• 한국데이타베이스학회:학술대회논문집
• /
• 한국데이타베이스학회 1997년도 International Conference MULTIMEDIA DATABASES on INTERNET
• /
• pp.24-48
• /
• 1997

. Supported byㆍDARPA′s image Understanding (IU) program under "Video Retrieval Based on Language and image Analysis" project.DARPA′s Computer Assisted Education and Training Initiative program (CAETI)ㆍObjective: Develop practical systems for automatic understanding and indexing of video sequences using both audio and video tracks(omitted)

• 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.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2004년도 가을 학술발표논문집 Vol.31 No.2 (2)
• /
• pp.694-696
• /
• 2004

With the more sophisticated abilities development of video, object motion analysis and interpretation has become the fundamental task for the computer vision understanding. For that understanding, firstly, we seek a sum of absolute difference algorithm to apply to the motion detection, which was based on the scene. Then we will focus on the moving objects representation in the scene using spatio-temporal relations. The video can be explained comprehensively from the both aspects : moving objects relations and video events intervals.

• 한국차세대컴퓨팅학회논문지
• /
• 제14권5호
• /
• pp.19-30
• /
• 2018

영상 데이터에 대한 시맨틱 정보를 정확하게 이해하는 것은 인공지능 및 기계학습 분야에서 가장 어려운 도전과제의 하나로 알려져 있다. 본 논문에서는 동영상 시맨틱 이해를 위한 시각 동사 도출과 이를 바탕으로 하는 동영상 데이터베이스인 액션넷 데이터베이스 구축에 관해 제안하고 있다. 오늘날 인공지능 기술의 눈부신 발달에는 인공지능 알고리즘의 발전이 크게 기여하였지만 알고리즘의 학습과 성능 평가를 위한 방대한 데이터베이스의 제공도 기여한 바가 매우 크다고 할 수 있다. 인공지능이 도전하기 어려운 분야였던 시각 정보 처리에 있어서도 정지 영상 내의 객체인식에 있어서는 인간의 수준을 능가하기 시작하면서 점차 동영상에서의 내용에 대한 시맨틱 이해 기술 개발로 발전하고 있다. 본 논문에서는 이러한 동영상 이해를 위한 학습 및 테스트 데이터베이스로서 액션넷 구축에 요구되는 시각 동사의 후보를 도출한다. 이를 위해 언어학 기반의 동사 분류체계를 살펴보고, 영상에서의 시각 정보를 명세한 데이터 및 언어학에서의 시각 동사 빈도 등으로부터 시각 동사의 후보를 도출한다. 시각 동사 분류체계와 시각 동사후보를 바탕으로 액션넷 데이터베이스 스키마를 정의하고 구축한다. 본 논문에서 제안하는 시각 동사 및 스키마와 이를 바탕으로 하는 액션넷 데이터베이스를 개방형 환경에서 확장하고 활용성을 제고함으로써 동영상 이해 기술 발전에 기여할 수 있을 것으로 기대한다.

• ETRI Journal
• /
• 제39권4호
• /
• pp.502-513
• /
• 2017

For video understanding, namely analyzing who did what in a video, actions along with objects are primary elements. Most studies on actions have handled recognition problems for a well-trimmed video and focused on enhancing their classification performance. However, action detection, including localization as well as recognition, is required because, in general, actions intersect in time and space. In addition, most studies have not considered extensibility for a newly added action that has been previously trained. Therefore, proposed in this paper is an extensible hierarchical method for detecting generic actions, which combine object movements and spatial relations between two objects, and inherited actions, which are determined by the related objects through an ontology and rule based methodology. The hierarchical design of the method enables it to detect any interactive actions based on the spatial relations between two objects. The method using object information achieves an F-measure of 90.27%. Moreover, this paper describes the extensibility of the method for a new action contained in a video from a video domain that is different from the dataset used.

• 한국의료질향상학회지
• /
• 제19권1호
• /
• pp.56-61
• /
• 2013

Objectives: This video has been produced to provide better awareness for our patients about radiotherapy treatment for anxiety and stress. This video will give inexperienced patients a better understanding of the processes and expectations of the radiotherapy. We have produced a radiotherapy guidance video regarding work flow and a method of radiotherapy to relieve anxiety and stress. It also improves patients satisfaction and understanding of radiotherapy to provide a high-quality health care for radiotherapy patients with indirect experience. Methods: We have evaluated the effectiveness of the video compared to our existing verbal method. See below for the evaluation criteria; 1) Patients satisfaction rate of guidance 2) a comparison of understanding of radiotherapy 3) a comparison of a time of education for patients 4) a researching of an incidence rate of radiotherapy. Results: When compared to the verbal explanation the patients had a increased level of understanding of the radiotherapy treatment. The time to educate patient was decreased and the level of incidents during the treatment was decreased due to the patient having a better understanding of the whole process. Conclusion : In conclusion, the audiovisual education increased the understanding of radiotherapy for patients compared to verbal education. The video also helped patients to cooperate in treatment room so we can provide premium radiotherapy treatment. By reducing the treatment time and education processa we improved the patients overall experience.

• 한국멀티미디어학회논문지
• /
• 제21권3호
• /
• pp.400-414
• /
• 2018

It is required for today's video contents to interact with a viewer in order to provide more personalized experience to viewer(s) than before. In order to do so by providing friendly experience to a viewer from video contents' systemic perspective, understanding and analyzing the situation of the viewer have to be preferentially considered. For this purpose, it is effective to analyze the situation of a viewer by understanding the state of the viewer based on the viewer' s behavior(s) in the process of watching the video contents, and classifying the behavior(s) into the viewer's emotion and state during the flow. The term 'Flow-emotion-state' presented in this study is the state of the viewer to be assumed based on the emotions that occur subsequently in relation to the target video content in a situation which the viewer of the video content is already engaged in the viewing behavior. This Flow-emotion-state of a viewer can be expected to be utilized to identify characteristics of the viewer's Flow-situation by observing and analyzing the gesture and the facial expression that serve as the input modality of the viewer to the video content.

• 로봇학회논문지
• /
• 제14권1호
• /
• pp.22-30
• /
• 2019

For effective human-robot interaction, robots need to understand the current situation context well, but also the robots need to transfer its understanding to the human participant in efficient way. The most convenient way to deliver robot's understanding to the human participant is that the robot expresses its understanding using voice and natural language. Recently, the artificial intelligence for video understanding and natural language process has been developed very rapidly especially based on deep learning. Thus, this paper proposes robot vision to audio description method using deep learning. The applied deep learning model is a pipeline of two deep learning models for generating natural language sentence from robot vision and generating voice from the generated natural language sentence. Also, we conduct the real robot experiment to show the effectiveness of our method in human-robot interaction.

• International Journal of Contents
• /
• 제10권4호
• /
• pp.23-29
• /
• 2014

Online video advertising is now an increasingly important tool for marketers to reach and connect with their consumers. The purpose of this study was to empirically investigate the impact of video format on online video advertising. More specifically, this study aimed to explore whether online video quality and image size influences viewer responses toward online video advertising. By conducting an experimental study on YouTube, the results suggested that enhanced video quality of online advertising may have an important impact on effectiveness of the advertising, and the concept of presence is a key to understanding the effects of enhanced video quality in online advertising.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.3769-3789
• /
• 2018

Social pedestrian groups are the basic elements that constitute a crowd; therefore, detection of such groups is scientifically important for modeling social behavior, as well as practically useful for crowd video understanding. A social group refers to a cluster of members who tend to keep similar motion state for a sustained period of time. One of the main challenges of social group detection arises from the complex dynamic variations of crowd patterns. Therefore, most works model dynamic groups to analysis the crowd behavior, ignoring the existence of stationary groups in crowd scene. However, in this paper, we propose a novel unified framework for detecting social pedestrian groups in crowd videos, including dynamic and stationary pedestrian groups, based on spatiotemporal-oriented energy measurements. Dynamic pedestrian groups are hierarchically clustered based on energy flow similarities and trajectory motion correlations between the atomic groups extracted from principal spatiotemporal-oriented energies. Furthermore, the probability distribution of static spatiotemporal-oriented energies is modeled to detect stationary pedestrian groups. Extensive experiments on challenging datasets demonstrate that our method can achieve superior results for social pedestrian group detection and crowd video classification.