• Proceedings of the Korea Society of Design Studies Conference
• /
• 2001.05a
• /
• pp.134-135
• /
• 2001

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.166-173
• /
• 2024

This study explores lip-sync detection, focusing on the synchronization between lip movements and voices in videos. Typically, lip-sync detection techniques involve cropping the facial area of a given video, utilizing the lower half of the cropped box as input for the visual encoder to extract visual features. To enhance the emphasis on the articulatory region of lips for more accurate lip-sync detection, we propose utilizing a pre-trained visual attention-based encoder. The Visual Transformer Pooling (VTP) module is employed as the visual encoder, originally designed for the lip-reading task, predicting the script based solely on visual information without audio. Our experimental results demonstrate that, despite having fewer learning parameters, our proposed method outperforms the latest model, VocaList, on the LRS2 dataset, achieving a lip-sync detection accuracy of 94.5% based on five context frames. Moreover, our approach exhibits an approximately 8% superiority over VocaList in lip-sync detection accuracy, even on an untrained dataset, Acappella.

• ETRI Journal
• /
• v.36 no.3
• /
• pp.479-489
• /
• 2014

This paper presents a model-based image steganography method based on Watson's visual model. Model-based steganography assumes a model for cover image statistics. This approach, however, has some weaknesses, including perceptual detectability. We propose to use Watson's visual model to improve perceptual undetectability of model-based steganography. The proposed method prevents visually perceptible changes during embedding. First, the maximum acceptable change in each discrete cosine transform coefficient is extracted based on Watson's visual model. Then, a model is fitted to a low-precision histogram of such coefficients and the message bits are encoded to this model. Finally, the encoded message bits are embedded in those coefficients whose maximum possible changes are visually imperceptible. Experimental results show that changes resulting from the proposed method are perceptually undetectable, whereas model-based steganography retains perceptually detectable changes. This perceptual undetectability is achieved while the perceptual quality - based on the structural similarity measure - and the security - based on two steganalysis methods - do not show any significant changes.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.30 no.6 s.154
• /
• pp.992-1000
• /
• 2006

The main purpose of this research is to develop the methodology of objective evaluation of clothing appearance by eye movement analysis. The visual clothing items used in this study were skirt, one-piece, pants and shirt with the style variation of silhouette and details. By observing eye movement during visual evaluation of clothing, we can achieve the basic fixation data of eye movement. Moreover, we developed the Matlab program to extract the fixation coordinate and number of eye fixation on each part of the clothing item. As results, there were differences in the duration of fixation time for each item and the fixation time was not different by styles within a clothing item. However, we could find differences in the fixation time within a style, in other words, we could select the important parts of the clothing by observing the fixation time in a certain clothing item. It is also noted that time required in visual information processing differs depending on the item, and there was a region which contain more information independent with styles in the same item. By developing the objective method of visual evaluation that correspond to human's visual information processing, the results are expected to be applied in the retrieval program in internet shopping mall or in the development of contents for advertisement of clothing.

• Journal of the Korean Society for information Management
• /
• v.26 no.3
• /
• pp.111-129
• /
• 2009

This study examined the usability of text-based search and visual search of a large multidisciplinary library database to provide an empirical analysis of the acceptability of visual systems in the information retrieval environment. It also examined if there are differences in the usability assessment based on experimental order. The results indicated that the text-based search supported users' search behaviors more efficiently than the visual search. Also the text-based search was rated higher than the visual search in terms of user perceptions of four usability factors.

• Korean Journal of Plant Taxonomy
• /
• v.47 no.2
• /
• pp.124-131
• /
• 2017

Species identification is a fundamental and routine process in plant systematics, and linguistic-based dichotomous keys are widely used in the identification process. Recently, novel tools for species identification have been developed to improve the accuracy, ease to use, and accessibility related to these tasks for a broad range of users given the advances in information and communications technology. A visual identification key is such an approach, in which couplets consist of images of plants or a part of a plant instead of botanical terminology. We developed a visual identification key for 101 taxa of Orchidaceae in Korea and evaluated its performance. It uses short statements for image couplets to avoid misinterpretations by users. The key at the initial steps (couplets) uses relatively easy characters that can be determined with the naked eye. The final steps of the visual key provide images of species and information about distributions and flowering times to determine the species that best fit the available information. The number of steps required to identify a species varies, ranging from three to ten with an average of 4.5. A performance test with senior college students showed that species were accurately identified using the visual key at a rate significantly higher than when using a linguistic-based dichotomous key and a color manual. The findings presented here suggest that the proposed visual identification key is a useful tool for the teaching of biodiversity at schools, for the monitoring of ecosystems by citizens, and in other areas that require rapid, easy, and accurate identifications of species.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.5
• /
• pp.55-60
• /
• 2021

This study aims to investigate the effects of 4 weeks visual biofeedback training on the knee joint angle and muscle activities of lower extremity. The participants in this study were 15 volunteers with hyperextended knee. To improve the hyperextended knee, visual biofeedback training was used during 4 weeks. The training is an exercise to maintain the balance between the anterior weight bearing and posterior weight bearing of the plantar foot. The knee joint angle significantly increased and the muscle activity of tibialis anterior was significantly decreased after visual biofeedback training. It was confirmed that visual biofeedback training of correcting hyperextended knee through the information on the plantar pressure distribution has a therapeutic effect.

• The Research Journal of the Costume Culture
• /
• v.27 no.6
• /
• pp.539-552
• /
• 2019

The purpose of the current study was to examine the role of information on shapewear's functionality in consumers' purchase decisions in an online shopping context. Through two steps of stimulus development process, four mock websites were developed to conduct a main study. In the main study, a 2 (visual information: absent vs. present images of the shapewear's functionality) x 2 (verbal information: absent vs. present descriptions of the shapewear's functionality) between-subject factorial design was employed to examine the impact of visual and verbal information regarding the functionality of shapewear on the consumer decision-making process (i.e., attitudes and purchase intentions). The results showed that verbal information about how shapewear reduces the size of specific body parts (i.e., waist, abdomen, hips, and thighs) were effective in increasing perceived attractiveness in an online context, which increased attitudes and purchase intentions. In addition, attitudes toward the shapewear mediated the effects of expected physical attractiveness on purchase intentions. The results of this study provided empirical support for the importance of expected physical attractiveness in consumers' online purchase decision on shapewear and useful managerial implications for enhancing the effectiveness of online shapewear presentations by including descriptions of the functionality of shapewear in decreasing the size of body parts.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.36 no.11
• /
• pp.1091-1097
• /
• 2012

Nowadays, some movie theaters provide additional sensory information in 3D movies to enhance visually induced motion perception. However, no studies have investigated how motion perception increases. Thus, in this study, we examined the effect of visual coherent sensory information on visually induced motion perception and quantification of sensory information. A visual stimulus rotated sinusoidally and visual coherent sensory information were applied as vibrations to a subject's foot. We measured the sway of the subject's body by using a force plate and somatosensory bar rotation that represents the subject's perception of the horizon using an encoder. By using this data, we obtained the weight of the sensory information using a Kalman filter. As a result, it was found that subjects rotated the somatosensory bar more when visual coherent vibrations were applied. The weight of vision also increased when visual coherent vibrations were applied. Thus, we can conclude that visual coherent sensory information tends to enhance visually induced motion perception and weight of vision.

• Journal of the Korean Home Economics Association
• /
• v.47 no.5
• /
• pp.23-34
• /
• 2009

The purpose of this study was to e${\times}$amine the effect of visual imagery stimulated by product information on consumer responses in online shopping conte${\times}$ts. Dual coding theory provided the theoretical framework of the study. The proposed model of the study was e${\times}$amined by conducting an e${\times}$periment using mock apparel websites with a between-subject factorial design: [2 (pictorial information: detailed views vs. no detailed views) ${\times}$ 2 (verbal information: detailed descriptions vs. abstract descriptions)]. A total of 439 female college students participated in the e${\times}$periment, and 433 responses were ultimately used to test the hypotheses. The findings from the results revealed: (1) the main effects of the pictorial and verbal information on visual imagery, and (2) positive relationships between (a) visual imagery and mood, (b) visual imagery and perceived product quality, (c) mood and perceived product quality, and (d) perceived quality and purchase intentions.