activity
20152023
most citedLook Wider to Match Image Patches with Convolutional Neural Networks

108 citations · 198 across the 17 of their papers we have counts for

collaborators
Showing 2019Show all

6 papers · 1 filter

cs.CV2019★ 13 cited

Fine-Grained Neural Architecture Search

Heewon Kim, Seokil Hong, Bohyung Han +2

We present an elegant framework of fine-grained neural architecture search (FGNAS), which allows to employ multiple heterogeneous operations within a single layer and can even gene…

cs.CV2019

PoseLifter: Absolute 3D human pose lifting network from a single noisy 2D human pose

Ju Yong Chang, Gyeongsik Moon, Kyoung Mu Lee

This study presents a new network (i.e., PoseLifter) that can lift a 2D human pose to an absolute 3D pose in a camera coordinate system. The proposed network estimates the absolute…

cs.CV2019

Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image

Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee

Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly prop…

cs.LG2019

Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation

Dongmin Park, Seokil Hong, Bohyung Han +1

Catastrophic forgetting is a critical challenge in training deep neural networks. Although continual learning has been investigated as a countermeasure to the problem, it often suf…

cs.LG2019

Learning to Forget for Meta-Learning

Sungyong Baik, Seokil Hong, Kyoung Mu Lee

Few-shot learning is a challenging problem where the goal is to achieve generalization from only few examples. Model-agnostic meta-learning (MAML) tackles the problem by formulatin…

cs.CV2019★ 4 cited

Multi-scale Aggregation R-CNN for 2D Multi-person Pose Estimation

Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee

Multi-person pose estimation from a 2D image is challenging because it requires not only keypoint localization but also human detection. In state-of-the-art top-down methods, multi…