Seonghoon Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Seonghoon Park has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Hojung Cha
Yonsei University, Seoul, Republic of Korea
7 shared publications - Jeho Lee
Yonsei University, Seoul, Republic of Korea
6 shared publications - Chanyoung Jung
Yonsei University, Seoul, Republic of Korea
3 shared publications - Gunjoong Kim
Yonsei University, Seoul, Republic of Korea
3 shared publications - Jiwon Kim
Uppsala University
3 shared publications - Hyungchol Jun
Yonsei University, Seoul, Republic of Korea
2 shared publications
Latest Publications
- Open Access
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1812-1828
viNPU: Optimizing Vision Transformer Inference on Mobile NPUs
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1812-1828
Open AccessviNPU: Optimizing Vision Transformer Inference on Mobile NPUs
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 878-893
EOS: Energy-Optimized Super-Resolution on Mobile Devices for Live 360-Degree Videos
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 878-893
Open AccessEOS: Energy-Optimized Super-Resolution on Mobile Devices for Live 360-Degree Videos
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1106-1120
Vega: Fully Immersive Mobile Volumetric Video Streaming with 3D Gaussian Splatting
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1106-1120
Open AccessVega: Fully Immersive Mobile Volumetric Video Streaming with 3D Gaussian Splatting
- Open Access
- 9 October 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 24 (6) , 1-26
Duration-Aware Sound Event Detection on Ultra-Low-Power Sensor Devices
Sound event detection (SED) based on on-device machine learning (ML) presents considerable energy challenges for ultra-low-power sensor devices. In this article, we propose DASH, a duration-aware SED system designed for energy-constrained sensor devices in domestic environments. As repeated inferences for continuous sound events lead to unnecessary energy consumption, DASH aims to minimize unnecessary inferences by predicting the duration of sound events. However, the variability of sound event durations across different environments and scenarios poses a major challenge in developing a responsive yet energy-efficient duration-aware SED system. To address this, DASH introduces three key solutions: (1) N-probability distribution-based event duration prediction, which identifies checkpoints where new inferences are likely needed; (2) Affinity-guided event classification, which performs low-energy affinity matching at checkpoints to determine whether ML inference is necessary; and (3) Interrupt blocking-enabling cycle-based device state control, which periodically checks for event presence with minimal energy consumption at non-checkpoint times. We implemented DASH on MSP430-based sensor devices deployed in real home environments. Experimental results demonstrate that DASH reduced energy consumption by approximately 97–98% compared to evaluation baselines, with only a 4.7% error rate.
- 9 October 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 24 (6) , 1-26
Open AccessDuration-Aware Sound Event Detection on Ultra-Low-Power Sensor Devices
Sound event detection (SED) based on on-device machine learning (ML) presents considerable energy challenges for ultra-low-power sensor devices. In this article, we propose DASH, a duration-aware SED system designed for energy-constrained sensor devices in domestic environments. As repeated inferences for continuous sound events lead to unnecessary energy consumption, DASH aims to minimize unnecessary inferences by predicting the duration of sound events. However, the variability of sound event durations across different environments and scenarios poses a major challenge in developing a responsive yet energy-efficient duration-aware SED system. To address this, DASH introduces three key solutions: (1) N-probability distribution-based event duration prediction, which identifies checkpoints where new inferences are likely needed; (2) Affinity-guided event classification, which performs low-energy affinity matching at checkpoints to determine whether ML inference is necessary; and (3) Interrupt blocking-enabling cycle-based device state control, which periodically checks for event presence with minimal energy consumption at non-checkpoint times. We implemented DASH on MSP430-based sensor devices deployed in real home environments. Experimental results demonstrate that DASH reduced energy consumption by approximately 97–98% compared to evaluation baselines, with only a 4.7% error rate.
- Open Access
- 26 September 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 24 (5s) , 1-24
Ember: Task Wakeup Sequence–Based Energy Optimization for Mobile Web Browsing
Existing Android systems exhibit energy inefficiency during mobile web browsing due to the lack of awareness of application-level context. Inferring such context from system-level data alone is challenging, but one promising opportunity is using the sequence of task wakeup events, where one task activates another. These sequences show correlation with the type of webpage being used. In this paper, we present Ember, a lightweight and responsive power management system for mobile web browsing using only task wakeup sequences. Ember introduces a neural network–based approach to predict optimal CPU clamping values by addressing three key challenges: (1) embedding task names, given as natural-language strings, into meaningful vectors using a Word2Vec-based embedding scheme tailored for task wakeup sequences; (2) minimizing inference overhead with a touch-driven hierarchical inference method that combines lightweight logistic regression with high-accuracy neural networks to balance responsiveness and efficiency; and (3) adapting to within-page interaction dynamics through an interaction-adaptive clamping mechanism that adjusts constraints across different user interaction phases. Implemented on commercial Android smartphones, Ember reduced power consumption by 6.2%–31.2% across a wide range of webpages while maintaining user-perceived quality of experience (QoE).
- 26 September 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 24 (5s) , 1-24
Open AccessEmber: Task Wakeup Sequence–Based Energy Optimization for Mobile Web Browsing
Existing Android systems exhibit energy inefficiency during mobile web browsing due to the lack of awareness of application-level context. Inferring such context from system-level data alone is challenging, but one promising opportunity is using the sequence of task wakeup events, where one task activates another. These sequences show correlation with the type of webpage being used. In this paper, we present Ember, a lightweight and responsive power management system for mobile web browsing using only task wakeup sequences. Ember introduces a neural network–based approach to predict optimal CPU clamping values by addressing three key challenges: (1) embedding task names, given as natural-language strings, into meaningful vectors using a Word2Vec-based embedding scheme tailored for task wakeup sequences; (2) minimizing inference overhead with a touch-driven hierarchical inference method that combines lightweight logistic regression with high-accuracy neural networks to balance responsiveness and efficiency; and (3) adapting to within-page interaction dynamics through an interaction-adaptive clamping mechanism that adjusts constraints across different user interaction phases. Implemented on commercial Android smartphones, Ember reduced power consumption by 6.2%–31.2% across a wide range of webpages while maintaining user-perceived quality of experience (QoE).
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 249-262
ARIA: Optimizing Vision Foundation Model Inference on Heterogeneous Mobile Processors for Augmented Reality
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 249-262
Open AccessARIA: Optimizing Vision Foundation Model Inference on Heterogeneous Mobile Processors for Augmented Reality
- Open Access
- 18 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 261-274
OmniLive: Super-Resolution Enhanced 360° Video Live Streaming for Mobile Devices
The live streaming of omnidirectional video (ODV) on mobile devices demands considerable network resources; thus, current mobile networks are incapable of providing users with high-quality ODV equivalent to conventional flat videos. We observe that mobile devices, in fact, underutilize graphics processing units (GPUs) while processing ODVs; hence, we envisage an opportunity exists in exploiting video super-resolution (VSR) for improved ODV quality. However, the device-specific discrepancy in GPU capability and dynamic behavior of GPU frequency in mobile devices create a challenge in providing VSR-enhanced ODV streaming. In this paper, we propose OmniLive, an on-device VSR system for mobile ODV live streaming. OmniLive addresses the dynamicity of GPU capability with an anytime inference-based VSR technique called Omni SR. For Omni SR, we design a VSR deep neural network (DNN) model with multiple exits and an inference scheduler that decides on the exit of the model at runtime. OmniLive also solves the performance heterogeneity of mobile GPUs using the Omni neural architecture search (NAS) scheme. Omni NAS finds an appropriate DNN model for each mobile device with Omni SR-specific neural architecture search techniques. We implemented OmniLive as a fully functioning system encompassing a streaming server and Android application. The experiment results show that our anytime VSR model provides four times upscaled videos while saving up to 57.15% of inference time compared with the previous super-resolution model showing the lowest inference time on mobile devices. Moreover, OmniLive can maintain 30 frames per second while fully utilizing GPUs on various mobile devices.
- 18 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 261-274
Open AccessOmniLive: Super-Resolution Enhanced 360° Video Live Streaming for Mobile Devices
The live streaming of omnidirectional video (ODV) on mobile devices demands considerable network resources; thus, current mobile networks are incapable of providing users with high-quality ODV equivalent to conventional flat videos. We observe that mobile devices, in fact, underutilize graphics processing units (GPUs) while processing ODVs; hence, we envisage an opportunity exists in exploiting video super-resolution (VSR) for improved ODV quality. However, the device-specific discrepancy in GPU capability and dynamic behavior of GPU frequency in mobile devices create a challenge in providing VSR-enhanced ODV streaming. In this paper, we propose OmniLive, an on-device VSR system for mobile ODV live streaming. OmniLive addresses the dynamicity of GPU capability with an anytime inference-based VSR technique called Omni SR. For Omni SR, we design a VSR deep neural network (DNN) model with multiple exits and an inference scheduler that decides on the exit of the model at runtime. OmniLive also solves the performance heterogeneity of mobile GPUs using the Omni neural architecture search (NAS) scheme. Omni NAS finds an appropriate DNN model for each mobile device with Omni SR-specific neural architecture search techniques. We implemented OmniLive as a fully functioning system encompassing a streaming server and Android application. The experiment results show that our anytime VSR model provides four times upscaled videos while saving up to 57.15% of inference time compared with the previous super-resolution model showing the lowest inference time on mobile devices. Moreover, OmniLive can maintain 30 frames per second while fully utilizing GPUs on various mobile devices.
- 15 March 2016
- Published by Morressier GmbH
DOWNREGULATION OF TUMOR NECROSIS FACTOR AND INTERLEUKIN-1 BY ELLAGIC ACID
- 15 March 2016
- Published by Morressier GmbH
DOWNREGULATION OF TUMOR NECROSIS FACTOR AND INTERLEUKIN-1 BY ELLAGIC ACID