NSF/ARPA Workshop on Visual Information Management Systems

这个讲习班将于1995年6月19日与在马萨诸塞州剑桥的麻省理工学院举行的ICCV会议一起举行。研讨会的目的是将在过去几年中开始解决视觉信息管理（VIM）问题的研究人员聚集在一起。然而，这些努力大多集中在问题的一个小方面或一个非常狭窄的应用上。显然，视觉信息管理系统包括数据库、图像处理和图像理解、非常复杂的接口、网络和存储系统、基于知识的系统、压缩和解压缩以及面向对象的系统等核心方面。如果不解决这些问题中的大多数，就只能解决理论问题，或者只能在一个在实用性和可扩展性方面极其狭窄的微观世界中工作。考虑到组织和检索视觉和其他非字母数字信息的需求和兴趣日益增长，以及这一领域的学术项目数量不足，视觉信息管理系统讲习班将提供一个急需的平台。虽然VIM是一个非常广泛的领域，但研讨会的重点是计算机视觉研究人员可以做出什么贡献。视觉研究人员面临的挑战是开发工具来分析视频和图像的语义内容，然后以一种可以有效搜索和比较的方式表示这些内容，最后以有用的、集中的呈现形式将这些内容传递给用户。计算机视觉可以提供半自动和自动提取特征的技术，这些特征对于图像和视频数据库的索引和查询公式至关重要。计算机视觉研究人员已经解决了人类和机器人视觉中的几个应用问题，但很少有人关注这个新兴领域。本工作坊将探讨为视觉资讯管理系统提供基本基础的电脑视觉技术。

This workshop will be held on June 19, 1995, in conjunction with the ICCV conference at MIT in Cambridge, Mass. The objective of the workshop is to bring together researchers who in the last few years have started addressing problems in Visual Information Management (VIM). Most of these efforts, however, were focussed either on only a small aspect of the problem or a very narrow application. Clearly, visual information management systems encompass central aspects of databases, image processing and image understanding, very sophisticated interfaces, networks and storage systems, knowledge based systems, compression and decompression, and object oriented systems. Without addressing most of these issues, one may either address only theoretical issues, or may work in a microcosm that will, at best, be extremely narrow in its utility and extensibility. Considering the growing need and interest in the organization and retrieval of visual and other non-alphanumeric information, and the insufficient number of academic projects in this area, the workshop on visual information management systems will provide a much needed platform. While VIM is a very broad area, the focus of the workshop is on what researchers in computer vision could contribute. The challange for vision researchers is to develop tools for analyzing the semantic content of video and image, and then representing that content in a way that can be efficiently searched and compared, and finally delivering that content to users in the form a of useful, focused presentation. Computer vision can contribute techniques for semiautomatically and automatically extracting features that will be essential for indexing and query formulation in image and video databases. Computer vision researchers have addressed problems in human and robotic vision for several applications, but very little attention has been given to this new emerging field. This workshop will be exploring computer vision techniques which are going to prov ide the basic foundation for visual information management systems.