• Journal of information and communication convergence engineering
• /
• v.21 no.1
• /
• pp.75-81
• /
• 2023

Video platforms, including YouTube, have a structure in which the number of video views is directly related to the publisher's profits. Therefore, video publishers induce viewers by using provocative titles and thumbnails to garner more views. The conventional technique used to limit such harmful videos has low detection accuracy and relies on follow-up measures based on user reports. To address these problems, this study proposes a technique to improve the accuracy of filtering harmful media using thumbnails, titles, and audio data from videos. This study analyzed these three pieces of multimodal information; if the number of harmful determinations was greater than the set threshold, the video was deemed to be harmful, and its upload was restricted. The experimental results showed that the proposed multimodal information extraction technique used for harmfulvideo filtering achieved a 9% better performance than YouTube's Restricted Mode with regard to detection accuracy and a 41% better performance than the YouTube automation system.

• Journal of Distribution Science
• /
• v.21 no.9
• /
• pp.43-53
• /
• 2023

Purpose: This study aims to examine the demographic similarities and differences in objectives, methodology, and findings of previous studies in the context of gaining financial literacy using videos. This study employs a systematic review design. Research design, data and methodology: Based on the content analysis method, 15 articles were chosen from Scopus and Science Direct during 2015-2020. After formulating the research questions, the paper identification process, screening, eligibility, and quality appraisal are discussed in the methodology. The keywords for the advanced search included "Financial literacy," "Financial Education," and "Video". Results: The results of this study indicate the effectiveness of learning financial literacy using videos. Significant results were obtained when students interacted with the video content distribution. The findings of this study provide an overview and lead to a better understanding of the use of video in financial literacy. Conclusions: This study is important as a guide for educators in future research and practice planning. A systematic review on this topic is the research gap. Video learning was active learning that involved student-centered activities that help students engage with financial literacy. By conducting a systematic review, researchers and readers may also understand how extending an individual's financial literacy may change after financial education.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.35-38
• /
• 2009

The paper presents an effective method to detect fire in video surveillance and monitoring system. The main contribution of this work is that we successfully use the Hidden Markov Models in the process of detecting the fire with a few preprocessing steps. First, the moving pixels detected from image difference, the color values obtained from the fire flames, and their pixels clustering are applied to obtain the image regions labeled as fire candidates; secondly, utilizing massive training data, including fire videos and non-fire videos, creates the Hidden Markov Models of fire and non-fire, which are used to make the final decision that whether the frame of the real-time video has fire or not in both temporal and spatial analysis. Experimental results demonstrate that it is not only robust but also has a very low false alarm rate, furthermore, on the ground that the HMM training which takes up the most time of our whole procedure is off-line calculated, the real-time detection and alarm can be well implemented when compared with the other existing methods.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.2
• /
• pp.51-58
• /
• 2023

This paper proposes a deep learning method for estimating the heart rate from facial videos. Our proposed method estimates remote photoplethysmography (rPPG) signals to predict the heart rate. Although there have been proposed several methods for estimating rPPG signals, most previous methods can not be utilized in low-power single board computers due to their computational complexity. To address this problem, we construct a lightweight student model and employ a knowledge distillation technique to reduce the performance degradation of a deeper network model. The teacher model consists of 795k parameters, whereas the student model only contains 24k parameters, and therefore, the inference time was reduced with the factor of 10. By distilling the knowledge of the intermediate feature maps of the teacher model, we improved the accuracy of the student model for estimating the heart rate. Experiments were conducted on the UBFC-rPPG dataset to demonstrate the effectiveness of the proposed method. Moreover, we collected our own dataset to verify the accuracy and processing time of the proposed method on a real-world dataset. Experimental results on a NVIDIA Jetson Nano board demonstrate that our proposed method can infer the heart rate in real time with the mean absolute error of 2.5183 bpm.

• ETRI Journal
• /
• v.44 no.1
• /
• pp.73-84
• /
• 2022

The moving picture experts group (MPEG) immersive video (MIV) technology has been actively developed and standardized to efficiently deliver immersive video to viewers in order for them to experience immersion and realism in various realistic and virtual environments. Such services are provided by MIV technology, which uses multiview videos as input. The pruning process, which is an important component of MIV technology, reduces interview redundancy in multiviews videos. The primary aim of the pruning process is to reduce the amount of data that available video codec must handle. In this study, two approaches are presented to improve the existing pruning algorithm. The first method determines the order in which images are pruned. The amount of overlapping region between the source views is then used to determine the pruning order. The second method considers global region-wise color similarity to minimize matching ambiguity when determining the pruning area. The proposed methods are evaluated under common test condition of MIV, and the results show that incorporating the proposed methods can improve both objective and subjective quality.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.33-36
• /
• 2021

In this paper, we propose a new method for improving compression efficiency of immersive video using reinforcement learning. Immersive video means a video that a user can directly experience, such as 3DOF+ videos and Point Cloud videos. It has a vast amount of information due to their characteristics. Therefore, lots of compression methods for immersive video are being studied, and generally, a method, which projects an 3D image into 2D image, is used. However, in this process, a region where information does not exist is created, and it can decrease the compression efficiency. To solve this problem, we propose the reinforcement learning-based filling method with considering the characteristics of images. Experimental results show that the performance is better than the conventional padding method.

• Research in Mathematical Education
• /
• v.26 no.2
• /
• pp.45-61
• /
• 2023

Number talks as a brief instructional routine benefits students and teachers. In general, the routines consist of four steps- introducing, posing questions, collecting answers, sharing ideas. This paper focuses on the sharing ideas step in which multiple strategies are shared by students because teachers sometimes do not know what to do with these multiple ideas. One way is to support students to engage in comparison given that teachers are expected to support students to compare strategies in number talks. This paper explores whether and how 15 prospective teachers supported students in their practicum classroom to compare different strategies in their enacted number talk. In this paper, 15 videos of number talks enacted by the prospective teachers were collected. Analyzing the videos produced multiple episodes in relation to comparing strategies, including 1) where prospective teachers created pre-conditions for comparison, 2) where they invited students for comparison, 3) where they pressed students to compare, and 4) where they offered their own way to compare. There were two patterns that might limit the potential of having multiple strategies as conditions for comparison. Additionally, this paper found that even though the prospective teachers missed opportunities to support students to compare different strategies, there were two ways for teachers to support students to engage in comparison. These findings can be used for mathematics teacher educators to support prospective teachers.

• Electronics and Telecommunications Trends
• /
• v.39 no.2
• /
• pp.33-42
• /
• 2024

With the recent rapid development of artificial intelligence (AI) technology, its use is gradually expanding to include creative areas and building new content using generative AI solutions, reaching beyond existing data analysis and reasoning applications. Content creation using generative AI faces challenges owing to technical limitations and other aspects such as copyright compliance. Nevertheless, generative AI may increase the productivity of experts and overcome barriers to creative work by allowing users to easily express their ideas as digital content. Thus, various types of applications will continue to emerge. As images and videos can be created using text input on a prompt, generative AI allows to create and edit digital assets quickly. We present trends in generative AI technology for images, videos, three-dimensional (3D) assets and scenes, digital humans, interactive content, and interfaces. In addition, the prospects for future technological development in this field are discussed.

• Journal of Broadcast Engineering
• /
• v.17 no.4
• /
• pp.640-658
• /
• 2012

One of the existing terrestrial multi-channel DTV service frameworks, called KoreaView, provides four programs, composed of MPEG-2 based one HD video and H.264/AVC based three SD videos within one single 6MHz frequency bandwidth. However the additional 3 SD videos can not provide enough quality due to its reduced spatial resolution and low target bitrates. In this paper, we propose a framework, which is called a terrestrial multi-channel high quality hybrid DTV service, to overcome such a weakness of KoreaView services. In the proposed framework, the three additional SD videos are encoded based on an H.264/SVC Spatial Base layer, which is compliant with H.264/AVC, and are delivered via broadcasting networks. On the other hand, and the corresponding three additional HD videos are encoded based on an H.264/SVC Spatial Enhancement layer, which are transmitted over broadband networks such as Internet, thus allowing the three additional videos for users with better quality of experience. In order to verify the effectiveness of the proposed framework, various experimental results are provided for real video contents being used for DTV services. First, the experimental results show that, when the SD sequences are encoded by the H.264/SVC Spatial Base layer at a target bitrate of 1.5Mbps, the resulting PSNR values are ranged from 34.5dB to 42.9dB, which is a sufficient level of service quality. Also it is noted that 690kbps-8,200kbps are needed for the HD test sequences when they are encoded in the H.264/SVC Spatial Enhancement layer at similar PSNR values for the same HD sequences encoded by MPEG-2 at a target bitrate of 12 Mbps.

• Journal of Broadcast Engineering
• /
• v.19 no.2
• /
• pp.148-157
• /
• 2014

Various techniques have been developed for efficient compression of stereoscopic 3D videos. Mixed-resolution based approach is one representative bit-rate saving method based on the characteristics of human visual system that the mixed-resolution stereoscopic videos are perceived close to the higher resolution. However, when the difference between the left and right image resolutions is bigger than a certain threshold level, it causes the perceived quality degradation of the 3D images. Subsequently, several researches tried to find the correlation between the difference in resolution and the level of the perceived quality degradation, but they conducted the experiments just considering the difference in resolution without considering the viewing distances, so thereby different results were retrieved from test to test. In this work, we calculated the optimal viewing distance based on the human visual system, and conducted the subjective tests with the calculated viewing distance. With the results, we demonstrate that the fixed and mobile hybrid 3DTV, which is based on mixed-resolution stereoscopic images, can provide the high quality 3D services.