Dr Changjae Oh

PhD

Lecturer in Multimedia

School of Electronic Engineering and Computer Science
Queen Mary University of London

c.oh@qmul.ac.uk

eecs.qmul.ac.uk/~coh/

Centre for Multimodal AI

Research
Publications
Grants

Research

Computer Vision, Image Processing, Vision-based robot perception

Interests

I am currently Lecturer at the School of Electronic Engineering and Computer Science (EECS), Queen Mary University of London (QMUL). Within QMUL, I'm member of Centre for Intelligent Sensing, Computer Vision Group, and Advanced Robotics at Queen Mary.

My current research interest is to investigate how to make embodied agents, such as physical or virtual robots, precisely perceive the environment and execute desirable actions. This research is related to several topics such as human-to-robot handover, 3D computer vision, robust machine learning, and vision-language models for robot perception and actions.

Publications

Publications of specific relevance to the Centre for Multimodal AI

2024

Incremental Object 6D Pose Estimation
Tian L, Sorrenti A, Pang YL, Bellitto G, Palazzo S, Spampinato C and Oh C
International Conference on Pattern Recognition.

QMRO

29-11-2024

Improving image de-raining using reference-guided transformers
Ye Z, Cho J and Oh C
IEEE International Conference on Image Processing 27 Oct 2024 - 30 Oct 2024.

DOI 10.1109/icip51287.2024.10648113

QMRO

27-09-2024

Sparse multi-view hand-object reconstruction for unseen environments
Pang YL, Oh C and Cavallaro A
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). vol. 00, 803-810.

DOI 10.1109/cvprw63382.2024.00085

QMRO

18-06-2024

Open-vocabulary object 6D pose estimation
Corsetti J, Boscaini D, Oh C, Cavallaro A and Poiesi F
IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024.

QMRO

17-06-2024

Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation
Kim J, Oh C, Do H, Kim S and Sohn K
IEEE/CVF International Conference on Computer Vision and Pattern Recognition 2024.

QMRO

17-06-2024

Learning by Erasing: Conditional Entropy Based Transferable Out-of-Distribution Detection
Xing M, Feng Z, Su Y and Oh C
AAAI Conference on Artificial Intelligence 2024.

DOI 10.1609/aaai.v38i6.28444

QMRO

24-03-2024

Test-time adaptation for 6D pose tracking
Tian L, Oh C and Cavallaro A
Pattern Recognition, Elsevier Bv, 110390-110390.

DOI 10.1016/j.patcog.2024.110390

QMRO

01-02-2024

Neuromorphic Tactile Sensing System for Textural Features Classification
Ali HAH, Abbass Y, Gianoglio C, Ibrahim A, Oh C and Valle M
Ieee Sensors Journal, Institute of Electrical and Electronics Engineers (Ieee) vol. 24 (10), 17193-17207.

DOI 10.1109/jsen.2024.3382369

QMRO

15-01-2024

Investigating Adversarial Policy Learning for Robust Agents in Automated Driving Highway Simulations
Pighetti A, Bellotti F, Oh C, Lazzaroni L, Forneris L, Fresta M and Berta R
Lecture Notes in Electrical Engineering. vol. 1110, 124-129.

DOI 10.1007/978-3-031-48121-5_18

QMRO

01-01-2024

2023

Implementation of a Stereo Vision System for a Mixed Reality Robot Teleoperation Simulator
Smiles AL, Chavanakunakorn KD, Omarali B, Oh C and Farkhatdinov I
In Towards Autonomous Robotic Systems, Springer Nature 494-502.

DOI 10.1007/978-3-031-43360-3_40

01-01-2023

2022

A WAVELET-BASED DUAL-STREAM NETWORK FOR UNDERWATER IMAGE ENHANCEMENT
Ma Z and Oh C
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). vol. 2022-May, 8662-8666.

DOI 10.1109/ICASSP43922.2022.9747781

QMRO

27-04-2022

Chapter 15 Visual adversarial attacks and defenses
Oh C, Xompero A and Cavallaro A
In Advanced Methods and Deep Learning in Computer Vision, Elsevier 511-543.

DOI 10.1016/b978-0-12-822109-9.00024-2

01-01-2022

IMPROVING GENERALIZATION OF DEEP NETWORKS FOR ESTIMATING PHYSICAL PROPERTIES OF CONTAINERS AND FILLINGS
Wang H, Zhu C, Ma Z and Oh C
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). vol. 2022-May, 9147-9151.

DOI 10.1109/ICASSP43922.2022.9747349

QMRO

01-01-2022

Boosting Video Object Segmentation Based on Scale Inconsistency
Wang H and Oh C
2022 IEEE International Conference on Multimedia and Expo (ICME). vol. 2022-July

DOI 10.1109/ICME52920.2022.9859938

QMRO

01-01-2022

CLUSTER-BASED 3D KEYPOINT DETECTION FOR CATEGORY-AGNOSTIC 6D POSE TRACKING
Tian L, Cavallaro A and Oh C
2022 IEEE International Conference on Image Processing (ICIP)., 3651-3655.

DOI 10.1109/ICIP46576.2022.9897746

QMRO

01-01-2022

2021

OHPL: One-shot Hand-eye Policy Learner
Oh C, Pang YL and Cavallaro A
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)., 3904-3910.

DOI 10.1109/IROS51168.2021.9636835

QMRO

16-12-2021

A Suite of Robotic Solutions for Nuclear Waste Decommissioning
Vitanov I, Farkhatdinov I, Denoun B, Palermo F, Otaran A, Brown J, Omarali B, Abrar T, Hansard M, Oh C, Poslad S, Liu C, Godaba H, Zhang K, Jamone L and Althoefer K
Robotics vol. 10 (4), 112-112.

DOI 10.3390/robotics10040112

QMRO

07-10-2021

Multi-modal robotic visual-tactile localisation and detection of surface cracks
Palermo F, Rincon-Ardila L, Oh C, Althoefer K, Poslad S, Venture G and Farkhatdinov I
2021 IEEE 17th International Conference on Automation Science and Engineering.

DOI 10.1109/CASE49439.2021.9551553

QMRO

05-10-2021

Semantically Adversarial Learnable Filters
Shahin Shamsabadi A, Oh C and Cavallaro A
Ieee Transactions On Image Processing, Institute of Electrical and Electronics Engineers

DOI 10.1109/TIP.2021.3112290

QMRO

20-09-2021

Towards safe human-to-robot handovers of unknown containers
Pang YL, Xompero A, Oh C and Cavallaro A
IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). vol. 00, 51-58.

DOI 10.1109/ro-man50785.2021.9515350

QMRO

12-08-2021

Wide and Narrow: Video Prediction from Context and Motion
Cho J, Lee J, Oh C, Song W and Sohn K
32nd British Machine Vision Conference, BMVC 2021.
01-01-2021

2020

An Alternative Laboratory Assessment Approach for Multimedia Modules in a Transnational Education (TNE) Programme during COVID-19
Alam AS, Lau E, Oh C and Chai KK
2020 Transnational Engineering Education using Technology (TREET). vol. 00, 1-4.

DOI 10.1109/treet50959.2020.9189756

31-07-2020

Edgefool: an Adversarial Image Enhancement Filter
Shamsabadi AS, Oh C and Cavallaro A
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). vol. 00, 1898-1902.

DOI 10.1109/icassp40776.2020.9054368

QMRO

08-05-2020

View-Action Representation Learning for Active First-Person Vision
Oh C and Cavallaro A
Ieee Transactions On Circuits and Systems For Video Technology, Institute of Electrical and Electronics Engineers, 1-1.

DOI 10.1109/tcsvt.2020.2987562

QMRO

13-04-2020

Simultaneous Deep Stereo Matching and Dehazing with Feature Attention
Song T, Kim Y, Oh C, Jang H, Ha N and Sohn K
International Journal of Computer Vision, Springer Verlag

DOI 10.1007/s11263-020-01294-2

QMRO

21-01-2020

2019

Learning action representations for self-supervised visual exploration
OH C and CAVALLARO A
IEEE Int. Conference on Robotics and Automation (ICRA).

DOI 10.1109/ICRA.2019.8794401

QMRO

12-08-2019

OCEAN: Object-centric arranging network for self-supervised visual representations learning
Oh C, Ham B, Kim H, Hilton A and Sohn K
Expert Systems With Applications, Elsevier vol. 125, 281-292.

DOI 10.1016/j.eswa.2019.01.073

01-07-2019

Deep network for simultaneous stereo matching and dehazing
Song T, Kim Y, Oh C and Sohn K
British Machine Vision Conference 2018, BMVC 2018.

QMRO

01-01-2019

2018

Multi-Task Self-Supervised Visual Representation Learning for Monocular Road Segmentation
Cho L, Kim Y, Jung H, Oh C, Youn J and Sohn K
2018 IEEE International Conference on Multimedia and Expo (ICME). vol. 00, 1-6.

DOI 10.1109/icme.2018.8486472

23-07-2018

2017

Personness estimation for real-time human detection on mobile devices
Kim K, Oh C and Sohn K
Expert Systems With Applications, Elsevier vol. 72, 130-138.

DOI 10.1016/j.eswa.2016.12.017

01-04-2017

Robust interactive image segmentation using structure-aware labeling
Oh C, Ham B and Sohn K
Expert Systems With Applications, Elsevier Bv vol. 79, 90-100.

DOI 10.1016/j.eswa.2017.02.031

QMRO

27-02-2017

Depth Prediction from a Single Image with Conditional Adversarial Networks
Jung H, Kim Y, Min D, Oh C and Sohn K
2017 IEEE International Conference on Image Processing (ICIP)., 1717-1721.

DOI 10.1109/icip.2017.8296575

01-01-2017

Point-Cut: Interactive Image Segmentation Using Point Supervision
Oh C, Ham B and Sohn K
Lecture Notes in Computer Science. vol. 10111, 229-244.

DOI 10.1007/978-3-319-54181-5_15

01-01-2017

2016

Structure Selective Depth Superresolution for RGB-D Cameras
Kim Y, Ham B, Oh C and Sohn K
Ieee Transactions On Image Processing, Institute of Electrical and Electronics Engineers (Ieee) vol. 25 (11), 5227-5238.

DOI 10.1109/tip.2016.2601262

QMRO

18-08-2016

Non-parametric human segmentation using support vector machine
Kim K, Oh C and Sohn K
Ieee Transactions On Consumer Electronics, Institute of Electrical and Electronics Engineers (Ieee) vol. 62 (2), 150-158.

DOI 10.1109/tce.2016.7514714

QMRO

29-07-2016

Depth Extraction from a Single Image Based on Block-Matching and Robust Regression
Jeong H, Oh C, Kim Y and Sohn K
Electronic Imaging. vol. 2016 (5), 1-6.

DOI 10.2352/issn.2470-1173.2016.5.sda-434

14-02-2016

Edge-Aware Image Smoothing Using Commute Time Distances
Kim Y, Oh C and Sohn K
2016 IEEE International Conference on Image Processing (ICIP)., 3304-3308.

DOI 10.1109/icip.2016.7532971

01-01-2016

Non-Parametric Human Segmentation Using Support Vector Machine
Kim K, Oh C and Sohn K
2016 IEEE International Conference on Consumer Electronics (ICCE)., 131-132.

DOI 10.1109/icce.2016.7430551

01-01-2016

2015

Depth Analogy: Data-Driven Approach for Single Image Depth Estimation Using Gradient Samples
Choi S, Min D, Ham B, Kim Y, Oh C and Sohn K
Ieee Transactions On Image Processing, Institute of Electrical and Electronics Engineers (Ieee) vol. 24 (12), 5953-5966.

DOI 10.1109/tip.2015.2495261

QMRO

27-10-2015

Segment-Based Free Space Estimation Using Plane Normal Vector in Disparity Space
Seo J, Oh C and Sohn K
2015 International Conference on Connected Vehicles and Expo (ICCVE)., 144-149.

DOI 10.1109/iccve.2015.6

01-10-2015

Structure-aware depth super-resolution using Gaussian mixture model
Kim S, Oh C, Kim Y and Sohn K
Three-Dimensional Image Processing, Measurement (3DIPM), and Applications 2015. vol. 9393

DOI 10.1117/12.2078795

17-03-2015

Visual Fatigue Relaxation for Stereoscopic Video via Nonlinear Disparity Remapping
Changjae Oh , Bumsub Ham , Sunghwan Choi and Kwanghoon Sohn
Ieee Transactions On Broadcasting, Institute of Electrical and Electronics Engineers (Ieee) vol. 61 (2), 142-153.

DOI 10.1109/tbc.2015.2402471

QMRO

02-03-2015

A Majorize-Minimize Approach for High-Quality Depth Upsampling
Kim Y, Choi S, Oh C and Sohn K
2015 IEEE International Conference on Image Processing (ICIP)., 392-396.

DOI 10.1109/icip.2015.7350827

01-01-2015

Sparse Edit Propagation for High Resolution Image Using Support Vector Machines
Oh C, Ryu S, Kim Y, Kim J, Park T and Sohn K
2015 IEEE International Conference on Image Processing (ICIP)., 4042-4046.

DOI 10.1109/icip.2015.7351565

01-01-2015

2013

Probability-Based Rendering for View Synthesis
Ham B, Min D, Oh C, N. M and Sohn K
Ieee Transactions On Image Processing, Institute of Electrical and Electronics Engineers (Ieee) vol. 23 (2), 870-884.

DOI 10.1109/tip.2013.2295716

20-12-2013

Disparity Search Range Estimation Based on Dense Stereo Matching
Li R, Ham B, Oh C and Sohn K
2013 IEEE 8th Conference on Industrial Electronics and Applications (ICIEA)., 753-759.

DOI 10.1109/iciea.2013.6566468

01-06-2013

2012

Hybrid Approach for Accurate Depth Acquisition with Structured Light and Stereo Camera
Choi S, Ham B, Oh C, Choo H-G, Kim J and Sohn K
IEEE international Symposium on Broadband Multimedia Systems and Broadcasting., 1-4.

DOI 10.1109/bmsb.2012.6264270

01-06-2012

Probabilistic Correspondence Matching using Random Walk with Restart
Oh C, Ham B and Sohn K
Procedings of the British Machine Vision Conference 2012., 37.1-37.10.

DOI 10.5244/c.26.37

01-01-2012

Grants

Grants of specific relevance to the Centre for Multimodal AI

Generative Models Based Robot Manipulation Environment for Human-to-Robot Handover
Changjae Oh
£19,751 Royal Society
01-10-2024 - 30-09-2025

Development of Multi-Modal Foundational Models and AI Accelerators for Zero-shot Intelligent Surveillance System
Changjae Oh
£384,699 KIAT Korea Institute for Advancement of Technology
01-08-2024 - 31-07-2027