Learn More
Visual attention analysis provides an alternative methodology to semantic image understanding in many applications such as adaptive content delivery and region-based image retrieval. In this paper, we propose a feasible and fast approach to attention area detection in images based on contrast analysis. The main contributions are threefold: 1) a new saliency(More)
Automatic generation of video summarization is one of the key techniques in video management and browsing. In this paper, we present a generic framework of video summarization based on the modeling of viewer's attention. Without fully semantic understanding of video content, this framework takes advantage of understanding of video content, this framework(More)
Due to the information redundancy of video, automatically extracting essential video content is one of key techniques for accessing and managing video library. In this paper, we present a generic framework of User Attention Model, which estimates the attentions viewers may pay to video contents when watching videos. Based on user attention model, video(More)
—In this paper, we propose a unified approach for video summarization based on the analysis of video structures and video highlights. Two major components in our approach are scene mod-eling and highlight detection. Scene modeling is achieved by normalized cut algorithm and temporal graph analysis, while highlight detection is accomplished by motion(More)
We propose a unified approach for summarization based on the analysis of video structures and video highlights. Our approach emphasizes both the content balance and perceptual quality of a summary. Normalized cut algorithm is employed to globally and optimally partition a video into clusters. A motion attention model based on human perception is employed to(More)
The video track is added into TREC-10, composed of two tasks, automatic shot boundary detection and video retrieval. In this year, we (MSR-Asia) participated in the video track, focusing on shot boundary detection task. Our work is to find out all of boundaries the shot changes by a fast algorithm based on uncompressed domain. In our algorithm, all of(More)