• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.1
• /
• pp.50-58
• /
• 2007

In this paper, we propose a query-based visual attention algorithm for effective object finding of a vision-based mobile robot. This algorithm is developed by extending conventional bottom-up visual attention algorithms. In our proposed algorithm various conspicuity maps are merged to make a saliency map, where weighting values are determined by query-dependent object properties. The saliency map is then used to find possible attentive location of queried object. To show the validities of our proposed algorithm, several objects are employed to compare performances of our proposed algorithm with those of conventional bottom-up approaches. Here, as one of exemplar query-dependent object property, color property is used.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.185-198
• /
• 2021

With the development of Internet technology, because traditional recommendation algorithms cannot learn the in-depth characteristics of users or items, this paper proposed a recommendation algorithm based on the AMITI(attention mechanism and improved TF-IDF) to solve this problem. By introducing the two-layer attention mechanism into the CNN, the feature extraction ability of the CNN is improved, and different preference weights are assigned to item features, recommendations that are more in line with user preferences are achieved. When recommending items to target users, the scoring data and item type data are combined with TF-IDF to complete the grouping of the recommendation results. In this paper, the experimental results on the MovieLens-1M data set show that the AMITI algorithm improves the accuracy of recommendation to a certain extent and enhances the orderliness and selectivity of presentation methods.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.870-878
• /
• 2019

In this paper, we propose an Attention-based BLSTM for predicting the video compression standard of a video. Recently, in NLP, many researches have been studied to predict the next word of sentences, classify and translate sentences by their semantics using the structure of RNN, and they were commercialized as chatbots, AI speakers and translator applications, etc. LSTM is designed to solve the gradient vanishing problem in RNN, and is used in NLP. The proposed algorithm makes video compression standard prediction possible by applying BLSTM and Attention algorithm which focuses on the most important word in a sentence to a bitstream of a video, not an sentence of a natural language.

• Journal of Information Technology Services
• /
• v.21 no.2
• /
• pp.85-95
• /
• 2022

This study analyzed the translation error factors of machine translation services such as Naver Papago and Google Translate through Self-Attention path visualization. Self-Attention is a key method of the Transformer and BERT NLP models and recently widely used in machine translation. We propose a method to explain translation error factors of machine translation algorithms by comparison the Self-Attention paths between ST(source text) and ST'(transformed ST) of which meaning is not changed, but the translation output is more accurate. Through this method, it is possible to gain explainability to analyze a machine translation algorithm's inside process, which is invisible like a black box. In our experiment, it was possible to explore the factors that caused translation errors by analyzing the difference in key word's attention path. The study used the XLM-RoBERTa multilingual NLP model provided by exBERT for Self-Attention visualization, and it was applied to two examples of Korean-Chinese and Korean-English translations.

• Journal of Korean Library and Information Science Society
• /
• v.53 no.2
• /
• pp.95-115
• /
• 2022

The purpose of this study is to transform the sub-categorization terms of the National Science and Technology Standards Classification System into technical keywords by applying a machine learning algorithm. For this purpose, AttentionMeSH was used as a learning algorithm suitable for topic word recommendation. For source data, four-year research status files from 2017 to 2020, refined by the Korea Institute of Science and Technology Planning and Evaluation, were used. For learning, four attributes that well express the research content were used: task name, research goal, research abstract, and expected effect. As a result, it was confirmed that the result of MiF 0.6377 was derived when the threshold was 0.5. In order to utilize machine learning in actual work in the future and to secure technical keywords, it is expected that it will be necessary to establish a term management system and secure data of various attributes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2131-2153
• /
• 2022

To achieve accurate detection of tuberculosis (TB) areas in chest radiographs, we design a chest X-ray TB area detection algorithm. The algorithm consists of two stages: the chest X-ray TB classification network (CXTCNet) and the chest X-ray TB area detection network (CXTDNet). CXTCNet is used to judge the presence or absence of TB areas in chest X-ray images, thereby excluding the influence of other lung diseases on the detection of TB areas. It can reduce false positives in the detection network and improve the accuracy of detection results. In CXTCNet, we propose a channel attention mechanism (CAM) module and combine it with DenseNet. This module enables the network to learn more spatial and channel features information about chest X-ray images, thereby improving network performance. CXTDNet is a design based on a sparse object detection algorithm (Sparse R-CNN). A group of fixed learnable proposal boxes and learnable proposal features are using for classification and location. The predictions of the algorithm are output directly without non-maximal suppression post-processing. Furthermore, we use CLAHE to reduce image noise and improve image quality for data preprocessing. Experiments on dataset TBX11K show that the accuracy of the proposed CXTCNet is up to 99.10%, which is better than most current TB classification algorithms. Finally, our proposed chest X-ray TB detection algorithm could achieve AP of 45.35% and AP50 of 74.20%. We also establish a chest X-ray TB dataset with 304 sheets. And experiments on this dataset showed that the accuracy of the diagnosis was comparable to that of radiologists. We hope that our proposed algorithm and established dataset will advance the field of TB detection.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4080-4097
• /
• 2020

In recent years, convolutional neural network (CNN) has become the primary method for face detection. But its shortcomings are obvious, such as expensive calculation, heavy model, etc. This makes CNN difficult to use on the mobile devices which have limited computing and storage capabilities. Therefore, the design of lightweight CNN for face detection is becoming more and more important with the popularity of smartphones and mobile Internet. Based on the CPU real-time face detector FaceBoxes, we propose a multi-task lightweight face detector, which has low computing cost and higher detection precision. First, to improve the detection capability, the squeeze and excitation modules are used to extract attention between channels. Then, the textual and semantic information are extracted by shallow networks and deep networks respectively to get rich features. Finally, the landmark detection module is used to improve the detection performance for small faces and provide landmark data for face alignment. Experiments on AFW, FDDB, PASCAL, and WIDER FACE datasets show that our algorithm has achieved significant improvement in the mean average precision. Especially, on the WIDER FACE hard validation set, our algorithm outperforms the mean average precision of FaceBoxes by 7.2%. For VGA-resolution images, the running speed of our algorithm can reach 23FPS on a CPU device.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.306-308
• /
• 2006

We propose an attention based object recognition system, to recognize object fast and robustly. For this we calculate visual stimulus degrees and make saliency maps. Through this map we find a strongly attentive part of image by stimulus degrees, where local features are extracted to recognize objects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.8
• /
• pp.1843-1859
• /
• 2013

The continuous increase of the spatial resolution of remote sensing images brings great challenge to image analysis and processing. Traditional prior knowledge-based region detection and target recognition algorithms for processing high resolution remote sensing images generally employ a global searching solution, which results in prohibitive computational complexity. In this paper, a more efficient region of interest (ROI) detection algorithm based on visual attention and threshold segmentation (VA-TS) is proposed, wherein a visual attention mechanism is used to eliminate image segmentation and feature detection to the entire image. The input image is subsampled to decrease the amount of data and the discrete moment transform (DMT) feature is extracted to provide a finer description of the edges. The feature maps are combined with weights according to the amount of the "strong points" and the "salient points". A threshold segmentation strategy is employed to obtain more accurate region of interest shape information with the very low computational complexity. Experimental statistics have shown that the proposed algorithm is computational efficient and provide more visually accurate detection results. The calculation time is only about 0.7% of the traditional Itti's model.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.2
• /
• pp.131-139
• /
• 2008

This paper presents a new saliency map which is constructed by providing dynamic weights on individual features in an input image to search ROI(Region Of Interest) or FOA(Focus Of Attention). To construct a saliency map on there is no a priori information, three feature-maps are constructed first which emphasize orientation, color, and intensity of individual pixels, respectively. From feature-maps, conspicuity maps are generated by using the It's algorithm and their information quantities are measured in terms of entropy. Final saliency map is constructed by summing the conspicuity maps weighted with their individual entropies. The prominency of the proposed algorithm has been proved by showing that the ROIs detected by the proposed algorithm in ten different images are similar with those selected by one-hundred person's naked eyes.