This paper presents a new medium, called tiling slideshow, to display photos in a tile-like manner, coordinating with the pace of background music. In contrast to the conventional photo slideshow, multiple photos that have similar characteristics are well arranged and displayed at the same layout. Motivated by the concepts of technical writing, each displaying layout is composed of a larger topic photo and several small-size supportive photos. Based on this idea, the proposed tiling slideshow system consists of three major components: image clustering, music analyzer, and layout organizer. Given the limited displaying space, we consider the context and relationship between photos and model the layout organization as a constrainted optimization problem. Experiments on real consumer photograph collections show that the novel displaying method gives users more pleasant browsing experience than the methods that focus only on single photograph display.

This demonstration presents a novel way to systematically display photos and enhance the viewing experience of photo browsing. In contrast to conventional photo slideshow, multiple photos that have similar characteristics are well arranged and displayed at the same layout. Moreover, the displaying pace is coordinated with the beat of the user-selected incidental music. To automatically generate the audiovisual slideshow, we develop a system that consists of three main components: photo analysis, music analysis, and audiovisual composition. Audiovisual content analysis and cross-media synchronization issues are addressed in this work. This novel demonstration is especially suitable to present photos taken in a journey. It vigorously presents the delights of traveling and helps us recall or experience the trip.

In this paper, a hierarchical and multi-modal based news item detection algorithm, which can be viewed as a mid-stage solution between the single-modal and the semantic-based approaches, is proposed for parsing TV news program videos. We investigate the production model of TV news program first and then make use of the so-obtained domain knowledge to develop the proposed algorithm. With the add of multi-modal features, such as volume and zero crossing rate in audios and keyframe and human face in videos, the proposed algorithm showed rather satisfactory results in both precision and recall measures for parsing a 6-hour news program test video.

The paper presents a method to distill the important frames and shots from long duration video clips. It is based on a voluntary choice by the subject (i.e. a top down approach). First, we introduce the concept of importance measurement. We use some predefined detectable events to represent the importance inferred from the semantics of the syntax. Since the event characteristics depend largely on the video sources, we choose news program videos as our analyzing focus. Then we calculate the importance measurement of frames and shots, respectively. Experiments show that a good subjective test result for news items distillation can be obtained, and the average distillation ratios of frames and shots are 13.18% and 41.23%, respectively.

A multi-modal-feature based scene change detection algorithm (which can be viewed as a mid-stage solution between the single-modal-feature- and the semantic-based approaches) is proposed to parse the news programs, effectively.