Hiroshi Mo

Topic threading for structuring a large-scale news video archive

We are building a broadcast news video archive where topics of interest can be retrieved and tracked easily. This paper introduces a structuring method applied to the accumulated news videos. First they are segmented into topic units and then threaded according to their mutual relations. A user interface for topic thread-based news video retrieval is also introduced. Since the topic thread structure is formed so that it has fewer number of emerging links from each topic than a simple link structure of related topics, it should lessen the tedious selection during a tracking process by a user. Although evaluation of the effect of threading and user study on the interface is yet to be done, we have found the interface informative to understand the details of a topic of interest.

Drawing image understanding system with capability of rule learning

A drawing understanding system using state transition models is described. This system performs flexible understanding following bottom-up and top down rules, which are easily derived. However, the system is sensitive to minor changes in drawings and has difficulty determining threshold values. A rule learning facility for overcoming these problems was added and evaluated. The system can generate rules from interactions with users using a machine learning method. It was confirmed that this system can generate proper rules for practical drawing understanding from plain interactions.<<ETX>>

Multi layer video object database based on interactive annotation and its application

As the use of applications employing video contents becomes widespread, it is crucial for representation systems to be able to handle video effectively and flexibly. The authors propose a method that has enriched video contents and an application for future interactive TV service, called Advanced Database TV (ADTV). The system requires three basic methods: one is a video handling method based on video objects; another is a construction method of a video object database achieved by feature extraction and tracking of objects; and the third is a protocol for delivery annotations of objects which are given by users. The objective is to provide a multi-layer video object database based on users interactive description of video objects. The database will have the ability to organize incomplete descriptions of video objects in each frame, mainly annotation, position and motion. We have implemented the prototype system, which provides user functions such as semi-automatic enrichment of annotations, similarity retrieval of objects, and semantic indexing, based on the video object database.

Unsupervised Estimation of Video Continuity Model from Large-Scale Video Archives and Its Application to Shot Boundary Detection

Video data is a sequence of video frames and their temporal continuity is an essential property of video stream. In this paper, we present a framework of constructing video continuity model from large-scale video archives with unsupervised learning. Our method estimates the similarity distribution of continuous frame pairs by applying simple assumption on the minimum duration of continuous video segments and then determines discontinuous frame pairs as outliers. The optimal estimation is pursued with measuring the separation between the estimated distribution of continuous frame pairs and that of discontinuous frame pairs. In order to verify the validity of the obtained model, the model is applied to the shot boundary detection. The results of experimental evaluation demonstrate the feasibility and the effectiveness of our method.