• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.544-564
• /
• 2022

Underwater images often suffer from color distortion, blurring and low contrast, which is caused by the propagation of light in the underwater environment being affected by the two processes: absorption and scattering. To cope with the poor quality of underwater images, this paper proposes a multiscale fusion underwater image enhancement method based on channel attention mechanism and local binary pattern (LBP). The network consists of three modules: feature aggregation, image reconstruction and LBP enhancement. The feature aggregation module aggregates feature information at different scales of the image, and the image reconstruction module restores the output features to high-quality underwater images. The network also introduces channel attention mechanism to make the network pay more attention to the channels containing important information. The detail information is protected by real-time superposition with feature information. Experimental results demonstrate that the method in this paper produces results with correct colors and complete details, and outperforms existing methods in quantitative metrics.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.794-802
• /
• 2022

The recovery of reasonable depth information from different scenes is a popular topic in the field of computer vision. For generating depth maps with better details, we present an efficacious monocular depth prediction framework with coordinate attention and feature fusion. Specifically, the proposed framework contains attention, multi-scale and feature fusion modules. The attention module improves features based on coordinate attention to enhance the predicted effect, whereas the multi-scale module integrates useful low- and high-level contextual features with higher resolution. Moreover, we developed a feature fusion module to combine the heterogeneous features to generate high-quality depth outputs. We also designed a hybrid loss function that measures prediction errors from the perspective of depth and scale-invariant gradients, which contribute to preserving rich details. We conducted the experiments on public RGBD datasets, and the evaluation results show that the proposed scheme can considerably enhance the accuracy of depth prediction, achieving 0.051 for log10 and 0.992 for δ<1.25³ on the NYUv2 dataset.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.1-14
• /
• 2024

Time-series forecasting is extensively used in the actual world. Recent research has shown that Transformers with a self-attention mechanism at their core exhibit better performance when dealing with such problems. However, most of the existing Transformer models used for time series prediction use the traditional encoder-decoder architecture, which is complex and leads to low model processing efficiency, thus limiting the ability to mine deep time dependencies by increasing model depth. Secondly, the secondary computational complexity of the self-attention mechanism also increases computational overhead and reduces processing efficiency. To address these issues, the paper designs an efficient multi-layer attention-based time-series forecasting model. This model has the following characteristics: (i) It abandons the traditional encoder-decoder based Transformer architecture and constructs a time series prediction model based on multi-layer attention mechanism, improving the model's ability to mine deep time dependencies. (ii) A cross attention module based on cross attention mechanism was designed to enhance information exchange between historical and predictive sequences. (iii) Applying a recently proposed sparse attention mechanism to our model reduces computational overhead and improves processing efficiency. Experiments on multiple datasets have shown that our model can significantly increase the performance of current advanced Transformer methods in time series forecasting, including LogTrans, Reformer, and Informer.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.1
• /
• pp.55-61
• /
• 2020

With the development of deep learning technology and advances in computing power, video-based research is now gaining more and more attention. Video data contains a large amount of temporal and spatial information, which is the biggest difference compared with image data. It has a larger amount of data. It has attracted intense attention in computer vision. Among them, motion recognition is one of the research focuses. However, the action recognition of human in the video is extremely complex and challenging subject. Based on many research in human beings, we have found that artificial intelligence-like attention mechanisms are an efficient model for cognition. This efficient model is ideal for processing image information and complex continuous video information. We introduce this attention mechanism into video action recognition, paying attention to human actions in video and effectively improving recognition efficiency. In this paper, we propose a new 3D residual attention network using convolutional neural network based on two attention models to identify human action behavior in the video. An evaluation result of our model showed up to 90.7% accuracy.

• Journal of information and communication convergence engineering
• /
• v.10 no.3
• /
• pp.300-306
• /
• 2012

An image attention model and its application to image quality assessment are discussed in this paper. The attention model is based on rarity quantification, which is related to self-information to attract the attention in an image. It is relatively simpler than the others but results in taking more consideration of global contrasts between a pixel and the whole image. The visual attention model is used to develop a local distortion predictor, named color visual differences predictor (CVDP), in color images in order to effectively detect luminance and color distortions.

• Sleep Medicine and Psychophysiology
• /
• v.5 no.2
• /
• pp.119-133
• /
• 1998

Attentional processes facilitate cognitive and behavioral performance in several ways. Attention serves to reduce the amount of information to receive. Attention enables humans to direct themselves to appropriate aspects of external environmental events and internal operations. Attention facilitates the selection of salient information and the allocation of cognitive processing appropriate to that information. Attention is not a unitary process that can be localized to a single neuroanatomical region. Before the cortical registration of sensory information, activation of important subcortical structures occurs, which is called as an orienting response. Once sensory information reaches the sensory cortex, a large number of perceptual processes occur, which provide various levels of perceptual resolution of the critical features of the stimuli. After this preattentional processing, information is integrated within higher cortical(heteromodal) systems in inferior parietal and temporal lobes. At this stage, the processing characteristics can be modified, and the biases of the system have a direct impact on attentional selection. Information flow has been traced through sensory analysis to a processing stage that enables the new information to be focused and modified in relation to preexisting biases. The limbic and paralimbic system play significant roles in modulating attentional response. It is labeled with affective salience and is integrated according to ongoing pressures from the motivational drive system of the hypothalamus. The salience of information greatly influences the allocation of attention. The frontal lobe operate response selection system with a reciprocal interaction with both the attention system of the parietal lobe and the limbic system. In this attentional process, the search with the spatial field is organized and a sequence of attentional responses is generated. Affective, motivational and appectitive impulses from limbic system and hypothalamus trigger response intention, preparation, planning, initiation and control of frontal lobe on this process. The reticular system, which produces ascending activation, catalyzes the overall system and increases attentional capacity. Also additional energetic pressures are created by the hypothalamus. As psychophysiological measurement, skin conductance, pupil diameter, muscle tension, heart rate, alpha wave of EEG can be used. Event related potentials also provide physiological evidence of attention during information process. NI component appears to be an electrophysiological index of selective attention. P3 response is developed during the attention related to stimulus discrimination, evaluation and response.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5580-5593
• /
• 2019

A malicious Uniform Resource Locator (URL) recognition and detection method based on the combination of Attention mechanism with Convolutional Neural Network and Long Short-Term Memory Network (Attention-Based CNN-LSTM), is proposed. Firstly, the WHOIS check method is used to extract and filter features, including the URL texture information, the URL string statistical information of attributes and the WHOIS information, and the features are subsequently encoded and pre-processed followed by inputting them to the constructed Convolutional Neural Network (CNN) convolution layer to extract local features. Secondly, in accordance with the weights from the Attention mechanism, the generated local features are input into the Long-Short Term Memory (LSTM) model, and subsequently pooled to calculate the global features of the URLs. Finally, the URLs are detected and classified by the SoftMax function using global features. The results demonstrate that compared with the existing methods, the Attention-based CNN-LSTM mechanism has higher accuracy for malicious URL detection.

• Asia pacific journal of information systems
• /
• v.30 no.4
• /
• pp.741-757
• /
• 2020

The outbreak of COVID-19 has changed our lifestyle. People spend much more time on YouTube, SNS and online shopping than before. Accordingly, the number of product review videos are steeply increasing in YouTube platform. When people watched the review videos, they might search additional information if they liked the videos. This study aims to investigate how the informativeness and the degree of attention gathering of product review videos influence on the product information sourcing intention and persuasion knowledge. We also try to find whether prior YouTube experience affects the relationship between the degree of attention gathering and persuasion knowledge. We conducted an online survey on 499 participants and analyzed using partial least square methods. Results show that 1) informativeness and the degree of attention gathering towards product review videos influence on the product information sourcing intention and user's persuasion knowledge. 2) Viewers' YouTube experiences moderate the increase of the viewers' persuasion knowledge caused by increasing the degree of viewers' attention gathering. This study implies that YouTube product review videos could be created in strategic manners. Also, it could be inferred that consumers' prior YouTube experiences may reduce negative potentials of the degree of attention gathering onto persuasion knowledge.

• Journal of Information Science Theory and Practice
• /
• v.8 no.3
• /
• pp.6-14
• /
• 2020

On information markets, we can identify different relations between sellers and their customers, with some users paying with money, some paying with attention, and others paying with their personal data. For the description of these different market relations, this article introduces the notion of arity into the scientific discussion. On unary information markets, customers pay with their money; examples include commercial information suppliers. Binary information markets are characterized by one market side paying with attention (e.g., on the search engine Google) or with personal data (e.g., on most social media services) and the other market side (mainly advertisers) paying with money. Our example of a ternary market is a social media market with the additional market side of influencers. If customers buy on unary markets, they know what to pay (in terms of money). If they pay with attention or with their personal data, they do not know what they have to pay exactly in the end. On n-ary markets (n greater than 1), laws should regulate company's abuse of money and-which is new-abuse of data streams with the aid of competition (or anti-trust) laws, and by modified data protection laws, which are guided by fair use of end users' attention and data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.493-495
• /
• 2023

Deep learning methods and attention mechanisms have been incorporated to improve facial emotion recognition, which has recently attracted much attention. The fusion approaches have improved accuracy by combining various types of information. This research proposes a fusion network with self-attention and local attention mechanisms. It uses a multi-layer perceptron network. The network extracts distinguishing characteristics from facial images using pre-trained models on RAF-DB dataset. We outperform the other fusion methods on RAD-DB dataset with impressive results.