This paper proposes a group-based image retrieval method for video image annotation systems. Although the wide spread use of video camera recorders has increased the demand for an automated annotation system for personal videos, conventional image retrieval methods cannot achieve enough accuracy to be used as an annotation engine. Recording conditions, such as change of the brightness by weather condition, shadow by the surroundings, and etc, affect the qualities of images recorded by the personal video camera recorders. The degraded image of personal video makes the retrieval task difficult. Furthermore, it is difficult to discriminate similar images without any auxiliary information. To cope with these difficulties, this paper proposes a group-based image retrieval method. Its characteristics are 1) the use of image similarity based on the wavelet transformation based features and the scale invariant feature transform based features, and 2) the pre-grouping of related images and screening using group information. Experimental results show that the proposed method can improve image retrieval accuracy to 90% up from the conventional method of 40%.
It is generally thought that living things have trends in their preferences. The mechanism of occurrence of another trends in successive periods is concerned in their conformity. According to social impact theory, the minority is always exists in the group. There is a possibility that the minority make the transition to the majority by conforming agents. Because of agent's promotion of their conform actions, the majority can make the transition. We proposed an evolutionary model with both genes and memes, and elucidated the interaction between genes and memes on sexual selection. In this paper, we propose an agent model for sexual selection imported the concept of conformity. Using this model we try an environment where male agents and female agents are existed, we find that periodic phenomena of fashion are expressed. And we report the influence of conformity and differentiation on the transition of their preferences.
We derived the oracle summary with the highest ROUGE score that can be achieved by integrating sentence extraction with sentence compression from the reference abstract. The analysis results of the oracle revealed that summarization systems have to assign an appropriate compression rate for each sentence in the document. In accordance with this observation, this paper proposes a summarization method as a combinatorial optimization: selecting the set of sentences that maximize the sum of the sentence scores from the pool which consists of the sentences with various compression rates, subject to length constrains. The score of the sentence is defined by its compression rate, content words and positional information. The parameters for the compression rates and positional information are optimized by minimizing the loss between score of oracles and that of candidates. The results obtained from TSC-2 corpus showed that our method outperformed the previous systems with statistical significance.
We describe an ``adaptation gap'' that indicates the differences between the functions of artificial agents users expect before starting their interactions and the functions they perceive after the interactions. We investigated the effects of this adaptation gap on users' impressions of the artificial agents because any variations in impressions before and after the start of an interaction determine whether the user feels that this agent is worth continuing an interaction. The results showed that the positive or negative signs of the adaptation gap and the subjective impression scores of the agents before the experiment affected the final users' impressions of the agents significantly.
This paper reviews three hybrid cognitive architectures (Soar, ACT-R, and CoJACK) and how they can support including models of emotions. There remain problems creating models in these architectures, which is a research and engineering problem. Thus, the term cognitive science engineering is introduced as an area that would support making models easier to create, understand, and re-use.
Quantum-inspired Evolutionary Algorithm (QEA) has been proposed as one of stochastic algorithms of evolutionary computation instead of a quantum algorithm. The authors have proposed Quantum-inspired Evolutionary Algorithm based on Pair Swap (QEAPS), which uses pair swap operator and does not group individuals in order to simplify QEA and reduce parameters in QEA. QEA and QEAPS imitationally use quantum bits as genes and superposition states in quantum computation. QEAPS has shown better search performance than QEA on knapsack problem, while eliminating parameters about immigration intervals and number of groups. However, QEAPS still has a parameter in common with QEA, a rotation angle unit, which is uncommon among other evolutionary computation algorithms. The rotation angle unit deeply affects exploitation and exploration control in QEA, but it has been unclear how the parameter influences QEAPS to behave. This paper aims to show that QEAPS involves few parameters and even those parameters can be adjusted easily. Experimental results, in knapsack problem and number partitioning problem which have different characteristics, have shown that QEAPS is competitive with other metaheuristics in search performance, and that QEAPS is robust against the parameter configuration and problem characteristics.
Haussler's convolution kernel provides a successful framework for engineering new positive semidefinite kernels, and has been applied to a wide range of data types and applications. In the framework, each data object represents a finite set of finer grained components. Then, Haussler's convolution kernel takes a pair of data objects as input, and returns the sum of the return values of the predetermined primitive positive semidefinite kernel calculated for all the possible pairs of the components of the input data objects. On the other hand, the mapping kernel that we introduce in this paper is a natural generalization of Haussler's convolution kernel, in that the input to the primitive kernel moves over a predetermined subset rather than the entire cross product. Although we have plural instances of the mapping kernel in the literature, their positive semidefiniteness was investigated in case-by-case manners, and worse yet, was sometimes incorrectly concluded. In fact, there exists a simple and easily checkable necessary and sufficient condition, which is generic in the sense that it enables us to investigate the positive semidefiniteness of an arbitrary instance of the mapping kernel. This paper presents and proves the validity of the condition. In addition, we introduce two important instances of the mapping kernel, which we refer to as the size-of-index-structure-distribution kernel and the edit-cost-distribution kernel. Both of them are naturally derived from well known (dis)similarity measurements in the literature (the maximum agreement tree, the edit distance), and are reasonably expected to improve the performance of the existing measures by evaluating their distributional features rather than their peak (maximum/minimum) features.
Information compilation is a novel research topic which aims to compile various information intelligently, and to make it easy to comprehend/access. The information compilation is emphasized by two characteristics. The first one is a cross-modalitiness achieved by cooperation between non-linguistic information and linguistic information, and the second one is a continuousness in supporting all aspects of information utilization. To foster researches related to the information compilation, we conducted three attempts: installation of a reference model on information compilation, distribution of annotated corpus and a visualization platform as boundary objects, and deployment of an evaluation workshop. The paper describes current efforts of the attempts.
Human behavior understanding in everyday life is promising but not established research field. Our project named 'open life matrix' is focused on this field. In these years, many sensor houses and robotic room projects have been studied and sensing and network technology have been established. However, still we have problems to realize everyday life support information systems and services. There are two major problems. The first one is data representation and computational modeling problem in everyday life. The second one is that we don't have a good way to realize valuable services from research outcomes. We propose a challenge to solve these problems by a scheme for accumulating common data set and probabilistic causal modeling during everyday life services.
This paper proposes multiscale service design method through the development of support service for prevention and recovery from dementia towards science of lethe. Proposed multiscale service model consists of tool, event, human, network, style and rule. Service elements at different scales are developed according to the model. Firstly, the author proposes and practices coimagination method as an ``event'', which is expected to prevent the progress of cognitive impairment. Coimagination support system was developed as a ``tool''. Experimental results suggest the effective activation of episodic memory, division of attention, and planning function of participants by the measurement of cognitive activities during the coimagination. Then, Fonobono Research Institute was established as a ''network'' for ``human'' who studies coimagination, which is a multisector research organization including elderly people living around Kashiwa city, companies including instrument and welfare companies, Kashiwa city and Chiba prefecture, researchers of the University of Tokyo. The institute proposes and realizes lifelong research as a novel life ``style'' for elderly people, and discusses life with two rounds as an innovative ``rule'' for social system of aged society.