Model learning for image understanding from video archives

从视频档案中理解图像的模型学习

• 批准号: 17300040
• 负责人: SATOH Shin'ichi
• 金额: $ 10.72万
• 依托单位: National Institute of Informatics
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B)
• 财政年份: 2005
• 资助国家: 日本
• 起止时间: 2005 至 2007
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-17300040/
• 关键词: Image indexing; Image mining; Image recognition model; Clustering; Multimodal analysis

In this study, we address techniques to automatically learn models for image understanding from everyday broadcast video. This is especially useful to realize video content analysis for video archive retrieval and to realize robot vision for interactive robot supporting daily life.For these purposes, it is not necessary to realize very precise visual measurement which is typically used for industrial robots, however, it is desired to identify many various types of objects which ordinary people know as the common sense, or to identify new object which might become new trend. The main goal of the study is to establish the methodology to automatically and dynamically obtain image understanding models from broadcast videos.

在本研究中，我们讨论了从日常广播视频中自动学习图像理解模型的技术。这对于实现用于视频存档检索的视频内容分析和实现用于支持日常生活的交互式机器人的机器人视觉特别有用。为了这些目的，不需要实现通常用于工业机器人的非常精确的视觉测量，然而，期望识别普通人作为常识所知的许多各种类型的对象，或者识别可能成为新趋势的新对象。本研究的主要目的是建立一套自动、动态地从广播视频中获取图像理解模型的方法。

项目成果

A study of intra-model association rules for visual modality representation,

视觉模态表示的模型内关联规则的研究，

• 发表时间: 2007
• 期刊: International Workshop on Content-Based Multimedia Indexing (CBMI2007),
• 作者: Jean Martinet;Shin'ichi Satoh
• 通讯作者: Shin'ichi Satoh

Ent-Boost : Boosting Using Entropy Measure for Robust Object Detection,

Ent-Boost ：使用熵度量进行增强以实现鲁棒目标检测，

• 发表时间: 2006
• 期刊: Proc. of International Conference on Pattern Recognition (ICPR2006)
• 作者: Duy-Dinh Le;Shin'ichi Satoh
• 通讯作者: Shin'ichi Satoh

National Institute of Informatics, Japan at TRECVID : BBC Rushes Summarization

日本国家信息研究所 TRECVID：BBC 急于总结

• 发表时间: 2007
• 期刊: TRECVID BBC Rushes Summarization Workshop, in conjunction with ACM Multimedia
• 作者: Duy-Dinh Le;Shin'ichi Satoh
• 通讯作者: Shin'ichi Satoh

"Boosting Face Retrieval By Using Relevant Set Correlation Clustering,"

“通过使用相关集相关聚类促进人脸检索”

• 发表时间: 2007
• 期刊: International Conference on Multimedia and Expo(ICME2007), Beijing,
• 作者: Duy-Dinh Le;Shin'ichi Satoh;and Michael Houle,
• 通讯作者: and Michael Houle,

Using Topic Concepts for Semantic Video Shots Classification

• DOI: 10.1007/11788034_31
• 发表时间: 2006-07
• 作者: S. Ayache;G. Quénot;J. Gensel;S. Satoh