使用异构互联网图像组的视频标注  

Video Annotation by Using Heterogeneous Multiple Image Groups on the Web

作　　者：王晗[1] 吴心筱[1] 贾云得[1] 

机构地区：[1]北京理工大学计算机学院智能信息技术北京市重点实验室,北京100081

出　　处：《计算机学报》2013年第10期2062-2069,共8页Chinese Journal of Computers

基　　金：国家自然科学基金(61203274);高等学校博士学科点专项科研基金(20121101110035)资助~~

摘　　要：标注用户视频中的事件是一项极具挑战性的工作.目前的研究主要关注如何从大量的已标注视频中获取视频相关概念,并用来标注未知的用户视频.现实场景下的视频具有复杂性和多样性的特点,建模需要收集大量已标注的视频训练样本,这个过程非常费时费力.为了缓解这一问题,作者利用大量互联网图像来建立模型,这些图像数据涵盖了各种环境下的各种事件.然而,从互联网上得到的知识变化多样且有噪声,如果不加选择而盲目进行知识迁移,反而会影响视频标注的效果.因此,作者提出了一种联合组权重学习框架来权衡互联网上不同但相关的图像组,并用这些知识建立视频标注模型.在该框架下,作者采用联合优化的方法来获得不同图像组的权重,每一个权重值表示了相应的图像组在知识迁移中所起的作用.为了解决视频与图像特征的异构问题,作者建立了一个共同特征子空间来连接视频和图像这两个特征空间.两个视频数据库上的实验结果表明了文中方法的有效性.Annotating events in uncontrolled videos is a challenging task. Current researches mainly focus on obtaining concepts from numerous labeled videos. But it is time consuming and labor expensive to collect a large amount of required labeled videos to model events under various circumstances. To alleviate the labeling process, we propose to learn models for videos by levera- ging abundant Web images which cover many roughly annotated events under various conditions. However, knowledge from the Web is noisy and diverse, brute force knowledge transfer may hurt the annotation performance. To address such negative transfer problem, we propose a novel Joint Group Weighting Learning （JGWL） framework to leverage different but related groups of knowledge （source domain） learned from the Web images to real-world videos （target domain）. Under this framework, weights of different groups are learned in a joint optimization problem, and each weight represents how contributive the corresponding image group is to the knowledge transferred to the video. Moreover, to deal with the problem of heterogeneous feature spaces between videos and images, we build a common feature subspace to bridge image and video feature spaces. Experimental results on two challenging video datasets demonstrate that it is effective to use grouped knowledge gained from Web images for video annotation.

关 键 词：知识迁移 视频标注 互联网图像搜索引擎 共同特征子空间 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]