• ETRI Journal
• /
• v.42 no.2
• /
• pp.230-238
• /
• 2020

Human-object interaction (HOI) detection is a popular computer vision task that detects interactions between humans and objects. This task can be useful in many applications that require a deeper understanding of semantic scenes. Current HOI detection networks typically consist of a feature extractor followed by detection layers comprising small filters (eg, 1 × 1 or 3 × 3). Although small filters can capture local spatial features with a few parameters, they fail to capture larger context information relevant for recognizing interactions between humans and distant objects owing to their small receptive regions. Hence, we herein propose a three-stream HOI detection network that employs a context convolution module (CCM) in each stream branch. The CCM can capture larger contexts from input feature maps by adopting combinations of large separable convolution layers and residual-based convolution layers without increasing the number of parameters by using fewer large separable filters. We evaluate our HOI detection method using two benchmark datasets, V-COCO and HICO-DET, and demonstrate its state-of-the-art performance.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.2 no.1
• /
• pp.54-62
• /
• 1999

Vectorizing for input processing of map is the most time and cost consuming task, and the quality of vector data depends on that processing result. Therefore, it is an important task to develop a good vectorizing system in the GIS. Thinning algorithm is the most important technology for deciding the quality of vector data in the vectorizing system. In this paper, as a suitable algorithm for map vectorizing we considered several algorithms that preserve topological and geometric characteristics, and have no distortion of the contour line. As a results, we implemented WPTA4 and well known thinning algorithm, and compared WPTA4 execution results with the others.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.337-351
• /
• 2021

Automatically recognizing facial expressions in video sequences is a challenging task because there is little direct correlation between facial features and subjective emotions in video. To overcome the problem, a video facial expression recognition method using spatiotemporal recurrent neural network and feature fusion is proposed. Firstly, the video is preprocessed. Then, the double-layer cascade structure is used to detect a face in a video image. In addition, two deep convolutional neural networks are used to extract the time-domain and airspace facial features in the video. The spatial convolutional neural network is used to extract the spatial information features from each frame of the static expression images in the video. The temporal convolutional neural network is used to extract the dynamic information features from the optical flow information from multiple frames of expression images in the video. A multiplication fusion is performed with the spatiotemporal features learned by the two deep convolutional neural networks. Finally, the fused features are input to the support vector machine to realize the facial expression classification task. The experimental results on cNTERFACE, RML, and AFEW6.0 datasets show that the recognition rates obtained by the proposed method are as high as 88.67%, 70.32%, and 63.84%, respectively. Comparative experiments show that the proposed method obtains higher recognition accuracy than other recently reported methods.

• Genomics & Informatics
• /
• v.19 no.3
• /
• pp.22.1-22.5
• /
• 2021

Automatic document classification for highly interrelated classes is a demanding task that becomes more challenging when there is little labeled data for training. Such is the case of the coronavirus disease 2019 (COVID-19) clinical repository-a repository of classified and translated academic articles related to COVID-19 and relevant to the clinical practice-where a 3-way classification scheme is being applied to COVID-19 literature. During the 7th Biomedical Linked Annotation Hackathon (BLAH7) hackathon, we performed experiments to explore the use of named-entity-recognition (NER) to improve the classification. We processed the literature with OntoGene's Biomedical Entity Recogniser (OGER) and used the resulting identified Named Entities (NE) and their links to major biological databases as extra input features for the classifier. We compared the results with a baseline model without the OGER extracted features. In these proof-of-concept experiments, we observed a clear gain on COVID-19 literature classification. In particular, NE's origin was useful to classify document types and NE's type for clinical specialties. Due to the limitations of the small dataset, we can only conclude that our results suggests that NER would benefit this classification task. In order to accurately estimate this benefit, further experiments with a larger dataset would be needed.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2003.11a
• /
• pp.388-394
• /
• 2003

To handle the high level radioactive materials such a spent fuel, the master-slave manipulators (MSM) are widely used as a remote handling device in nuclear facilities such as the hot cell with sealed and shielded space. In this paper, the Digital Mockup which simulates the remote operation of the Advanced Conditioning Process(ACP) is developed. Also, the workspace and the motion of the slave manipulator, as well as, the remote operation task should be analyzed. The process equipment of ACP and Maintenance/Handling Device are drawn in 3D CAD models using IGRIP. Modeling device of manipulator is assigned with various mobile attributes such as a relative position, kinematics constraints, and a range of mobility, The 3D graphic simulator using the external input device of space ball displays the movement of manipulator. To connect the external input device to the graphic simulator, the interface program of external input device with 6 DOF is deigned using the Low Level Tele-operation Interface(LLTI). The experimental result shows that the developed simulation system gives much-improved human interface characteristics and shows satisfactory response characteristics in terms of synchronization speed. This should be useful for the development of work's education system in the virtual environment.

• Journal of Digital Contents Society
• /
• v.5 no.1
• /
• pp.22-27
• /
• 2004

To handle the high level radioactive materials such a spent fuel, the master-slave manipulaters (MSM) are wide1y used as a remote handling device in nuclear facilities such as the hot cell with sealed and shielded space. In this paper, the Digital Mockup which simulates the remote operation of the Advanced Conditioning Process(ACP) is developed. Also, the workspace and the motion of the slave manipulator, as well as, the remote operation task should be analyzed. The process equipment of ACP and Maintenance/Handling Device are drawn in 3D CAD model using IGRIP. Modeling device of manipulator is assigned with various mobile attributes such as a relative position, kinematics constraints, and a range of mobility. The 3D graphic simulator using the extermal input device of spare ball displays the movement of manipulator. To connect the exterral input device to the graphic simulator, the interface program of external input device with 6 DOF is deigned using the Low Level Tele-operation Interface(LLTI). The experimental result show that the developed simulation system gives much-improved human interface characteristics and shows satisfactory reponse characteristics in terms of synchronization speed. This should be useful for the development of work`s education system in the environment.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.5_6
• /
• pp.299-306
• /
• 2003

This paper formulates a problem of embedded real-time system re-engineering, and presents its solution approach. Embedded system re-engineering is defined as a development task of meeting performance requirements newly imposed on a system after its hardware and software have been fully implemented. The performance requirements nay include a real-time throughput and an input-to-output latency. The proposed solution approach is based on a bottleneck analysis and nonlinear optimization. The inputs to the approach include a system design specified with a process network and a set of task graphs, task allocation and scheduling, and a new real-time throughput requirement specified as a system's period constraint. The solution approach works in two steps. In the first step, it determines bottleneck precesses in the process network via estimation of process latencies. In the second step, it derives a system of constraints with performance scaling factors of processing elements being variables. It then solves the constraints for the performance staling factors with an objective of minimizing the total hardware cost of the resultant system. These scaling factors suggest the minimal cost hardware upgrade to meet the new performance requirement. Since this approach does not modify carefully designed software structures, it helps reduce the re-engineering cycle.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.5
• /
• pp.599-604
• /
• 2019

This study examined how the characteristics of smartphone affect the functional performance of smartphones. In particular, this study focused on an understanding of the correlation between smartphone functional factors and usage habits. Functionality is defined as 11 kinds of functional elements. The characteristics of the smartphones were defined as the hardware characteristics and the user habits characteristics. Eighty subjects were organized to collect actual data by the smartphone function. The actual time required to perform each function was measured and observed five times for each functional element. Regression analysis was performed using Minitab ver.14 by classifying the measured values of the functional elements as dependent variables, the hardware characteristics collected through the questionnaire, and the user's usage habits as 12 independent variables. Overall, it is difficult to conclude that demographic and hardware characteristics of smartphone users have a significant effect on the performance. On the other hand, the variables related to smartphone usage habits have had a great impact on the performance of smartphone tasks, and as a result, the task execution time has increased. In simple input variables or viewing variables, the effects on usability was relatively small, but in all active variables, the execution time increased 10% - 30% in all tasks except for phone calls, seeking phone numbers, and dictionary search. Thus far, if the smartphone user interface has been provided uniformly in a large and simple manner, users with various usage habits can be utilized even if the input method and task processing method are more complicated and various interface types are provided.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.2
• /
• pp.76-89
• /
• 2010

The performance of Distributed Heterogeneous Computing System depends on the algorithm which schedules input DAG graph. Among various scheduling algorithms, list scheduling algorithm provides superior performance with low complexity. List scheduling consists of task prioritizing phase and processor allocation phase, but most studies only focus on task prioritizing phase. In this paper, we propose LIP policy which has the same complexity with traditional allocation policies but has superior performance. The performance of LIP has been observed by applying them to task prioritizing phase of traditional list scheduling algorithms, HCPT, HEFT, GCA, and PETS. The results show that LIP has better performance than insertion-based policy and non-insertion-based policy, which are traditional processor allocation policies.

• The Journal of Korean Association of Computer Education
• /
• v.23 no.4
• /
• pp.61-68
• /
• 2020

The purpose of this study is to develop a debugging task to support process-centered assessment on software(SW) education and to develop a service site. Achievement criteria for programming in elementary and middle school SW curriculum consists of control structures such as repetition and condition, and elements such as variables and input/output. In order to apply the process-centered assessment presented by the Ministry of Education, it is necessary to present tasks that can be used in the actual classroom environment and to consider connection with achievement levels. Therefore, in this study, 12 tasks for elementary school and 15 tasks for middle school were developed as debugging tasks and their validity was verified. As a result of conducting Delphi verification for validity, it was found that the level and content of the debugging task are appropriate. In addition, as a result of verifying the usability of the debugging challenge site by applying a heuristic evaluation method, it was found that it is suitable for use in the real educational field.