Yukiko Nishizaki

Emotional video scene retrieval system for lifelog videos based on facial expression intensity

Lifelog videos, which are the records of a persons daily life as video data, draw attention since various recording devices such as smartphone become widely used. Due to privacy reasons, lifelog videos are usually managed by the owners of the videos although the amount of video data is quite large. This makes it quite difficult to find interesting and impressive scenes from lifelog videos. In order to facilitate the retrieval of such scenes, we develop a video scene retrieval system for lifelog videos. We focus on emotional scenes as interesting scenes taking into consideration the strength of emotion derived from the intensity of facial expression. Our retrieval system thus displays emotional scenes of various intensity to users in a comprehensible way. We clarify the usability of the retrieval system through an evaluation experiment.

A proposal of a user-interface index that corresponds with mental model structural elements

The objective of this research is to propose a user-interface design index that corresponds with mental model structural elements. A total of 35 user-interface design indexes were extracted from previous design related rules and design guidelines that pertain to design indexes. Next, the user-interface design indexes were linked to the mental model structural elements and a formal concept analysis was done in order to determine the relationship between them. The mental model structural elements were classified and structured according to human information processing, functional and structural models. Finally, we describe how designers can easily construct user-interface designs based mainly on the user-interface design index and mental model structural elements.

Revised coloring method of characters for presentation slides and coloring system

The colors of characters suitable to presentation slides were proposed. Here, five color combinations were proposed. A combination has three colors of “Base color,” “Main color,” and “Accent color.” The “Base color” is for the background. The color white is used as the “Base color.” The “Main color” is for the part becoming the frame. The “Accent color” is for the place where we want to emphasize. This paper proposes a new coloring method of characters in slides. The proposed method uses term-frequency (TF) and the words in the “Conclusion” slide and textboxes (WCT). It is called TF-WCT method. This method decides the words suitable to the “Accent color.” It is shown that the proposed method could more precisely color the words than the TF-IDF and the WCT methods, which have already been proposed. The prototype coloring system based on the proposed method is constructed.

Effect of Embodied Cognition on an Impression of a Robot

It is important that participants form a positive impression when they meet with a new robot for the first time. Therefore, we tried to change how participants evaluate a new robot by changing the surrounding environment in the experiment. Embodied Cognition is a theory that our cognition for a target is strongly influenced by physical stimulation of our own bodies. Our research investigated a hypothesis that a soft chair can make favorable impressions of a robot. We performed an experiment using a hard plastic chair and a soft cushioned chair. Although the results did not support the hypothesis, they suggested that the effect of embodied cognition can be different between males and females.

Effect of the reality of pictures in a horror game on feelings of fear

This paper tried to find the cause of fear by horror games. We prepared two types of horror games whose reality of pictures are changed, and observed the change of autonomic nervous function and the amount of perspiration. As a result, the physiological response to the horror game which has real pictures was scarier. Also, people who are familiar with horror games are scared at several horror scenes in the horror game, whereas the others are not. Additionally, men are afraid of the horror games of real pictures, while women feel scared of horror games of simple pictures.

Where Do Drivers Look When Driving in a Foreign Country

The importance of developing automated driving systems based on driver characteristics is increasing rapidly. Although some previous studies indicated differences in driver eye movements caused by driving experience or the situation, few studies have focused on the effects of familiarity with the driving environment on driver eye movements. In this study, we investigated differences in eye movements, especially fixation duration and location, between novice and expert drivers when driving abroad. The eye movements of about 50 participants were measured during driving simulations in two situations: driving in their own country and in a foreign one. Results indicated that experienced drivers were more likely to be influenced by familiarity of the driving situation. This results show the need to develop an automated driving system that considers drivers’ driving background.

Evaluation of coloring methods of characters for presentation slides

This paper experimentally and quantitatively evaluates three methods of coloring words on presentation slides. These are the method using term-frequency (TF) and inverse document frequency (IDF), the one focusing on the words in the “Conclusion” slide and textboxes (WCT), and the one using TF and WCT. These methods try to identify important words in a presentation slide. After the important words are identified, they are colored with the “Accent color,” which is for the place where we want to emphasize. It is shown that the TF-WCT method is more precisely color the words than the other methods, and that it could select the same words as those the subject selected at the very best selection.

Visual Attention During Simulated Autonomous Driving in the US and Japan

To explore cultural differences in driver behavior for the purposes of vehicle automation, we used eye tracking to measure fixation patterns of Japanese and US participants (N = 98) viewing video simulations of automated driving through San Francisco and Osaka. After each drive, we asked participants questions about objects and events from the video. Japanese participants showed higher fixation counts and durations than US participants for salient foreground objects in the traffic scene, and answered questions about those objects more correctly. US participants showed higher fixation counts than Japanese participants on visually prominent background features, and gave more correct answers about those. Consistency between fixation count and fixation duration on an object or feature, and recall of that object or feature, suggests that situation awareness during simulated automated driving proceeds from patterns of visual fixation on elements of the traffic scene.

Which Design Seems Easy to Use? An Analysis of Individual Differences in Mental Models

We investigated whether the influence of age and individual differences in mental model construction level affect the evaluation of appearance and functionality when users select household electrical appliances based only on appearance. Results showed that older (age 66–80) adults emphasized usability more than young (age 20–34) adults did. Moreover, users with high proficiency in mental model construction focused more on usability than did those with less advanced mental models.

The Optimum Rate of Mimicry in Human-Agent Interaction

The importance of building rapport between a human and an agent is increasing with the burgeoning development of robot technology. Several recent studies have focused on the chameleon effect, using psychological concepts to investigate human-agent interaction. However, the validity of the chameleon effect in human-agent interaction is controversial. Few studies have explored the influence of individual cognitive ability and the rate of mimicry on the human-agent interaction. We explored the optimal rate of mimicry and the relationship between mimicry rate and individual empathic ability. We controlled the amount of agent mimicry and examined the effect on participants classified as high- and low-perspective takers. We found that, overall, participants preferred agents that mimicked their behavior 83% of the time. Moreover, high-, but not low-, perspective takers tended to be influenced by the mimicry rate.