Transductive Learning for Retrieving and Mining Visual Contents

当前用于视觉内容挖掘任务的视觉学习方法受到几个关键和基本挑战的困扰：(1)大量标注数据集的不可用阻碍了有效的监督学习；(2)不同工作环境中的多样性对归纳学习方法的推广提出了挑战；(3)这些任务的高维面临着许多现有学习技术的效率问题。本研究项目的目的是通过探索一种新的转导学习方法来克服这些挑战。该方法提供了一个统一的框架，包括四个子任务：(1)整合未标记和标记数据的转导，以减轻有限监督的挑战，并实现自动注释传播；(2)模型转导，自动使学习的模型适应未经训练的环境，以实现高效的模型重用；(3)共转导，促进多通道转导，以处理视觉数据中的高维数据；以及(4)协同推理，它利用多种模式之间的相互作用来实现有效的模型转换。研究与教育活动相联系，包括开发基于内容的视觉数据挖掘的综合课程，以及开发创新的课程项目以吸引学生参与研究。该项目通过组织研讨会和教程向其他研究社区传播研究，并通过创建Open House活动向普通公众、少数群体和女学生传播研究。该项目的结果将显著提高基于内容和对象级别的多媒体检索的质量，将极大地有利于需要大量数据集进行训练和评估的视觉识别，将显著减少针对未经训练的场景训练全新模型的努力，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。网站http://www.ece.nwu.edu/~yingwu，包含研究结果，包括演示、构建的基准数据集和软件可以访问。

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.