activity
20192022
most citedWide and Narrow: Video Prediction from Context and Motion

2 citations · 2 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CV2022

Boosting Video Object Segmentation based on Scale Inconsistency

Hengyi Wang, Changjae Oh

We present a refinement framework to boost the performance of pre-trained semi-supervised video object segmentation (VOS) models. Our work is based on scale inconsistency, which is…

cs.CV2022

Improving Generalization of Deep Networks for Estimating Physical Properties of Containers and Fillings

Hengyi Wang, Chaoran Zhu, Ziyin Ma +1

We present methods to estimate the physical properties of household containers and their fillings manipulated by humans. We use a lightweight, pre-trained convolutional neural netw…

cs.CV2022

A Wavelet-based Dual-stream Network for Underwater Image Enhancement

Ziyin Ma, Changjae Oh

We present a wavelet-based dual-stream network that addresses color cast and blurry details in underwater images. We handle these artifacts separately by decomposing an input image…

cs.CV20212 cited

Wide and Narrow: Video Prediction from Context and Motion

Jaehoon Cho, Jiyoung Lee, Changjae Oh +2

Video prediction, forecasting the future frames from a sequence of input frames, is a challenging task since the view changes are influenced by various factors, such as the global…

cs.RO2021

OHPL: One-shot Hand-eye Policy Learner

Changjae Oh, Yik Lung Pang, Andrea Cavallaro

The control of a robot for manipulation tasks generally relies on object detection and pose estimation. An attractive alternative is to learn control policies directly from raw inp…

cs.RO2021

Towards safe human-to-robot handovers of unknown containers

Yik Lung Pang, Alessio Xompero, Changjae Oh +1

Safe human-to-robot handovers of unknown objects require accurate estimation of hand poses and object properties, such as shape, trajectory, and weight. Accurately estimating these…