• 한국콘텐츠학회논문지
• /
• 제20권4호
• /
• pp.1-13
• /
• 2020

본 연구는 온라인 동영상 플랫폼에 적용되는 추천 알고리듬을 이해하고자 유튜브에서 K-pop 뮤직비디오의 콘텐츠 특성과 재생 시 추천되는 연관 비디오(related video)의 관계를 규명하고 네트워크 분석을 통해 어떤 비디오가 연관 비디오로 추천되는지 살펴보았다. 분석 결과, K-pop 재생 시 비디오의 좋아요 수가 추천 순위에 영향을 주었으며 대부분 같은 채널에 속하거나 동일한 기획사에서 제작한 비디오가 연관 비디오로 추천되었다. 그리고 연관 비디오의 네트워크 분석 결과, K-pop 뮤직비디오의 네트워크가 강하게 형성되어 있으며 연관 비디오의 네트워크 분석에서 BTS의 뮤직비디오가 중심성이 높게 나타났다. 이러한 연구결과는 K-pop간의 네트워크가 강하기 때문에 K-pop을 검색 쿼리로 입력해서 비디오를 시청할 때는 연속적으로 K-pop을 즐길 수 있지만, 반대로 다른 장르의 비디오를 시청할 때는 K-pop이 연관 비디오로 추천되지 못할 수 있음을 의미한다.

• 한국컴퓨터정보학회논문지
• /
• 제25권7호
• /
• pp.65-73
• /
• 2020

바이럴 영상광고는 광고 및 영화산업에서 특정제품이나 개봉전 영화에 대한 사전 홍보 목적으로 활용되고 있으며, 투자 대비 많은 효과를 내고 있다. 향후 발전 방향을 예측해 보려면 바이럴 영상 인식에 대한 분석이 필요하다. 이에 본 연구는 광고나 영화를 가장 많이 접하는 연령층인 20대 대학생 118명에 대한 바이럴 영상 설문조사를 하였다. 이를 통해 바이럴 영상에 대한 인지 여부, 기억에 남는 바이럴 영상, 만족도, 메시지 전파여부, 전파 방식, 바이럴 영상에 대한 긍정도, 향후 발전 예상, 희망하는 바이럴 영상 유형 등에 대한 설문을 실시하였다. 이 결과 바이럴 영상 인지도는 16.7%로 나타났고, 가장 기억에 남는 바이럴 영상으로 "겨울왕국" 영화의 "Let it Go" 영상이 설문조사 결과 69.1%로 나타났다. 바이럴 영상에 대한 만족도는 31.2%로 높지 않았으며, 바이럴영상을 시청한 후 타인에게 메시지를 전달한 경우는 73.5%로 높게 나타났다. 바이럴 영상에 대한 부정적 의견은 13.7%로 낮게 나타났으며, 바이럴 영상 분야가 64.5%는 "발전할 것이다"라고 답하였고, 6.7%는 "발전하지 못할 것이다"라고 답하였다.

• 한국콘텐츠학회논문지
• /
• 제13권10호
• /
• pp.170-180
• /
• 2013

본 연구는 산업적인 관점에서 K-POP의 뮤직비디오와 PPL과의 연계 가능성과 관련하여 국, 내외 뮤직비디오를 대상으로 PPL을 비교, 검토하여 K-POP 에서의 성공적인 PPL 전략을 수립하고자 한다. 이를 위한 연구방법으로 K-POP과 해외 뮤직비디오(영미권)에서 나타난 PPL의 사례를 내용분석하고 이들의 성공 요인을 도출 하였다. 또한 본 연구는 PPL 노출횟수 및 노출시간, PPL 배치유형, PPL 제품군 유형, 그리고 광고주 등의 내용 분석을 통하여 K-POP과 해외 뮤직비디오 PPL 전략을 분석하였다. 연구결과 K-POP 뮤직비디오에서는 패션 뿐 만 아니라 PPL 제품군을 다양화할 필요가 있다. 또한 노출횟수 보다는 노출시간에 초점을 맞춘 해외 뮤직비디오의 PPL 전략을 활용하는 것이 필요하다. 아울러 K-POP 뮤직비디오에서는 보다 과감한 PPL 배치 노출전략 세우는 것이 중요한 것으로 나타났다. 따라서 본 연구는 향후 K-POP에서의 성공적인 PPL 전략에 필요한 이론적, 정책적 시사점을 제공하는데 그 의의가 있다고 볼 수 있다.

• 전자통신동향분석
• /
• 제35권3호
• /
• pp.20-33
• /
• 2020

Temporal action detection (TAD) in untrimmed videos is an important but a challenging problem in the field of computer vision and has gathered increasing interest recently. Although most studies on action in videos have addressed action recognition in trimmed videos, TAD methods are required to understand real-world untrimmed videos, including mostly background and some meaningful action instances belonging to multiple action classes. TAD is mainly composed of temporal action localization that generates temporal action proposals, such as single action and action recognition, which classifies action proposals into action classes. However, the task of generating temporal action proposals with accurate temporal boundaries is challenging in TAD. In this paper, we discuss TAD technologies that are considered high performance in terms of representative TAD studies based on deep learning. Further, we investigate evaluation methodologies for TAD, such as benchmark datasets and performance measures, and subsequently compare the performance of the discussed TAD models.

• Journal of Multimedia Information System
• /
• 제4권4호
• /
• pp.225-232
• /
• 2017

Understanding actions in videos is an important task. It helps in finding the anomalies present in videos such as fights. Detection of fights becomes more crucial when it comes to sports. This paper focuses on finding fight scenes in Hockey sport videos using blur & radon transform and convolutional neural networks (CNNs). First, the local motion within the video frames has been extracted using blur information. Next, fast fourier and radon transform have been applied on the local motion. The video frames with fight scene have been identified using transfer learning with the help of pre-trained deep learning model VGG-Net. Finally, a comparison of the methodology has been performed using feed forward neural networks. Accuracies of 56.00% and 75.00% have been achieved using feed forward neural network and VGG16-Net, respectively.

• ETRI Journal
• /
• 제42권3호
• /
• pp.411-419
• /
• 2020

In real-world intelligent transportation systems, accuracy in vehicle license plate detection and recognition is considered quite critical. Many algorithms have been proposed for still images, but their accuracy on actual videos is not satisfactory. This stems from several problematic conditions in videos, such as vehicle motion blur, variety in viewpoints, outliers, and the lack of publicly available video datasets. In this study, we focus on these challenges and propose a license plate detection and recognition scheme for videos based on a temporal matching prior network. Specifically, to improve the robustness of detection and recognition accuracy in the presence of motion blur and outliers, forward and bidirectional matching priors between consecutive frames are properly combined with layer structures specifically designed for plate detection. We also built our own video dataset for the deep training of the proposed network. During network training, we perform data augmentation based on image rotation to increase robustness regarding the various viewpoints in videos.

• 한국컴퓨터정보학회논문지
• /
• 제21권12호
• /
• pp.219-226
• /
• 2016

In this paper, we propose an efficient repository model for online software education. The software education of app development consists of 7 stages: coding & debugging, submit, collaboration, review, validate, deployment, certification. Proposed repository model supports all 7 stages efficiently. In the coding & debugging stage, the students repeat coding and debugging of source. In the submit stage, the output of previous process such as source codes, project, and videos, are uploaded to repository server. In the collaboration stage, other students or experts can optimize or upgrade version of source code, project, and videos stored in the repository. In the review stage, mentors can review and send feedbacks to students. In the validate stage, the specialists validate the source code, project, and the videos. In the deployment stage, the verified source code, project, and videos are deployed. In the certification stage, the source code, project, and the videos are evaluated to issue the certificate.

• 한국정보시스템학회지:정보시스템연구
• /
• 제32권4호
• /
• pp.29-50
• /
• 2023

Purpose The impact of online reviews is widely acknowledged, with extensive research focused on text-based reviews. However, there's a lack of research regarding reviews in video format. To address this gap, this study aims to explore the connection between company-sponsored product review videos and the extent of directive speech within them. This article analyzed viewer sentiments expressed in video comments based on the level of directive speech used by the presenter. Design/methodology/approach This study involved analyzing speech acts in review videos based on sponsorship and examining consumer reactions through sentiment analysis of comments. We used Speech Act theory to perform the analysis. Findings YouTubers who receive company sponsorship for review videos tend to employ more directive speech. Furthermore, this increased use of directive speech is associated with a higher occurrence of negative consumer comments. This study's outcomes are valuable for the realm of user-generated content and natural language processing, offering practical insights for YouTube marketing strategies.

• 복식문화연구
• /
• 제27권6호
• /
• pp.599-614
• /
• 2019

The aim of this study to provide basic reference data for the development of video contents used in pattern drafting education and to explore the possibility of utilizing YouTube videos in such education. Subject videos were selected using the number of views. A total of 596 videos and 28 channels were analyzed for the period July to September 2019 and the results are as follows. With regard to content, there were 27 pattern drafting items, the majority being dress, pants, skirt, blouse and sleeve drafting, although high-level content such as cowl, bustier, corset patterns were also available. Therefore, there is a high likelihood that YouTube videos could be used as educational material, especially as supplementary references to provide specific examples and easy explanations for difficult concepts or method, for students majoring in this field. However, as most videos currently focus on a few items, expanding video content to features a wider variety of clothing items at different levels is necessary. With regard to video length, it mostly ranged from 10 to 15 minutes. It is not advisable to create lengthy lecture-style videos expounding on different principles or variations in pattern drafting when developing educational video material.

• 한국조경학회지
• /
• 제26권3호
• /
• pp.312-320
• /
• 1998

The purpose of this study is to investigate and compare the validity of various visual simulation methods with or without sounds and videos of the landscapes The landscape evaluation through such media as color slide, color slide with sounds, video and video without sounds are compared with on-site evaluaton of the landscape. The results are as follows : ·Video can generally convey the feelings for the real landscapes better than traditonal mathod, i.e., slide without sounds. ·When the sources of sounds are dominant in the view, there are great differences in responses among 4 different media and video can convey the feelings for real landscapes on site most successfully. ·There are slight differences by landscape types ; in mixed landscapes, there are higher correlations between the on-site estimaton and estimations through media ; in natural landscapes, video can reflect the feelings for real landscapes on site better. ·There is little difference between two shooting methods, fixed shot and pan shot. These results suggest that traditional visual simulation, with slides or photographs, could not reflect the real landscapes in certain situations and the visual simulation method with sounds and videos should be used in such situatios to represent the real landscape better. Especially, when the whole and comprehensive evaluatio of the landscape properties is important, the visual simulation with sounds and videos should be used. And simulation techniques with sounds and videos should be further developed for practial applications.