108 citations · 109 across the 8 of their papers we have counts for
9 papers
Decision-Aware Attention Propagation for Vision Transformer Explainability
Sehyeong Jo, Gangjae Jang, Haesol Park
Vision Transformers (ViTs) have become a dominant architecture in computer vision, yet their prediction process remains difficult to interpret because information is propagated thr…
GMAR: Gradient-Driven Multi-Head Attention Rollout for Vision Transformer Interpretability
Sehyeong Jo, Gangjae Jang, Haesol Park
The Vision Transformer (ViT) has made significant advancements in computer vision, utilizing self-attention mechanisms to achieve state-of-the-art performance across various tasks,…
V-NAW: Video-based Noise-aware Adaptive Weighting for Facial Expression Recognition
JunGyu Lee, Kunyoung Lee, Haesol Park +2
Facial Expression Recognition (FER) plays a crucial role in human affective analysis and has been widely applied in computer vision tasks such as human-computer interaction and psy…
MAIR++: Improving Multi-view Attention Inverse Rendering with Implicit Lighting Representation
JunYong Choi, SeokYeong Lee, Haesol Park +3
In this paper, we propose a scene-level inverse rendering framework that uses multi-view images to decompose the scene into geometry, SVBRDF, and 3D spatially-varying lighting. Whi…
IG-FIQA: Improving Face Image Quality Assessment through Intra-class Variance Guidance robust to Inaccurate Pseudo-Labels
Minsoo Kim, Gi Pyo Nam, Haksub Kim +2
In the realm of face image quality assesment (FIQA), method based on sample relative classification have shown impressive performance. However, the quality scores used as pseudo-la…
MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation
JunYong Choi, SeokYeong Lee, Haesol Park +3
We propose a scene-level inverse rendering framework that uses multi-view images to decompose the scene into geometry, a SVBRDF, and 3D spatially-varying lighting. Because multi-vi…
Joint Blind Motion Deblurring and Depth Estimation of Light Field
Dongwoo Lee, Haesol Park, In Kyu Park +1
Removing camera motion blur from a single light field is a challenging task since it is highly ill-posed inverse problem. The problem becomes even worse when blur kernel varies spa…
Look Wider to Match Image Patches with Convolutional Neural Networks
Haesol Park, Kyoung Mu Lee
When a human matches two images, the viewer has a natural tendency to view the wide area around the target pixel to obtain clues of right correspondence. However, designing a match…
Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence
Haesol Park, Kyoung Mu Lee
The conventional methods for estimating camera poses and scene structures from severely blurry or low resolution images often result in failure. The off-the-shelf deblurring or sup…