• 한국정보전자통신기술학회논문지
• /
• 제16권5호
• /
• pp.301-306
• /
• 2023

Attention is a fundamental aspect in the cognitive process of human. Cognitive system of human body requires to focus on selected information among a vast amount of information from sensory organs. It has widely studied that various environmental factors affected the level of attention; however, few researches have aimed to the effect of direct cryotherapy. In this research, level of attention was studied comparing sub-indexes of FAIR test between groups with different duration of direct cryotheapy to the back of neck. FAIR test is a evaluation tool for visual attention consisting of three sub-indexes. Selective attention, accuracy of attention, and persistence of attention can be independently analyzed by FAIR test. In the analysis of selective attention, cryotherapy for 5 to 20 minutes showed higher result than cryotherapy for 40 minutes. In the analysis of persistence of attention, cryotherapy for 5 to 15 minutes showed higher result than cryotherapy for 40 minutes. Overall, selective attention and persistence of attention turns out to be maximized between 5 to 20 minutes of cryotherapy and tends to decrease afterwards. However, accuracy of attention does not seem to be affected by the duration of cryotherapy. Correlation between selective attention and the skin temperature by cryotherapy tends to be negative supporting the findings by ANOVA and post-hoc test. Correlation between persistence of attention and the skin temperature showed similar results.

• Computers and Concrete
• /
• 제26권5호
• /
• pp.411-420
• /
• 2020

Deep Convolution neural network (DCNN) has been widely used in the healthy maintenance of civil infrastructure. Using DCNN to improve crack detection performance has attracted many researchers' attention. In this paper, a light-weight spatial attention network module is proposed to strengthen the representation capability of ResNet and improve the crack detection performance. It utilizes attention mechanism to strengthen the interested objects in global receptive field of ResNet convolution layers. Global average spatial information over all channels are used to construct an attention scalar. The scalar is combined with adaptive weighted sigmoid function to activate the output of each channel's feature maps. Salient objects in feature maps are refined by the attention scalar. The proposed spatial attention module is stacked in ResNet50 to detect crack. Experiments results show that the proposed module can got significant performance improvement in crack detection.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권8호
• /
• pp.3791-3805
• /
• 2016

The visual attention mechanism includes 2 attention models, the bottom-up (B-U) and the top-down (T-D), the physiology of which have not yet been accurately described. In this paper, the visual attention mechanism is regarded as a Bayesian fusion process, and a visual attention model based on particle filter is proposed. Under certain particular assumed conditions, a calculation formula of Bayesian posterior probability is deduced. The visual attention fusion process based on the particle filter is realized through importance sampling, particle weight updating, and resampling, and visual attention is finally determined by the particle distribution state. The test results of multigroup images show that the calculation result of this model has better subjective and objective effects than that of other models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권9호
• /
• pp.1613-1631
• /
• 2011

Several metrics have been reported in the literature to assess stereo image quality, mostly based on visual attention or human visual sensitivity based distortion prediction with the help of disparity information, which do not consider the combined aspects of human visual processing. In this paper, visual attention and depth assisted stereo image quality assessment model (VAD-SIQAM) is devised that consists of three main components, i.e., stereo attention predictor (SAP), depth variation (DV), and stereo distortion predictor (SDP). Visual attention is modeled based on entropy and inverse contrast to detect regions or objects of interest/attention. Depth variation is fused into the attention probability to account for the amount of changed depth in distorted stereo images. Finally, the stereo distortion predictor is designed by integrating distortion probability, which is based on low-level human visual system (HVS), responses into actual attention probabilities. The results show that regions of attention are detected among the visually significant distortions in the stereo image pair. Drawbacks of human visual sensitivity based picture quality metrics are alleviated by integrating visual attention and depth information. We also show that positive correlation with ground-truth attention and depth maps are increased by up to 0.949 and 0.936 in terms of the Pearson and the Spearman correlation coefficients, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• 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.

• 정보보호학회논문지
• /
• 제33권4호
• /
• pp.621-631
• /
• 2023

적대적 학습은 적대적 샘플에 대한 딥러닝 모델의 강건성을 향상시킨다. 하지만 기존의 적대적 학습 기법은 입력단계의 작은 섭동마저도 은닉층의 특징에 큰 변화를 일으킨다는 점을 간과하여 adversarial loss function에만집중한다. 그 결과로 일반 샘플 또는 다른 공격 기법과 같이 학습되지 않은 다양한 상황에 대한 정확도가 감소한다. 이 문제를 해결하기 위해서는 특징 표현 능력을 향상시키는 모델 아키텍처에 대한 분석이 필요하다. 본 논문에서는 입력 이미지의 attention map을 생성하는 attention module을 일반 모델에 적용하고 PGD 적대적학습을수행한다. CIFAR-10 dataset에서의 제안된 기법은 네트워크 구조에 상관없이 적대적 학습을 수행한 일반 모델보다 적대적 샘플에 대해 더 높은 정확도를 보였다. 특히 우리의 접근법은 PGD, FGSM, BIM과 같은 다양한 공격과 더 강력한 adversary에 대해서도 더 강건했다. 나아가 우리는 attention map을 시각화함으로써 attention module이 적대적 샘플에 대해서도 정확한 클래스의 특징을 추출한다는 것을 확인했다.

• Journal of Information Processing Systems
• /
• 제18권5호
• /
• pp.614-627
• /
• 2022

Aspect-based sentiment analysis is to discover the sentiment polarity towards an aspect from user-generated natural language. So far, most of the methods only use the implicit position information of the aspect in the context, instead of directly utilizing the position relationship between the aspect and the sentiment terms. In fact, neighboring words of the aspect terms should be given more attention than other words in the context. This paper studies the influence of different position embedding methods on the sentimental polarities of given aspects, and proposes a position embedding interactive attention network based on a long short-term memory network. Firstly, it uses the position information of the context simultaneously in the input layer and the attention layer. Secondly, it mines the importance of different context words for the aspect with the interactive attention mechanism. Finally, it generates a valid representation of the aspect and the context for sentiment classification. The model which has been posed was evaluated on the datasets of the Semantic Evaluation 2014. Compared with other baseline models, the accuracy of our model increases by about 2% on the restaurant dataset and 1% on the laptop dataset.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(4)
• /
• pp.239-242
• /
• 2001

As systems for real time computer vision are confronted with prodigious amounts of visual information, it has become a priority to locate and analyze just that information essential to the task at hand, while ignoring the vast flow of irrelevant detail. A method of achieving this is to using human visual attention mechanism. In this paper, short review of human visual attention mechanisms and some computation models of visual attention were shown. This paper can be used as the basic data for researches on development of visual attention system that can perform various complex tasks more efficiently.

• 대한간호학회지
• /
• 제20권2호
• /
• pp.214-226
• /
• 1990

For a man to maintain attention, he needs to keep a certain level of arousal. An inordinate increase or decrease in the level of arousal eventually has a negative influence on attention. Precedent research has shown that the degree of attention changes when an experience of stress is related to anxiety resulting in a rise in arousal. This research was done to examine this hypothesis by looking at the 27 female students, 14 of whom had failed in the annual examination. The results of the investigation are as follows : The stress of failure in the examination was seen to raise the level of physiological arousal. Although pulse and electromyography showed no significant change, further inquiries should be made based on other types of methodology. In spite of the rise of arousal, the performance of selective task was degraded. This suggests those students failed to give moderate attention to given information for that kind of task. But the exact reason of that failure was not identified : that is it was difficult decide whether they gave too much attention to the anxiety brought about by stress. Performance of integral tasks, however, did not show any degradation. Judging from these results, stress seems to exert significant influence on attention in the selection of the appropriate information among the various options given. This offers an important hint in relation to the health care situation where nursing information is offered. Clients who receive nursing information in stressful situations may have difficulty in separating and selecting this helpful information from other options which they have acquired through their life experience. The content and terminology of nursing information may be strange and unintelligible to clients, although they are quite familiar and distinct to nurses. So, it is desirable for nurses to give, in addition and at the same time when nursing information is given, some certain related information as devices for selection, instead of merely giving nursing informations as such. So far it is not clear whether the concepts of information processing theory can be suitably applied to nursing. However, it is obvious, according to this research, that the quality of attention is disturbed in the stress situation. This is why further inquiries should be made into attention in practical nursing situation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4439-4455
• /
• 2021

Compared with two-stage object detection algorithms, one-stage algorithms provide a better trade-off between real-time performance and accuracy. However, these methods treat the intermediate features equally, which lacks the flexibility to emphasize meaningful information for classification and location. Besides, they ignore the interaction of contextual information from different scales, which is important for medium and small objects detection. To tackle these problems, we propose an image pyramid network based on dual attention mechanism (DAIPNet), which builds an image pyramid to enrich the spatial information while emphasizing multi-scale informative features based on dual attention mechanisms for one-stage object detection. Our framework utilizes a pre-trained backbone as standard detection network, where the designed image pyramid network (IPN) is used as auxiliary network to provide complementary information. Here, the dual attention mechanism is composed of the adaptive feature fusion module (AFFM) and the progressive attention fusion module (PAFM). AFFM is designed to automatically pay attention to the feature maps with different importance from the backbone and auxiliary network, while PAFM is utilized to adaptively learn the channel attentive information in the context transfer process. Furthermore, in the IPN, we build an image pyramid to extract scale-wise features from downsampled images of different scales, where the features are further fused at different states to enrich scale-wise information and learn more comprehensive feature representations. Experimental results are shown on MS COCO dataset. Our proposed detector with a 300 × 300 input achieves superior performance of 32.6% mAP on the MS COCO test-dev compared with state-of-the-art methods.