基于张量表示的直推式多模态视频语义概念检测 - 软件学报.pdfVIP

ISSN 1000-9825, CODEN RUXUEW E-mail: jos@ Journal of Software , Vol.19, No.11, November 2008, pp.2853−2868 DOI: 10.3724/SP.J.1001.2008.02853 Tel/Fax: +86-10 © 2008 by Journal of Software . All rights reserved. ∗ 基于张量表示的直推式多模态视频语义概念检测 + 吴 飞 , 刘亚楠, 庄越挺 (浙江大学 计算机科学与技术学院 数字媒体计算与设计实验室,浙江 杭州 310027) Transductive Multi-Modality Video Semantic Concept Detection with Tensor Representation + WU Fei , LIU Ya-Nan, ZHUANG Yue-Ting (Digital Media Computing Design Lab., College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China) + Corresponding author: E-mail: wufei@ Wu F, Liu YN, Zhuang YT. Transductive multi-modality video semantic concept detection with tensor representation. Journal of Software, 2008,19(11):2853−2868. /1000-9825/19/2853.htm Abstract : A higher-order tensor framework for video analysis and understanding is proposed in this paper. In this framework, image frame, audio and text are represented, which are the three modalities in video shots as data points by the 3rd-order tensor. Then a subspace embedding and dimension reduction method is proposed, which explicitly considers the manifold structure of the tensor space from temporal-sequenced associated co-occurring multimodal media data in video. It is called TensorShot approach. Transductive learning uses a large amount of unlabeled data together with the labeled data to build better classifiers. A transductive support tensor machines algorithm is proposed to train effective classifier. This algorithm preserves the intrinsic structure of the