Changjae Oh

I am a Lecturer (Assistant Professor) at the School of Electronic Engineering and Computer Science (EECS), Queen Mary University of London (QMUL) . I was a postdoctoral researcher at QMUL (May 2018-Aug 2019). I obtained the PhD degree in Electrical and Electronic Engineering from Yonsei University, South Korea.

Email  /  GitHub  /  Google Scholar  /  CV

Prospective Students

I'm looking for prospective students who are interested in computer vision or vision-based machine perception for robot manipulation. Please feel free to contact me. You can find information on the QMUL EECS PhD opportunities here, with some scholarships such as:

[C25] Cluster-based 3D Keypoint Detection for Category-agnostic 6D Pose Tracking

[C24] Boosting Video Object Segmentation based on Scale Inconsistency

[W01] Improving Generalization of Deep Networks for Estimating Physical Properties of Containers and Fillings

[C23] A Wavelet-based Dual-stream Network for Underwater Image Enhancement

[C22] Wide and Narrow: Video Prediction from Context and Motion

[J11] Semantically Adversarial Learnable Filters

[C21] OHPL: One-shot Hand-eye Policy Learner

[C20] Towards safe human-to-robot handovers of unknown containers

[C19] Multi-modal robotic visual-tactile localisation and detection of surface cracks

[J10] View-Action Representation Learning for Active First-Person Vision

[J9] Simultaneous Deep Stereo Matching and Dehazing with Feature Attention

[C18] Edgefool: An Adversarial Image Enhancement Filter

[J8] OCEAN: Object-Centric Arranging Network for Self-supervised Visual Representations Learning

[C17] Learning Action Representations for Self-supervised Visual Exploration

[C16] Deep Network for Simultaneous Stereo Matching and Dehazing

[C15] Multi-task Self-supervised Visual Representation Learning for Monocular Road Segmentation

[C14] Depth Prediction from a Single Image with Conditional Adversarial Networks

[J7] Robust Interactive Image Segmentation using Structure-aware Labeling

[J6] Structure selective depth super-resolution for RGB-D cameras

[J5] Non-Parametric Human Segmentation Using Support Vector Machine

[J4] Personness estimation for real-time human detection on mobile devices

[C13] Point-cut: Interactive Image Segmentation using Point Supervision

[C12] Edge-Aware Image Smoothing using Commute Time Distances

[C11] Depth Extraction from a Single Image Based on Block-Matching and Robust Regression

[C10] Non-Parametric Human Segmentation Using Support Vector Machine

[J3] Depth Analogy: Data-driven Approach for Single Image Depth Estimation using Gradient Samples

[C9] Segment-based Free Space Estimation using Plane Normal Vector in Disparity Space

[C8] Sparse Edit Propagation for High Resolution Image using Support Vector Machines

[C7] A Majorize-minimize Approach for High-Quality Depth Upsampling

[C6] Structure-Aware Depth Super-Resolution Using Gaussian Mixture Model

[J2] Visual Fatigue Relaxation for Stereoscopic Video via Nonlinear Disparity Remapping

[J1] Probability-Based Rendering for View Synthesis

[C5] Visual Fatigue Prediction and Its Visualization

[C4] Disparity Search Range Estimation Based on Dense Stereo Matching

[C3] Probabilistic Correspondence Matching using Random Walk with Restart

[C2] Hybrid Approach for Accurate Depth Acquisition with Structured Light and Stereo Camera

[C1] Joint Radiometric Calibration and Multi-view Matching with Ground Control Points

[Sep. 2019 - Present] CORSMAL: Collaborative Object Recognition, Shared Manipulation and Learning

[May. 2018 - Aug. 2019] Nuclear Centre for Nuclear Robotics (NCNR)

[2020/2021] Computer Vision

[2020/2021] Image and Video Processing

[2020] Interactive Media Design and Production

[2019] Advanced Transform Methods

Design and source code from Jon Barron's website