On broadcasted game video analysis: event detection,highlight detection,and highlight forecast

Multimedia Tools and Applications - Efficient access to broadcasted computer game videos is urgently demanded due to the emergence of live streaming platforms. The popularity of game video...     

Cultural difference and visual information on hotel rating prediction

Due to the emergence of hotel social media platforms, how to discover interesting properties and utilize these discovered characteristics in hotel-related applications become important issues. In this work, we extend a large-scale hotel information collection to include heterogeneous hotel information, in order to facilitate multimodal and cross-culture analysis. With this rich dataset, we analyze various correlations between hotel properties and unveil interesting characteristics that would benefit hotel recommendation. We found that travelers from different cultural areas (countries) have different rating behaviors. In addition, beyond the scope of conventional text-based hotel analysis, we utilize visual analysis techniques to analyze hotel’s cover photo, and investigate the relationship between rating behaviors and visual information. We adopt these correlations to predict hotel ratings, and verify that by considering visual information and cultural difference, prediction performance can be improved.     

Modeling spatiotemporal relationships between moving objects for event tactics analysis in tennis videos

Evolution of spatial relationships between objects often provides important clues for semantic video analysis. We present a symbolic representation that describes spatiotemporal characteristics and facilitates tactics detection based on string matching. To find typical spatiotemporal patterns of a targeted tactic, we organize training sequences as a tree, and effectively discover frequent patterns from the structure. Tactics detection is conducted by comparing a given test sequence with these frequent patterns. To realize the proposed idea, we develop elaborate audio/video processes to transform broadcasting tennis videos into symbolic sequences, and comprehensively tackle event detection and tactics analysis. We experiment on ten most important tennis championships in the year 2008, and report promising detection results on seven events/tactics. We demonstrate not only the effectiveness of the proposed methods, but also study the impacts brought by the results of tactics analysis.     

Nanocrystalline ruthenium oxide of fine mesoporosity prepared by templating for electrochemical capacitor applications

Hydrous ruthenium-oxide (RuO_xH_y) particles composed of nanocrystallites of ～5 nm in size were prepared, using hexagonal self-ordered mesoporous SiO₂ (SBA-15) as a template and RuCl₃ as the ruthenium precursor. The material has a highly mesoporous structure with a sharp distribution of fine pores of size around 3–4 nm. A high specific capacitance of 954 F g^?1 for the RuO_xH_y in 1 M H₂SO₄(aq) and a high energy density of 118.9 J g^?1 (or 32.7 W h kg^?1) were obtained from an electrochemical capacitor made with the material. Rectangular shape of the cyclic voltammetry was observed even increasing the scan rate to about 100 mV s^?1.     

Consumer photo management and browsing facilitated by near-duplicate detection with feature filtering

Near-duplicate detection techniques are exploited to facilitate representative photo selection and region-of-interest (ROI) determination, which are important functionalities for efficient photo management and browsing. To make near-duplicate detection module resist to noisy features, three filtering approaches, i.e., point-based, region-based, and probabilistic latent semantic (pLSA), are developed to categorize feature points. For the photos taken in travels, we construct a support vector machine classifier to model matching patterns between photos and determine whether photos are near-duplicate pairs. Relationships between photos are then described as a graph, and the most central photo that best represents a photo cluster is selected according to centrality values. Because matched feature points are often located in the interior or at the contour of important objects, the region that compactly covers the matched feature points is determined as the ROI. We compare the proposed approaches with conventional ones and demonstrate their effectiveness.     

Toward semantic indexing and retrieval using hierarchical audio models

Semantic-level content analysis is a crucial issue in achieving efficient content retrieval and management. We propose a hierarchical approach that models the statistical characteristics of audio events over a time series to accomplish semantic context detection. Two stages, audio event and semantic context modeling, are devised to bridge the semantic gap between physical audio features and semantic concepts. In this work, hidden Markov models (HMMs) are used to model four representative audio events, i.e., gunshot, explosion, engine, and car-braking, in action movies. At the semantic-context level, Gaussian mixture models (GMMs) and ergodic HMMs are investigated to fuse the characteristics and correlations between various audio events. They provide cues for detecting gunplay and car-chasing scenes, two semantic contexts we focus on in this work. The promising experimental results demonstrate the effectiveness of the proposed approach and exhibit that the proposed framework provides a foundation in semantic indexing and retrieval. Moreover, the two fusion schemes are compared, and the relations between audio event and semantic context are studied.     

Toward better retrieval and presentation by exploring cross-media correlations

This paper addresses explicit correlation and implicit correlation between various media streams in a composite multimedia document, the so-called navigated hypermedia document in our language learning system, in order to facilitate document retrieval and synchronized presentation. For replaying a recorded lecture in a form as close as possible to the original classroom experience, we devised a capturing mechanism to explicitly record all the lecturing media streams and relations between them, including instructors voice, slide change of the HTML lectures, and various guiding actions (e.g., tele-pointers, pen strokes, document scrolling, keyword highlighting, and text annotations) on HTML-based slides. In addition, for more effective learning, we study three different aspects - temporal, spatial, and content relation - of the implicit correlations that are inherently hidden between the media involved. The implicit relations are discovered by three designed processes: the speech-text alignment process for temporally synchronized speech-text presentation, the automatic scrolling process for the viewing windows spatial synchronization, and the content dependency checking process to ensure consistency of the content processed and the relations involved. The experimental results show that exploring cross-media correlations is helpful for system development in document presentation and retrieving. Users are allowed to replay a vivid and learning-effective multimedia lecture and to access the desired part of the document very easily via cross-media indexing. Hence the results have been applied to the development of online multimedia language learning systems aimed at improving students English and Chinese language capabilities.Published online: 14 December 2004     

Tiling Slideshow: An Audiovisual Presentation Method for Consumer Photos

The Tiling Slideshow system automatically organizes consumer photos and provides a novel audiovisual presentation. Displaying at the same pace as user-selected music, photos are elaborately manipulated and displayed to mold a novel browsing experience. In contrast to conventional photo slideshows, the proposed presentation provides tighter audiovisual coordination, and offers a more lively viewing experience.     

Explicit semantic events detection and development of realistic applications for broadcasting baseball videos

This paper presents a framework that explicitly detects events in broadcasting baseball videos and facilitates the development of many practical applications. Three phases of contributions are included in this work: reliable shot classification, explicit event detection, and elaborate applications. At the shot classification stage, color and geometric information are utilized to classify video shots into several canonical views. To explicitly detect semantic events, rule-based decision and model-based decision methods are developed. We emphasize that this system efficiently and exactly identifies what happened in baseball games rather than roughly finding some interesting parts. On the basis of explicit event detection, many accurate and practical applications such as automatic box score generation and game summarization could be built. The reported results show the effectiveness of the proposed framework and demonstrate some research opportunities about bridging the semantic gap for sports videos.