• Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This research proposes a novel method to extract image regions of products from an advertisement video, by analyzing features which are completely independent from the target object. Namely, we focus on how each product is emphasized in the video production, and propose the utilization of low-level visual features which leverage the technical know-how of video producers. By using such features, our proposal can achieve highly accurate detection of temporal and spatial locations of the advertised products, regardless of the product domain. Evaluation of the proposed method has been conducted with the actual advertisement video, in which accuracy of 79.4% in F­ measure has been achieved.
    Proceedings of the 2011 IEEE International Conference on Multimedia and Expo, ICME 2011, 11-15 July, 2011, Barcelona, Catalonia, Spain; 01/2011
  • [Show abstract] [Hide abstract]
    ABSTRACT: The automatic recording function of DVR is a powerful tool for users. However, increase of the stored content makes it difficult to access desired content. To solve this issue, this paper proposes a new method of providing suitable thumbnails of TV programs by detecting important objects from them. Our approach is based on identifying typical shooting and editing techniques, which are estimated from camera motion and visual features density. The proposed method is independent of types of target object and it achieves detection accuracy of about 79%, which outperforms the existing object-dependent approaches. The method is applied to the prototype application on the DVR. It enables the user to find desired content intuitively and access important scenes easily.
    IEEE Transactions on Consumer Electronics 06/2010; · 1.09 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Content-based copy detection (CBCD) recently has appeared a promising technique for video monitoring and copyright protection. In this paper, a novel framework for CBCD is proposed. Robust global features and local Speeded Up Robust Features (SURF) are first combined to describe video contents, and the density sampling method is proposed to improve the generation of visual codebook. Secondly, Smith-Waterman algorithm is introduced to find the similar video segments, meanwhile, a video matching method based on visual codebook is proposed to calculate the similarity of copy videos. Finally, a hierarchical fusion scheme is used to refine the detection results. Experiments on TRECVID dataset show that the proposed framework gives better results than the average results of CBCD task in TRECVID 2008.


Available from