Search

Social Media allows people to post widely and share the posted online-items. Such items gain their popularity by the amount of attention received. Thus, studies on modeling the arrival process of attention to an individual item have recently attracted a great deal of interest. In this paper, we propose, by combining a Dirichlet process with a Hawkes process in a novel way, a probabilistic model, called cooperative Hawkes process (CHP) model, to discover the cooperative structure among all the items involved. The proposed model takes into account all the arrival processes of shares for those items. We develop an efficient method of inferring the CHP model from the observed sequences of share events, and present an effective framework for predicting the future popularity of each of these items. Using synthetic data and real data from a cooking-recipe sharing site, we demonstrate the effectiveness of the CHP model, and uncover the cooperative structure among cooking-recipes in view of attention dynamics.

We have improved a previously reported method for extracting and judging camerawork for an online training-oriented video-shooting navigation system.It uses video grammar for evaluating user's high-speed camerawork to assist them in effectively shooting video that can be easily edited.High-speed processing is required in the navigation system,so we use a luminance-projection correlation method to extract the camerawork parameters at high speed.However,the accuracy is insufficient.To improve the accuracy,we combined the luminance-projection correlation method with a split tensor histogram method that classifies each frame into one of seven camerawork types.Camerawork analysis results showed that the accuracy was significantly improved.

We aim to develop a video-shooting learning system using video grammar and a real-time,on- and offline navigation system.As an initial step,we have developed an online navigation system that uses video grammar for evaluating users' high-speed camerawork to assist them with effectively shooting shots that can be easily edited.Previous camerawork analysis results showed that by classifying each frame into one of seven camerawork types,high-speed processing accuracy is improved.The system issues three types of alarms depending on the camerawork and the video grammar while a user is shooting that guide the user toward a specified shot.Users thus can naturally acquire a shooting style by trying to decrease the number of alarms and can obtain the specified shot without having to consider the video grammar.

Acquiring a network of trust relations among users in social media sites, e.g., item-review sites, is important for analyzing users' behavior and efficiently finding reliable information on the Web. We address the problem of predicting trustlinks among users for an item-review site. Non-negative matrix factorization (NMF) methods have recently been shown useful for trust-link prediction in such a site where both link and activity information is available. Here, a user activity in an item-review site means posting a review and giving a rating for an item. In this paper, for better trust-link prediction, we propose a new NMF method that incorporates people's evaluation of users' activities as well as trust-links and users' activities themselves. We further apply it to an analysis of users' behavior. Using two real world item-review sites, we experimentally demonstrate the effectiveness of the proposed method.

We aim to develop an automatic contents production system of soccer video commentary based on digital shooting techniques, which consists of digital camera work and digital switching technique. Digital camera work is defined as virtual panning and virtual zooming. Virtual panning is a video production technique of clipping a fixed size frame and then controlling the frame location on a high definition material video. Virtual zooming is a video production technique of clipping a frame and then controlling frame size. Also, digital switching is defined as the change in virtual cameras by controlling the rapid change of frame location or size on a high definition material video. We describe a method of digital camera work that focused on players and a ball as a sub-system of an automatic contents production system for soccer video commentary. This study uses analytic hierarchy process to carry out subjective evaluation of the produced video contents with digital camera work.

Since the advent of the digital era the lack of video coding has been a problem. In order to resolve this problem, the editing work, which takes the most time during the production of video content, must be made more efficient. In general, broadcast video is set up using video grammar, a set of standard principles used for broadcasting any video content. Therefore, in order to make editing work more efficient, a video editing support system which reflects this video grammar must be developed. In order to create this kind of video editing support system, indexing information must be set up beforehand for the raw video shot by the camera operator so as to take advantage of the video grammar. Within the video grammar the particularly important rules have to do with connecting shots. In this paper the authors propose a method to automatically index shot size, along with proposing a video editing support system based on video grammar. © 2003 Wiley Periodicals, Inc. Electron Comm Jpn Pt 2, 86(11): 61–71, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjb.10201

Video editing is used to produce a final version with a specific duration by finding and selecting appropriate shots from the raw video material and connecting them. Video editing process is generally conducted according to the special rules called “video grammar” in order to produce excellent and intelligible videos for broadcasting. However, this editing consumes a lot of human editor's working time. To solve this problem, an efficient and new video editing technique or system is required. The goal of this study is to develop an intelligent support system for video editing based on video grammar. This paper proposes a method of using camerawork density, camerawork instability, and cut point parameters to automatically segment the raw video materials into useful sections and useless sections. The method is based on video grammar as a part of the video editing support system.

The Island Model encourages genetic diversity, and often displays better search performance than single population models. In order to enhance the Island Model in the framework of genetic programming (GP), we propose a novel migration strategy based on frequent trees, where the frequent trees in an island mean the sub-trees appearing frequently among the individuals in the island. The proposed method evaluates each island by measuring its activation level in terms of not only how high the best fitness value is but also how many types of frequent trees are newly created, and then makes several individuals migrate from an island with high activation level to an island with low activation level, and vice versa. Using three benchmark problems widely adopted in the literature, we demonstrate that performance improvement can be achieved through incorporating the information of frequent trees into a migration strategy, and the proposed method significantly outperforms a typical method of the Island Model GP.

One of the most well studied issues in genetic programming is how to make building blocks efficiently. To make building blocks, it is important to find the substructures that appear in the individuals with higher fitness. Recently, a method based on frequent substructures has been proposed, and it has shown good performance; however, the depth of trees is not considered in the method. In this paper, we propose a hybrid crossover that involves the consideration of a combination of frequent trees and the depth of trees and apply the proposed method to symbolic regression problems. We experimentally demonstrate the effectiveness of the proposed method.

We address the problem of predicting missing links for a social network in Social Media by using user activity data. We propose a simple and natural probabilistic model with latent features (traits) for simultaneously generating links and activities in the set of nodes, and present an efficient method of learning the model from the observed links and activities. In order to estimate the total number of latent features and the probability distribution of them for each node from the observed data, we incorporate a hierarchical Dirichlet process (HDP) into the model. On the basis of the learned model, we present a method of predicting missing links in the social network. We experimentally show by using synthetic data that the proposed learning method can estimate the link creation probabilities in good accuracy when there is an enough amount of training data. Moreover, using real and synthetic data, we experimentally demonstrate the effectiveness of the proposed link prediction method.

In this paper, we propose a video shooting navigation system by real-time useful shot discrimination based on video grammar to support users shooting nice shots for later editing work. In this system, the processing speed must be very high so that we use a gray value projection method to extract the camerawork parameters in real-time. From the result of camerawork and gray value analysis, the shots are classified into 16 states and the system issues alarms and instructions about the usefulness and uselessness of the shots in real-time just after shooting the shot. Thereby, users can retake a shot necessary for later editing efficiently

To deliver baseball highlight scenes broadcast live to baseball fans outside, image processings such as an online video analyzing, meta information extraction and automatic editing have to be performed in real time. This paper proposes a high-speed image processing to automatically extract PC (pitcher and catcher) scenes, based on feature mining, from a baseball live game broadcast in real time as a part of the baseball highlight scene delivery system. This method showed 95.5% accuracy in the F-measure score within 1/30 of real time.

Video editing is the work to produce the final videos with certain duration by finding and selecting appropriate shots from the material videos and connecting them. In order to produce the excellent videos, this process is generally conducted according to the special rules called "video grammar". In this paper, we propose an intelligent support system for the video editing where metadata are extracted automatically and then the video grammars are applied to the extracted metadata.