• Journal of KIISE
• /
• v.42 no.4
• /
• pp.451-458
• /
• 2015

Previous multimodal learning methods focus on problem-solving aspects, such as image and video search and tagging, rather than on knowledge acquisition via content modeling. In this paper, we propose the Multimodal Concept Hierarchy (MuCH), which is a content modeling method that uses a cartoon video dataset and a character-based subtitle generation method from the learned model. The MuCH model has a multimodal hypernetwork layer, in which the patterns of the words and image patches are represented, and a concept layer, in which each concept variable is represented by a probability distribution of the words and the image patches. The model can learn the characteristics of the characters as concepts from the video subtitles and scene images by using a Bayesian learning method and can also generate character-based subtitles from the learned model if text queries are provided. As an experiment, the MuCH model learned concepts from 'Pororo' cartoon videos with a total of 268 minutes in length and generated character-based subtitles. Finally, we compare the results with those of other multimodal learning models. The Experimental results indicate that given the same text query, our model generates more accurate and more character-specific subtitles than other models.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.47-48
• /
• 2021

본 연구는 타이포그래피 기술을 접목한 동영상과 기본 자동 자막을 사용한 동영상의 한글 자막 가독성을 비교·분석하여 모바일 동영상 시청 시 한글 자막의 가독성 개선을 위한 기초자료를 제공하는 데 목적이 있다. 연구의 목적을 위해 기본으로 설정되는 자동 자막을 사용한 동영상과 타이포그래피 기술을 적용·개선한 한글 폰트를 자막에 적용한 동영상을 비교하는 설문을 실시하였다. 시각디자인 전공자(73명)과 비전공자(52명)간의 자막 가독성 설문조사의 결과를 비교·분석하였다. 또한, 모바일을 통해 외국어 동영상 시청 시 자막 설정 기능에서 중요하게 여겨지는 요인과 현재 자막 설정 기능 중 불편하게 여기는 요인을 분석하였다. 수집된 설문의 자료는 Windows SPSS 26.0을 사용하여 분석하였다. 자막 설정 기능에서 중요하게 여겨지는 요인과 현재 자막 설정 기능의 불편 사항 등에 대한 인식의 차이를 살펴보기 위해 빈도분석, 𝑥2 검정, t 검정, 일원변량분석(one-way ANOVA) 등을 실시하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.88-90
• /
• 2021

This paper introduces a method for extracting subtitles from lecture videos through a Korean morpheme analyzer and classifying video categories according to the extracted morpheme information. In some cases incorrect information is entered due to human error and reflected in the characteristics of the items, affecting the accuracy of the recommendation system. To prevent this, we generate a keyword table for each category using morpheme information extracted from pre-classified videos, and compare the similarity of morpheme in each category keyword table to classify categories of Lecture videos using the most similar keyword table. These human intervention reduction systems directly classify videos and aim to increase the accuracy of the system.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.7 no.4
• /
• pp.111-118
• /
• 2011

Recent advances in the media have no special change is the development of the 3D stereoscopic image, which started in the movie is coming over now to the broadcast. Confusing variety having, in the production of 3D images that are waiting for the standardized production. 3D images of them being used in broadcast subtitles, first because there is no standardized production systems, making it look is dedicated to the time and effort. This research necessary to create 3D images of these subtitles, titles, text-based objects, such as Rig imaging using a standardized way to synthesize the most stable is proposed. First, with captions or titles, and the readability and understanding of the uniqueness to the human eye to create an environment that is kind of crowd. Because of this, excessive camera Ferrell Rex (gap) created a branch bunch of snow, work should not hurt readability. 100 adult men and women throughout the experiment.

• Korean Association of Arts Management
• /
• no.50
• /
• pp.213-241
• /
• 2019

Recently, many interests in the economic contribution of performing arts for the city's tourist attractions have been increasing, and the policy projects supporting surtitle for foreign tourists are expanding. Therefore, the purpose of this study is to explore the acceptance process of subtitle systems using the TAM(Technical Acceptance Model) to understand the influential relations of factors affecting the viewing of the performance of subtitling service by foreign tourists. Data for empirical analysis were collected in a survey of foreign tourists who had experienced performance subtitles with smart pads in three languages. The results of this study are as follows. First, the higher the information system quality of the performance subtitles, the higher the perceived usefulness of the subtitles. Second, for Korean performances, the decreasing level of both the performance-based risk and the psychological risk has a positive influence on the viewing intent. But, the decreasing level of the financial risk has a negative influence on the viewing intent. Third, the decreasing level of performance risk has a positive influence on the perceived usefulness, while the decreasing level of psychological risk has a negative influence on the perceived usefulness. Finally, the psychological risk has the moderating effect of the viewing intention, which it has a negative influence on the perceived usefulness.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.5
• /
• pp.128-137
• /
• 2009

This research aimed at providing the direction for future improvement of broadcast subtitle design by identifying the user perception on broadcast subtitles of Terrestrial DMB. First, we contemplated on the existing research about broadcast subtitles. As a result, we found out that broadcast subtitle plays an essential role when watching a program and that the minimization of letters, clear fonts and color arrangement, rearrangement of components were identified as main factors that increase readability. However, the terrestrial DMB user evaluation on image quality, composition, color and brightness was not that positive. In addition, the evaluation on the readability of broadcast subtitle, information transmission, subtitle composition, letter font, number and size of letter was more negative. Developing a subtitle design which considers user convenience and suits terrestrial DMB screens in aspects of broadcast subtitle form and composition, limit of information, clearness and size of the letter is required.

• Journal of Digital Convergence
• /
• v.19 no.3
• /
• pp.25-35
• /
• 2021

We are able to watch international multimedia anytime and anywhere, if we have the devices to connect Internet. Netflix and Youtube are the most massive and the most visited streaming platforms in the world. So If audiences are not familiar with the exotic culture such as behaviors, contexts, sarcasm, history and the current issues, It would happen a consequence that they entirely have to rely on subtitles in order to get inform. This research hereby aims to compare Korean transcriptions of the same movies streamed by the two selected platforms(Netflix and Youtube). As a result, good translation is that translators should use appropriate omissions and detailed explanations in limited time and space so that audience can concentrate on the vedio. If translators study the work in depth and spend enough time working on it, the quality of translation will definitely increase. Finally, this study contributed to the revitalization of the video translation market, which is still in the past, through the misinterpretation of videos produced at a low unit price and with minimal time without guidelines for video translation.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.279-285
• /
• 2024

This study aims to evaluate the accuracy and completeness of Korean and English closed captions for Netflix's "Squid Game" and to present implications based on the findings. To achieve this, the closed captioning guidelines of the U.S. Federal Communications Commission, DCMP, and the Korea Communications Commission were identified and analyzed. The analysis of the subtitle of the entire "Squid Game" series reveals that, while Korean closed captions accurately present slangs and titles, they present non-existent information in speaker identification. In English closed captions, speaker identification guidelines are well followed, but omissions of slangs and title mistranslations are observed. In terms of completeness, both Korean and English closed captions are found to omit certain audio parts. To address these issues, the study suggests strengthening the QA process, establishing a system to communicate original text problems during translation, and utilizing general English subtitles.

• Journal of the Korean housing association
• /
• v.10 no.1
• /
• pp.37-50
• /
• 1999

The aim of this study is to consider the meaning of the traditional dwelling house and the cardinal points. The cardinal points is a complex concept of the body-scheme direction and celestial direction. This paper explains the meanings of the traditional dwelling house under the following three subtitles; dwelling as the image of the cosmos; dwelling as the center of the world; dwelling as the subjective space. The traditional dwellings have the prominent characteristic of the image of the cosmos and the center of the world which is regarded the human and the architecture as the microcosmos, and which communicates the heaven with the earth. The traditional dwellings which aims to harmonize the human with the nature have the subjective and meaningful space which articulates the nature through the self-systematization.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.397-400
• /
• 2020

본 논문은 영화에 나오는 효과음을 자막으로 생성해주는 자동자막생성을 제안하며, 그의 첫 단계로써 다중 사운드 분류 모델을 제안하였다. 고양이, 강아지, 사람의 음성을 분류하기 위해 사운드 데이터의 특정벡터를 추출한 뒤, 4가지의 기계학습에 적용한 결과 최적모델로 딥러닝이 선정되었다. 전처리 과정 중 주성분 분석의 유무에 따라 정확도는 81.3%와 33.3%로 확연한 차이가 있었으며, 이는 복잡한 특징을 가지는 사운드를 분류하는데 있어 주성분 분석과 넓고 깊은 형태의 신경망이 보다 개선된 분류성과를 가져온 것으로 생각된다.