Soungsill Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Soungsill Park has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Young Ho Chai
Chung-Ang University
3 shared publications - Adithya Balasubramanyam
CAVE Labs, PES University, Bengaluru, Karnataka, India
1 shared publication - Ashok Kumar Patil
Virtual Environments Lab, Graduate School of Advanced Imaging Science, Multimedia and Film, Chung-Ang University, Seoul 06974, Korea
1 shared publication - Bharatesh Chakravarthi
Arizona State University
1 shared publication - HyunBeom Kim
Chung-Ang University, Seoul, Republic of Korea
1 shared publication - Jae Yeong Ryu
Virtual Environments Lab, Graduate School of Advanced Imaging Science, Multimedia and Film, Chung-Ang University, Seoul 06974, Korea
1 shared publication
Latest Publications
- Open Access
- 12 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-2
MoPriC : Two Stage Approach for Text Guided Motion-Primitives Composition
- 12 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessMoPriC : Two Stage Approach for Text Guided Motion-Primitives Composition
- Open Access
- 12 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Partial Joint Correction of Abnormal Motion Data via Reward Function Design in Virtual Environments
- 12 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessPartial Joint Correction of Abnormal Motion Data via Reward Function Design in Virtual Environments
- Open Access
- 20 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 9645-9657
Angular Features-Based Human Action Recognition System for a Real Application With Subtle Unit Actions
Human action recognition (HAR) technology is receiving considerable attention in the field of human-computer interaction. We present a HAR system that works stably in real-world applications. In real-world applications, the HAR system needs to identify detailed actions for specific purposes, and the action data includes many variations. Accordingly, we conducted three experiments. First, we tested our recognition system’s performance on the UTD-MHAD dataset. We compared our system’s accuracy with results from previous research and confirmed that our system achieves an average performance among recognition systems. Furthermore, we hypothesized the use of a HAR system to detect burglary. In the second experiment, we compared the existing benchmark data with our crime detection dataset. We recognized the test scenarios’ data by using the recognition system trained by each dataset. The recognition system trained by our dataset achieved higher accuracy than the past benchmark dataset. The results show that the training data should contain detailed actions for a real application. In the third experiment, we tried to find the motion data type that stably recognizes action regardless of data variation. In a real application, the action data are changed by people. Thus, we introduced variations in the action data using the cross-subject protocol and moving area setting. We trained the recognition system using each position and angle data. In addition, we compared the accuracy of each system. We found that the angle format results in better accuracy because the angle data are beneficial for converting the action variation into a consistent pattern.
- 20 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 9645-9657
Open AccessAngular Features-Based Human Action Recognition System for a Real Application With Subtle Unit Actions
Human action recognition (HAR) technology is receiving considerable attention in the field of human-computer interaction. We present a HAR system that works stably in real-world applications. In real-world applications, the HAR system needs to identify detailed actions for specific purposes, and the action data includes many variations. Accordingly, we conducted three experiments. First, we tested our recognition system’s performance on the UTD-MHAD dataset. We compared our system’s accuracy with results from previous research and confirmed that our system achieves an average performance among recognition systems. Furthermore, we hypothesized the use of a HAR system to detect burglary. In the second experiment, we compared the existing benchmark data with our crime detection dataset. We recognized the test scenarios’ data by using the recognition system trained by each dataset. The recognition system trained by our dataset achieved higher accuracy than the past benchmark dataset. The results show that the training data should contain detailed actions for a real application. In the third experiment, we tried to find the motion data type that stably recognizes action regardless of data variation. In a real application, the action data are changed by people. Thus, we introduced variations in the action data using the cross-subject protocol and moving area setting. We trained the recognition system using each position and angle data. In addition, we compared the accuracy of each system. We found that the angle format results in better accuracy because the angle data are beneficial for converting the action variation into a consistent pattern.