• Journal of Information Processing Systems
• /
• 제15권5호
• /
• pp.1171-1178
• /
• 2019

This study proposes a deep neural network model based on an encoder-decoder structure for visual dialogs. Ongoing linguistic understanding of the dialog history and context is important to generate correct answers to questions in visual dialogs followed by questions and answers regarding images. Nevertheless, in many cases, a visual understanding that can identify scenes or object attributes contained in images is beneficial. Hence, in the proposed model, by employing a separate person detector and an attribute recognizer in addition to visual features extracted from the entire input image at the encoding stage using a convolutional neural network, we emphasize attributes, such as gender, age, and dress concept of the people in the corresponding image and use them to generate answers. The results of the experiments conducted using VisDial v0.9, a large benchmark dataset, confirmed that the proposed model performed well.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2435-2438
• /
• 2003

In this paper, we propose a Korean speech understanding model using dictionary and thesaurus. The proposed model search the dictionary for the same word with in input text. If it is not in the dictionary, the proposed model search the high level words in the high level word dictionary based on the thesaurus. We compare the probability of sentence understanding model with threshold probability, and we'll get the speech understanding rate. We evaluated the performance of the sentence speech understanding system by applying twenty questions game. As the experiment results, we got sentence speech understanding accuracy of 79.8％. In this case probability of high level word is 0.9 and threshold probability is 0.38.

• 전자통신동향분석
• /
• 제38권6호
• /
• pp.12-21
• /
• 2023

Visual relationship understanding in computer vision allows to recognize meaningful relationships between objects in a scene. This technology enables the extraction of representative information within visual content. We discuss the technology of visual relationship understanding, specifically focusing on videos. We first introduce visual relationship understanding concepts in videos and then explore the latest existing techniques. Next, we present benchmark datasets commonly used in video visual relationship understanding. Finally, we discuss future research directions in video visual relationship understanding.

• 대한두경부종양학회지
• /
• 제26권2호
• /
• pp.193-197
• /
• 2010

Objectives : Patients with neck tumor and their family need every information about the disease. Especially, the size and location are confusing with verbal information. With the aid of CT, the problem had some answer, but it needs some medical education. We would like to know the usefullness of 3D reconstructed images in patient education about the disease. Material and Methods : Neck CT data were collected from 10 patients with various neck tumors and converted to 3D reconstructed images. Understanding of the patients about the size and location of tumors were rated from questionaires using axial CT images and 3D images. Results : Understanding score about 3D images were greater than that of CT images(p<0.006). Conclusion : 3D reconstructed images of CT could give the patients more real visual information about the disease.

• 한국식생활문화학회지
• /
• 제17권2호
• /
• pp.141-152
• /
• 2002

This study provides a national examination on youths' 'understanding' of irradiated food. The 1,200 subjects of the survey were randomly sampled from male and female students throughout the nation, between grades five and eleven. The survey was conducted toward these samples in November 2000. The number of respondents with exposure to irradiated food was so small, amounting to only 4.0 percent of the whole sample. The core concept used in this study is 'impression'. An impression is information about a specific subject, which carries significance to an individual. The results show that the higher the grade was, the more value the contents of impression contained. Furthermore, impressions concerning atomic or nuclear energy, and radioactivity increased greatly among students in middle school and above. Providing information of effects and advantages of irradiated food was focused to increase positive impressions and decrease the negative ones more greatly than providing simple factual information. Youths showed less value-centered impressions of irradiated food and more impressions centered on fragmented facts than adults. Respondents previously exposed irradiated food were shown to acquire the most of their information from the television and newspaper media. Among six information sources presented in the survey, youths pointed out 'science and technology research institutes' as the most credible. International organizations and environmental/ consumer organizations were evaluated as having relatively high credibility. Providing simple factual information of irradiated food did not seem to bring about any difference to the intention of purchasing irradiated food. On the other hand, respondents provided with effects-included information showed an increase in such intention. Our research results of the youth show a notable difference with that of the adults. Thus, programs and strategies to enhance youths' understanding should differ from those concerning adults.

• 정보교육학회논문지
• /
• 제9권3호
• /
• pp.367-376
• /
• 2005

지식정보사회에서 컴퓨터교육의 중요성은 날로 증가하고 있으며, 이제 컴퓨터는 하나의 필수도구처럼 인식되고 있으나 컴퓨터교육의 주요 매체인 컴퓨터 교과서에 대한 연구가 부족한 실정이다. 이에 본 연구는 충청북도 내 초등학생 4.5.6학년 학생들을 대상으로 컴퓨터 교과서에서 사용되는 주요 용어에 대한 이해 수준을 파악하고 개인 변인에 따른 이해 수준의 차이를 분석하였다. 연구 결과, 용어에 대한 학생들의 이해 수준은 전반적으로 낮은 것으로 밝혀졌으며, 개인 변인 중 지역, 학년, 컴퓨터 소유 여부, 과거 컴퓨터교육의 경험 유무, 컴퓨터 수업 진행 형태, 컴퓨터 수업의 호응도, 컴퓨터 수업의 참여도, 성적 수준 등에 따라서 용어의 이해 수준에 대해 유의미한 차이가 발견되었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1760-1763
• /
• 2002

In this paper the authors present their attempt io realize a motion pattern detector that finds specified sequence of image from input motion image. The detector is intended to be used for time-varying facial expression understanding. Needless to say, facial expression understanding by machine is crucial and enriches quality of human machine interaction. Among various facial expressions, like blinking, there must be such expressions that can not be recognized if input expression image is static. Still image of blinking can not be distinguished from sleeping. In this paper, the authors discuss implementation of their motion pattern detector and describe experiments using the detector. Experimental results confirm the feasibility of the idea behind the implemented detector.

• 한국콘텐츠학회논문지
• /
• 제12권7호
• /
• pp.323-335
• /
• 2012

정보통신기술의 발달로 온라인 시장에서 제공되는 영화상품의 정보콘텐츠는 고객의 구매의사결정에 많은 영향을 미치고 있다. 본 논문의 목적은 정보콘텐츠의 내용이 영화상품 구매고객의 정보서비스만족도와 구매의도에 어떠한 영향을 주며, 이러한 영향이 영화상품에 대한 고객관여도에 따라 어떻게 변화하는지를 실증분석을 통해 밝히는데 있다. 연구결과는 다음과 같다. 첫째, 온라인에서 제공되는 정보콘텐츠의 정보서 비스만족도는 관람정보(시간, 장소, 가격, 구매방법)보다는 내용정보(줄거리, 배우, 관람후기)가 고객관여도 수준에 관계없이 유의적 영향을 미친다. 둘째, 고객의 온라인구매의도에는 관람정보와 내용정보 모두 영향을 미친다. 고객관여도가 낮은 경우는 관람정보가, 높은 경우에는 내용정보가 유의적 영향을 미치는 것으로 나타나 조절효과를 보여주었다. 셋째, 정보서비스만족도는 고객관여도의 수준과 상관없이 온라인구매의도에 강력한 영향을 준다. 결국, 고객의 만족도를 높이기 위해서 내용정보의 다양성과 품질 제고가 필요하며 온라인구매의도를 높이기 위해서는 내용정보와 더불어 관람정보의 개선도 필요하다는 것을 보여주었다. 이러한 연구 결과는 영화상품의 온라인구매사이트를 통한 마케팅전략 수립에 도움이 될 것으로 기대된다.

• 정보관리연구
• /
• 제33권3호
• /
• pp.27-43
• /
• 2002

본 연구는 도서관 정보센터에서 정보를 복제의 방법으로 이용하는 현황을 조사하였다. 동시에 정보제공 업무를 담당하는 전문직의 저작권 보호에 관한 이해 정도와 저작권법 중 관련 규정에 대한 지식과 준수 현황을 검토하였다.

• 한국문헌정보학회지
• /
• 제3권
• /
• pp.1-24
• /
• 1973

This paper is intended as a basic study in which the purpose is to provide understanding of the workings of man in relation to his information resources. Such understanding would prove of value in formulating the policies of an inoformation center serving the fields of science and technology. The information problem of the scientific community was assessed in the lights of the characteristics of the information (cumulativeness, currency versus obsolescence, volume versus redundancy, interrelationships, and foreign literature)and the flow of information and communication patterns covering the use of the variety of media and the information gathering habits of scientists. What can be done to ease the problem was sought in the improvements and innovations which call the attentions of the scientists and the technologists as producers and users of the information, of the professional organizations of various disciplines and of government.