency drills. This project produces non-scripted, real-world, labeled action recognition datasets, of benefit to the research community as a whole.

计算机视觉的目标之一是建立一个可以看到人们并认识其活动的系统。人类的行为很少是孤立的 - 周围环境，附近的物体和附近的人类会影响执行活动的性质。例子包括诸如“饮食”和“握手”之类的动作。该项目的研究目标是在理解人类对象和人类互动定义的活动视频时达到人类绩效。本项目利用结构化的上下文表示，以给定时空数据做出预测。它通过将对象识别的最新成功工作扩展到时空域，从而引入了时空分组和上下文建模的扩展。视频可以在静态图像中提取其他动态提示，但这构成了其他计算负担，这些计算负担是通过算法创新来解决的，用于近似解析和大规模歧视性学习。将活动识别置于企业定量基础上，使用基于日常生活模型（ADLECTOM）和人类培训的混凝土量来评估所建议的模型，并在ADLECMONTIC上进行了培训（ADLECTIM）和人类的培训。例如，用于与日常对象相互作用的中风患者自动监测的系统以及在紧急演习期间对危机反应团队互动的自动分析。该项目产生了对整个研究界有益的未录制的，现实世界中标记的行动识别数据集。