Sungjun Hong
Papers
1
Total Citations
4
H-Index
1
About
Sungjun Hong is a researcher advancing the field of action recognition for robotic perception, with a focus on efficient temporal modeling in video understanding. His most notable contribution is the development of the **Discriminative Temporal Shift Module (D-TSM)**, a novel 2D CNN architecture that addresses the persistent challenge of capturing complex temporal dynamics in action recognition tasks. By refining the widely-used Temporal Shift Module (TSM), Hong’s D-TSM enhances discriminative power without sacrificing computational efficiency, making it highly relevant for real-time robotic applications. This work, published in 2023, has already garnered **4 citations**, signaling its early impact in the computer vision community. Hong’s research sits at the intersection of deep learning, video analysis, and robotics, aiming to equip machines with robust perceptual abilities. His contributions are particularly valuable for students and researchers seeking lightweight yet powerful models for temporal reasoning, bridging the gap between theoretical advances and practical deployment in autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1D-TSM: Discriminative Temporal Shift Module for Action Recognition4 citations · 2023