• The Journal of the Korea Contents Association
• /
• v.6 no.1
• /
• pp.41-53
• /
• 2006

In this paper, an adaptive ROI(region of interest) detection system for spatialtemporal features is proposed. It utilizes spatiotemporal features for the purpose of detecting ROI. It is assumed that motion representing temporal visual conspicuity between adjacent frames takes higher priority over spatial visual conspicuity. Because objects or regions in motion usually draw stronger attention than others in motion pictures. In case of still images visual features that constitute topographic feature maps are used as spatial features. Comparative experiments with a human subjective evaluation show that correct detection rate of visual attention region is improved by exploiting both spatial and temporal features compared to the case of exploiting either feature.

• Korean Journal of Cognitive Science
• /
• v.16 no.3
• /
• pp.155-174
• /
• 2005

Oh and Kim (2004) and Woodman and Lurk (2004) demonstrated that spatial working memory (SWM) load Interfered concurrent visual search and that search process also impaired the maintenance of spatial information implying that visual search and SWM task both require access to the same limited-capacity mechanism. Two obvious possibilities have been suggested about what this shared limited-capacity mechanism is: common demand for attention to the locations where the items f9r the two tasks were presented (spatial attention load hypothesis), and common use of working memory to maintain a record of locations have been processed(SWM load hypothesis). To test these two hypothetical explanations, Experiment 1 replicated the mutual interference between visual search and SWM task in spite of difference of procedure with preceding researches; possible areas where the items for two tasks were presented were not separated. In Experiment 2, we presented the items for visual search either in the same quadrants where the items for SWM task had appeared (same-location rendition) or in the different quadrants (different-location condition). As a result, search efficiency was more impaired in the different-location condition than in the same-location condition. The memory accuracy was worse in the different-location rendition than in the same-location rendition. Overall results of study indicate that the mutual interference between SWM and visual search might be related to the overload of spatial attention, but not to that of SWM.

• The Journal of the Korea Contents Association
• /
• v.19 no.6
• /
• pp.214-221
• /
• 2019

Visual perception information acquired through human eyes contains much information on how to view visual stimuli using eye tracking technology, it is possible to acquire and analyze consumer visual information as quantitative data. These measurements can be used to measure emotions that customers feel unconsciously, and they can be directly collected by numerically quantifying the character's search response through eye tracking. In this study, we traced the character's area of interest (AOI) and found that the average of fixation duration, count, average of visit duration, count, and finally the time to first fixation was analyzed. As a result of analysis, it was found that there were many cognitive processing processes on the face than the character's body, and the visual attention was high. The visual attention of attraction factor has also been able to verify that attraction is being presented as an important factor in determining preferences for characters. Based on the results of this study, further studies of more characters will be conducted and quantitative interpretation methods can be used as basic data for character development and factors to be considered in determining character design.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3976-3990
• /
• 2022

Currently, cross-attention is widely used in Siamese trackers to replace traditional correlation operations for feature fusion between template and search region. The former can establish a similar relationship between the target and the search region better than the latter for robust visual object tracking. But existing trackers using cross-attention only focus on rich semantic information of high-level features, while ignoring the appearance information contained in low-level features, which makes trackers vulnerable to interference from similar objects. In this paper, we propose a Multi-level Cross-attention Siamese network(MCSiam) to aggregate the semantic information and appearance information at the same time. Specifically, a multi-level cross-attention module is designed to fuse the multi-layer features extracted from the backbone, which integrate different levels of the template and search region features, so that the rich appearance information and semantic information can be used to carry out the tracking task simultaneously. In addition, before cross-attention, a target-aware module is introduced to enhance the target feature and alleviate interference, which makes the multi-level cross-attention module more efficient to fuse the information of the target and the search region. We test the MCSiam on four tracking benchmarks and the result show that the proposed tracker achieves comparable performance to the state-of-the-art trackers.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06c
• /
• pp.291-296
• /
• 1998

In the experiment carried out on 20 college students, recorded were frontal, temporal and occipital EEG, skin conductance response, skin conductance level, heart rate and respiration rate during listening to two music fragments with different affective valences and white noise administered immediately after negative visual stimulation. Analysis of physiological patterns observed during the experiment suggests that affective auditory stimulation with music is able to selectively modulate autonomic and cortical activity evoked by preceding aversive visual stimulation and to restore initial baseline levels. On other hand, physiological responses to white noise, which does not possess emotion-eliciting capabilities, evokes response typical for orienting reaction after the onset of a stimulus and is rapidly followed by habituation. Observed responses to white noise were similar to those specific to attention only and had no evidence for any emotion-related processes. Interpretation of the obtained data is considered in terms of the role of emotional and orienting significance of stimuli, dependence of effects on the background physiological activation level and time courses of attention and emotion processes. Physiological parameters are summarized with regard to their potential utility in differentiation of psychological processes induced by auditory stimuli.

• Journal of Korea Multimedia Society
• /
• v.20 no.3
• /
• pp.446-455
• /
• 2017

A color image compression based on saliency map was proposed. The proposed method provides higher quality in saliency blocks on which people's attention focuses, compared with non-saliency blocks on which the attention less focuses at a given bitrate. The proposed method uses 3 different quantization tables according to each block's saliency level. In the experiment using 6 typical images, we compared the proposed method with JPEG and other conventional methods. As the result, it showed that the proposed method (Qup=0.5*Qx) is about 3.1 to 1.2 dB better than JPEG and others in saliency blocks in PSNR at the almost similar bitrate. In the comparison of result images, the proposed one also showed less error than others in saliency blocks.

• Journal of Korea Multimedia Society
• /
• v.23 no.3
• /
• pp.508-515
• /
• 2020

For the success of mobile messenger emoticons, it is important to grab the attentions of users or consumers and identify the influence factors that can satisfy empathy and emotional satisfaction. In this study, first, subjective evaluation of the mobile messenger emoticons of the subjects was examined through a preliminary survey, and then Eye-tracking experiments were conducted to identify the influence factors that can attention of the subject's eyes in the emoticons. The study revealed that emoticons such as Ompangi and Onaeui yeosin highlighting their characters mainly focus on characters(face). Secondly, Gyuiyomjueui and Handprinting emoticons focused on Text. Contrary to earlier studies, such results showed that people are presumed to focus on characteristic elements such as size, form, color and location of visually exposed elements rather than primarily having a keen interest in characters.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.425-430
• /
• 2022

As robots are considered one of the mainstream digital transformations, robots with machine vision becomes a main area of study providing the ability to check what robots watch and make decisions based on it. However, it is difficult to find a small object in the image mainly due to the flaw of the most of visual recognition networks. Because visual recognition networks are mostly convolution neural network which usually consider local features. So, we make a model considering not only local feature, but also global feature. In this paper, we propose a detection method of a small marker on the object using deep learning and an algorithm that considers global features by combining Transformer's self-attention technique with a convolutional neural network. We suggest a self-attention model with new definition of Query, Key and Value for model to learn global feature and simplified equation by getting rid of position vector and classification token which cause the model to be heavy and slow. Finally, we show that our model achieves higher mAP than state of the art model YOLOr.

• Journal of Korea Multimedia Society
• /
• v.21 no.2
• /
• pp.166-172
• /
• 2018

The distraction of the driver's attention causes as much traffic accidents as drowsiness driving. Yet though there have been many studies on drowsiness driving, research on distraction driving is insufficient. In this paper, we divide distraction of attention into visual distraction and cognitive distraction and analyze the EEG of subjects while viewing images of distracting situations. The results show that more information is received and processed when distractions occur. It is confirmed that the probability of accident increases when the driver receives overwhelming amount of information that he or she cannot concentrate on driving.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1318-1330
• /
• 2018

Video captioning refers to the process of extracting features from a video and generating video captions using the extracted features. This paper introduces a deep neural network model and its learning method for effective video captioning. In this study, visual features as well as semantic features, which effectively express the video, are also used. The visual features of the video are extracted using convolutional neural networks, such as C3D and ResNet, while the semantic features are extracted using a semantic feature extraction network proposed in this paper. Further, an attention-based caption generation network is proposed for effective generation of video captions using the extracted features. The performance and effectiveness of the proposed model is verified through various experiments using two large-scale video benchmarks such as the Microsoft Video Description (MSVD) and the Microsoft Research Video-To-Text (MSR-VTT).