Transductive Learning for Retrieving and Mining Visual Contents

用于检索和挖掘视觉内容的转化学习

• 批准号: 0308222
• 负责人: Ying Wu
• 金额: --
• 依托单位: Northwestern University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2003
• 资助国家: 美国
• 起止时间: 2003-09-01 至 2008-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0308222&HistoricalAwards=false
• 关键词: Transductive; Learning; Retrieving; Mining; Visual

Contemporary visual learning methods for visual content mining tasks are plagued by several critical and fundamental challenges: (1) the unavailability of large annotated datasets prevents effective supervised learning; (2) the variability in different working environments challenges the generalization of inductive learning approaches; and (3) the high-dimensionality of these tasks confronts the efficiency of many existing learning techniques. The goal of this research project is to overcome these challenges by exploring a novel transductive learning approach.The approach provides a unified framework accommodating four subtasks: (1) transduction that integrates unlabelled and labeled data to alleviate the challenge of limited supervision and to enable automatic annotation propagation; (2) model transduction that automatically adapts a learned model to untrained environments for efficient model reuse; (3) co-transduction that facilitates transduction with multi-modalities to handle high-dimensionality in visual data; and (4) co-inference that exploits the interactions among multiple modalities to enable efficient model transduction.The research is linked to educational activities including the development of an integrated course of content-based visual data mining and the development of innovative course projects to engage students inresearch. The project disseminates research to other research communities through organizing workshops and tutorials, and to the general public, minority groups and woman students through creating Open House events.The results of this project will lead to significant improvement on the quality of content-based and object-level multimedia retrieval, will greatly benefit visual recognition that requires large datasets for training and evaluation, will significantly reduce the efforts of training brand new models for un-trained scenarios, and will be very useful in intelligent video surveillance applications thus having a great impact on homeland security. A website, http://www.ece.nwu.edu/~yingwu, contains research results, including demos, constructed benchmark datasets and software can be accessed.

视觉内容挖掘任务的当代视觉学习方法受到几个关键和根本性挑战的困扰：（1）大型注释数据集的不可用性阻碍了有效的监督学习;（2）不同工作环境中的可变性挑战归纳学习方法的推广;以及（3）这些任务的高维性面临许多现有学习技术的效率。本研究的目标是通过探索一种新的转换学习方法来克服这些挑战，该方法提供了一个统一的框架，包含四个子任务：（1）转换，将未标记和标记的数据整合在一起，以减轻有限监督的挑战，并实现自动注释传播;（2）模型转换，其自动地使学习的模型适应于未经训练的环境以用于有效的模型重用;（3）共转导，其促进多模态的转导以处理视觉数据中的高维性;以及（4）利用多种模态之间的相互作用来实现有效的模型转换的协同推理。该研究与教育活动相联系，包括开发内容-基于可视化数据挖掘和创新课程项目的开发，让学生参与研究。该项目通过组织研讨会和教程向其他研究团体传播研究成果，并通过创建开放日活动向公众、少数群体和女学生传播研究成果。该项目的结果将导致基于内容和对象级多媒体检索质量的显著提高，将大大有利于需要大量数据集进行训练和评估的视觉识别，将大大减少为未经训练的场景训练全新模型的工作，并将在智能视频监控应用中非常有用，从而对国土安全产生重大影响。一个网站http：//www.ece.nwu.edu/zhiyingwu载有研究成果，包括演示、构建的基准数据集和软件。