Keiichiro Hoashi

Personalization of user profiles for content-based music retrieval based on relevance feedback

Numerous efforts on content-based music information retrieval have been presented in recent years. However, the object of such existing research is to retrieve a specific song from a large music database. In this research, we propose a music retrieval method which retrieves songs based on the users musical preferences. This enables users to discover new songs which they are expected to like. Since music preferences are expected to be highly ambiguous, we propose the implementation of relevance feedback methods to improve the performance of our music information retrieval method. In order to reduce the burden of users to input learning data to the system, we also propose a method to generate user profiles based on genre preferences, and refinement of such profiles based on relevance feedback. Evaluation experiments are conducted based on a corpus of music data with user ratings. Results of these experiments prove the effectiveness of our method.

Robust web page segmentation for mobile terminal using content-distances and page layout information

The demand of browsing information from general Web pages using a mobile phone is increasing. However, since the majority of Web pages on the Internet are optimized for browsing from PCs, it is difficult for mobile phone users to obtain sufficient information from the Web. Therefore, a method to reconstruct PC-optimized Web pages for mobile phone users is essential. An example approach is to segment the Web page based on its structure, and utilize the hierarchy of the content element to regenerate a page suitable for mobile phone browsing. In our previous work, we have examined a robust automatic Web page segmentation scheme which uses the distance between content elements based on the relative HTML tag hierarchy, i.e., the number and depth of HTML tags in Web pages. However, this scheme has a problem that the content-distance based on the order of HTML tags does not always correspond to the intuitional distance between content elements on the actual layout of a Web page. In this paper, we propose a hybrid segmentation method which segments Web pages based on both the content-distance calculated by the previous scheme, and a novel approach which utilizes Web page layout information. Experiments conducted to evaluate the accuracy of Web page segmentation results prove that the proposed method can segment Web pages more accurately than conventional methods. Furthermore, implementation and evaluation of our system on the mobile phone prove that our method can realize superior usability compared to commercial Web browsers.

Document filtering method using non-relevant information profile

Document filtering is a task to retrieve documents relevant to a users profile from a flow of documents. Generally, filtering systems calculate the similarity between the profile and each incoming document, and retrieve documents with similarity higher than a threshold. However, many systems set a relatively high threshold to reduce retrieval of non-relevant documents, which results in the ignorance of many relevant documents. In this paper, we propose the use of a non-relevant information profile to reduce the mistaken retrieval of non-relevant documents. Results from experiments show that this filter has successfully rejected a sufficient number of non-relevant documents, resulting in an improvement of filtering performance.

SVM-Based Shot Boundary Detection with a Novel Feature

This paper describes our new algorithm for shot boundary detection and its evaluation. We adopt a 2-stage data fusion approach with SVM technique to decide whether a boundary exists or not within a given video sequence. This approach is useful to avoid huge feature space problems, even when we adopt many promising features extracted from a video sequence. We also introduce a novel feature to improve detection. The feature consists of two kinds of values extracted from a local frame sequence. One is the image difference between the target frame and that synthesized from the neighbors. The other is the difference between neighbors. This feature can be extracted quickly with a least-square technique. Evaluation of our algorithm is conducted with the TRECVID evaluation framework. Our system obtained a high performance at a shot boundary detection task in TRECVID2005

Constructing a landmark identification system for Geo-tagged photographs based on Web data analysis

In this research, we propose a method to automatically generate a landmark identification system for geo-tagged photographs, based on analysis of various data collected from the Web. The method first conducts Web analysis based on three major procedures: (1) Automatic extraction of pointsof- interest (POIs) based on geographical clustering of geotagged images, (2) Retrieval of landmark candidates for each extracted POI from search results of map search API, and (3) Collection and feature extraction of Web images of the landmark candidates. The system then identifies the landmark which appears in the query geo-tagged photograph, by comparing the location and content-based features of the query with the information accumulated by the previous procedures. Experimental results show that the proposed method is capable to construct a highly accurate landmark identification system by leveraging Web information.

Social Indexing of TV Programs: Detection and Labeling of Significant TV Scenes by Twitter Analysis

Technology to analyze the content of TV programs, especially the extraction and annotation of important scenes and events within a program, is beneficial for users to enjoy recorded programs. In this paper, we propose a method of detecting significant scenes in TV programs and automatically annotating the content of the extracted scenes through Twitter analysis. Experiments conducted on baseball games indicate that the proposed method is capable of detecting major events in a baseball game with an accuracy of 90.6%. Moreover, the names of persons involved in the events were detected with an accuracy of 87.2%, and labels describing the event were applied with an accuracy of 66.8%. The proposed technology is very helpful, because it enables users to skip to the highlights of a recorded program.

Feature Analysis and Normalization Approach for Robust Content-Based Music Retrieval to Encoded Audio with Different Bit Rates

In order to achieve highly accurate content-based music information retrieval (MIR), it is necessary to compensate the various bit rates of encoded songs which are stored in the music collection, since the bit rate differences are expected to apply a negative effect to content-based MIR results. In this paper, we examine how the bit rate differences affect MIR results, propose methods to normalize MFCC features extracted from encoded files with various bit rates, and show their effects to stabilize MIR results.

Query expansion method based on word contribution (poster abstract)

Query expansion (QE) has been considered as one of the most indispensable methods to achieve successful information retrieval. The application of QE lightens the burden imposed on the user, who would otherwise need to generate an effective query by themselves. One of the widely known methods of QE is the method based on Rocchio’s algorithm[2], which is based on the vector space model. While QE based on Rocchio’s algorithm has been proved to achieve excellent performance[l], we believe an even more effective QE can be achieved by applying the discriminativeness of words extracted from relevant documents. This proposed weighting scheme can be implemented by extracting not only the importance of the word in relevant documents, but also the influence of the word to query-document similarity. In this paper, we propose a novel QE method based on a measure called word contribution, and prove its effectiveness by experiments.

Feature Space Modification for Content-Based Music Retrieval Based on User Preferences

This paper proposes a feature space modification method for feature extraction of music, which is effective for the development of a content-based music information retrieval (MIR) system based on user preferences. The proposed method conducts clustering of all songs in the music collection, and utilizes the resulting cluster IDs as training data for feature space modification, and is capable to automatically generate a feature space which is suitable to the content of any music collection. Experiment results prove that the proposed method improves accuracy of user preference based MIR

Video story segmentation and its application to personal video recorders

Video story segmentation, i.e., segmentation of video to semantically meaningful units, is an essential technology for advanced video processing, such as video retrieval, summarization, and so on. In this paper, we will introduce a generic video story segmentation method, which has achieved highly accurate segmentation on both broadcast news and non-news variety TV programs. Furthermore, we will probe the problems which need to be solved in order to implement story segmentation to practical applications.