Heeseung Kwon

18 papers A* 3Journal 10Unranked 5
YearRankTypeTitle / Venue / Authors
2025 J jnl
ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context.
CoRR
Huiwon Jang, Sihyun Yu, Heeseung Kwon, Hojin Jeon, Younggyo Seo, Jinwoo Shin
2025 J jnl
Lightweight Structure-Aware Attention for Visual Understanding.
Int. J. Comput. Vis.
Heeseung Kwon, Francisco M. Castro, Manuel J. Marín-Jiménez, Nicolás Guil, Karteek Alahari
2023 J jnl
Effect of flow structures on natural ventilation performance in office model.
J. Vis.
Gun Young Yoon, Sang Joon Lee, Heeseung Kwon, Jeong Jae Kim
2022 J jnl
Lightweight Structure-Aware Attention for Visual Understanding.
CoRR
Heeseung Kwon, Francisco M. Castro, Manuel J. Marín-Jiménez, Nicolás Guil, Karteek Alahari
2021 — conf
IntegralAction: Pose-Driven Feature Integration for Robust Human Action Recognition in Videos.
CVPR Workshops
Gyeongsik Moon, Heeseung Kwon, Kyoung Mu Lee, Minsu Cho
2021 J jnl
Learning Self-Similarity in Space and Time as Generalized Motion for Action Recognition.
CoRR
Heeseung Kwon, Manjin Kim, Suha Kwak, Minsu Cho
2021 A* conf
Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition.
ICCV
Heeseung Kwon, Manjin Kim, Suha Kwak, Minsu Cho
2021 A* conf
Relational Embedding for Few-Shot Classification.
ICCV
Dahyun Kang, Heeseung Kwon, Juhong Min, Minsu Cho
2021 J jnl
Relational Embedding for Few-Shot Classification.
CoRR
Dahyun Kang, Heeseung Kwon, Juhong Min, Minsu Cho
2021 A* conf
Relational Self-Attention: What's Missing in Attention for Video Understanding.
NeurIPS
Manjin Kim, Heeseung Kwon, Chunyu Wang, Suha Kwak, Minsu Cho
2021 J jnl
Relational Self-Attention: What's Missing in Attention for Video Understanding.
CoRR
Manjin Kim, Heeseung Kwon, Chunyu Wang, Suha Kwak, Minsu Cho
2020 J jnl
IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos.
CoRR
Gyeongsik Moon, Heeseung Kwon, Kyoung Mu Lee, Minsu Cho
2020 — conf
MotionSqueeze: Neural Motion Feature Learning for Video Understanding.
ECCV (16)
Heeseung Kwon, Manjin Kim, Suha Kwak, Minsu Cho
2020 J jnl
MotionSqueeze: Neural Motion Feature Learning for Video Understanding.
CoRR
Heeseung Kwon, Manjin Kim, Suha Kwak, Minsu Cho
2019 — conf
Temporal U-Nets for Video Summarization with Scene and Action Recognition.
ICCV Workshops
Heeseung Kwon, Woohyun Shim, Minsu Cho
2018 J jnl
First Person Action Recognition via Two-stream ConvNet with Long-term Fusion Pooling.
Pattern Recognit. Lett.
Heeseung Kwon, Yeonho Kim, Jin S. Lee, Minsu Cho
2018 — conf
Video Understanding via Convolutional Temporal Pooling Network and Multimodal Feature Fusion.
CoVieW@MM
Heeseung Kwon, Suha Kwak, Minsu Cho
2014 — conf
Hidden UI: projection-based augmented reality for map navigation on multi-touch tabletop.
SUI
Seungjae Oh, Heeseung Kwon, Hyo-Jeong So