RI: Small: Temporal Causality For Video Event Analysis
RI: Small: Temporal Causality For Video Event Analysis
批准号:
1016772
负责人:
James Rehg
金额:
$45.58万
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
2010
资助国家:
美国
项目状态:
已结题
起止时间:
2010-09-01 至 2014-08-31
中文摘要
该项目正在寻求一种新的策略,通过利用时间因果关系的统计测试来分析视频中的时间结构。其动机是需要无监督的视频分析方法,不需要一个预定义的视频类别集或标记的例子的大型语料库。我们的出发点是经典的格兰杰因果关系公式,它为两个时间序列之间的直接影响提供了一个原则性的统计检验。对经典的成对格兰杰检验进行了改进,得到了一种适用于视频事件的多点过程检验方法。使用这种表示,正在开发的方法分组的视觉单词集的基础上,随着时间的推移,他们的互动。这导致了一种新的自下而上的分割方法,可以识别视觉词之间的相互作用,而无需监督。另一个目标是开发一种综合方法来建模视觉事件和识别因果关系。额外的努力旨在开发新的功能,从因果关系构建的目标,提高分类和检索任务的性能。总之,该项目正在开发新的无监督方法,用于基于时间因果分析来表示和分割视频。由此产生的算法在视频检索和分类任务中提高了性能,并提供了组织和搜索非结构化内容(如YouTube视频)的新方法。用于视频分割和分类的新数据集正在沿着一个分析软件库一起开发,以促进研究界的采用。
英文摘要
This project is pursuing a novel strategy for the analysis of temporal structure in video through the exploitation of statistical tests of temporal causality. The motivation is the need for unsupervised video analysis methods which do not require a pre-defined set of video categories or a large corpus of labeled examples. The starting point is the classical formulation of Granger causality, which provides a principled statistical test for directed influence between two time series. Modifying the classical pair-wise Granger test leads to a method which is suitable for video events, which are represented as multiple point processes. Using this representation, methods are being developed for grouping visual words into sets based on their interaction over time. This results in a novel bottom-up segmentation approach which can identify interactions between visual words without supervision. A further goal is the development of an integrated approach to modeling visual events and identifying causal relations. Additional efforts are aimed at developing novel features constructed from causal relations with the goal of improved performance on categorization and retrieval tasks. In summary, the project is developing new unsupervised methods for representing and segmenting video based on temporal causal analysis. The resulting algorithms yield improved performance in video retrieval and categorization tasks, and provide new approaches to organizing and searching unstructured content such as YouTube videos. Novel datasets for video segmentation and categorization are being developed along with a library of analysis software to facilitate adoption by the research community.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
CRI: CI-EN: Collaborative Research: mResearch: A platform for Reproducible and Extensible Mobile Sensor Big Data Research
-
批准号:1823201
-
项目类别:Standard Grant
-
资助金额:$22.5万
-
财政年份:2018
-
负责人:James Rehg
-
依托单位:
I-CORPS: First Person Visual Analytics
-
批准号:1600474
-
项目类别:Standard Grant
-
资助金额:$5.0万
-
财政年份:2016
-
负责人:James Rehg
-
依托单位:
Comp Cog: Collaborative Research on the Development of Visual Object Recognition
-
批准号:1524565
-
项目类别:Continuing Grant
-
资助金额:$31.36万
-
财政年份:2015
-
负责人:James Rehg
-
依托单位:
RI: Small: A Compositional Approach to Video Segmentation
-
批准号:1320348
-
项目类别:Standard Grant
-
资助金额:$48.34万
-
财政年份:2013
-
负责人:James Rehg
-
依托单位:
Collaborative Research: Automating the Large-Scale Measurement of Insect Behavior
-
批准号:0960618
-
项目类别:Continuing Grant
-
资助金额:$78.49万
-
财政年份:2010
-
负责人:James Rehg
-
依托单位:
Collaborative Research: Sino-USA Summer School in Vision, Learning, Pattern Recognition VLPR 2010
-
批准号:1037845
-
项目类别:Standard Grant
-
资助金额:$2.5万
-
财政年份:2010
-
负责人:James Rehg
-
依托单位:
Collaborative Research: Computational Behavioral Science: Modeling, Analysis, and Visualization of Social and Communicative Behavior
-
批准号:1029679
-
项目类别:Continuing Grant
-
资助金额:$325.07万
-
财政年份:2010
-
负责人:James Rehg
-
依托单位:
Collaborative Research:Creating Dynamic Social Network Models from Sensor Data
-
批准号:0433012
-
项目类别:Standard Grant
-
资助金额:$16.05万
-
财政年份:2004
-
负责人:James Rehg
-
依托单位:
ITR: Analysis of Complex Audio-Visual Events Using Spatially Distributed Sensors
-
批准号:0205507
-
项目类别:Continuing Grant
-
资助金额:$106.57万
-
财政年份:2002
-
负责人:James Rehg
-
依托单位:
CAREER: Motion Capture from Movies: Video-Based Tracking and Modeling of Human Motion
-
批准号:0133779
-
项目类别:Continuing Grant
-
资助金额:$37.0万
-
财政年份:2002
-
负责人:James Rehg
-
依托单位:
Interdisciplinary Automated Manufacturing Laboratory for theElectro-Mechanical Engineering Technology Program
-
批准号:9651001
-
项目类别:Standard Grant
-
资助金额:$5.03万
-
财政年份:1996
-
负责人:James Rehg
-
依托单位:
Process Control Laboratory Exercises
-
批准号:8162786
-
项目类别:Standard Grant
-
资助金额:$1.33万
-
财政年份:1981
-
负责人:James Rehg
-
依托单位:
Course Improvement Through Equipment Integration
-
批准号:7814652
-
项目类别:Standard Grant
-
资助金额:$0.4万
-
财政年份:1978
-
负责人:James Rehg
-
依托单位:
国内基金
海外基金
登录
查看更多内容
昼夜节律性small RNA在血斑形成时间推断中的法医学应用研究
-
批准号:
-
项目类别:省市级项目
-
资助金额:--
-
批准年份:2024
-
负责人:
-
依托单位:
tRNA-derived small RNA上调YBX1/CCL5通路参与硼替佐米诱导慢性疼痛的机制研究
-
批准号:
-
项目类别:省市级项目
-
资助金额:10.0万元
-
批准年份:2022
-
负责人:张祥忠
-
依托单位:
Small RNA调控I-F型CRISPR-Cas适应性免疫性的应答及分子机制
-
批准号:32000033
-
项目类别:青年科学基金项目
-
资助金额:24.0万元
-
批准年份:2020
-
负责人:林平
-
依托单位:
Small RNAs调控解淀粉芽胞杆菌FZB42生防功能的机制研究
-
批准号:31972324
-
项目类别:面上项目
-
资助金额:58.0万元
-
批准年份:2019
-
负责人:高学文
-
依托单位:
变异链球菌small RNAs连接LuxS密度感应与生物膜形成的机制研究
-
批准号:81900988
-
项目类别:青年科学基金项目
-
资助金额:21.0万元
-
批准年份:2019
-
负责人:毛梦莹
-
依托单位:
肠道细菌关键small RNAs在克罗恩病发生发展中的功能和作用机制
-
批准号:31870821
-
项目类别:面上项目
-
资助金额:56.0万元
-
批准年份:2018
-
负责人:陈江宁
-
依托单位:
基于small RNA 测序技术解析鸽分泌鸽乳的分子机制
-
批准号:31802058
-
项目类别:青年科学基金项目
-
资助金额:26.0万元
-
批准年份:2018
-
负责人:麻慧
-
依托单位:
Small RNA介导的DNA甲基化调控的水稻草矮病毒致病机制
-
批准号:31772128
-
项目类别:面上项目
-
资助金额:60.0万元
-
批准年份:2017
-
负责人:吴建国
-
依托单位:
基于small RNA-seq的针灸治疗桥本甲状腺炎的免疫调控机制研究
-
批准号:81704176
-
项目类别:青年科学基金项目
-
资助金额:20.0万元
-
批准年份:2017
-
负责人:赵继梦
-
依托单位:
水稻OsSGS3与OsHEN1调控small RNAs合成及其对抗病性的调节
-
批准号:91640114
-
项目类别:重大研究计划
-
资助金额:85.0万元
-
批准年份:2016
-
负责人:何祖华
-
依托单位: