Dr Changjae Oh
Lecturer
School of Electronic Engineering and Computer Science
Queen Mary University of London
Queen Mary University of London
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 AI2025
An Embedded System Architecture for Robust Deep Learning-based Traffic Light DetectionLazzaroni L Bellotti F Pighetti A Forneris L Fresta M Oh C Ballout H Pantawane S et al.
IEEE Sensors Journal, Institute of Electrical and Electronics Engineers
05-11-2025
Learning Human-To-Robot Handovers through 3D Scene ReconstructionWu Y Pang YL Cavallaro A Oh C
IEEE International Conference on Robot and Human Interactive Communication (RO-MAN).
03-11-2025
Robust Photo-Realistic Hand Gesture Generation: from Single View to Multiple ViewFu Q Chen X Asad M Yuan S Oh C Slabaugh G
Proceedings of the 33rd ACM International Conference on Multimedia., 10662-10670.
27-10-2025
High-resolution open-vocabulary object 6D pose estimationCorsetti J Boscaini D Giuliari F Oh C Cavallaro A Poiesi F
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers
23-10-2025
RAFT: Regularized Adversarial Fine-Tuning to Enhance Deep Reinforcement Learning for Self-ParkingPighetti A Bellotti F Berta R Cavallaro A Lazzaroni L Oh C
IEEE Sensors Letters, Institute of Electrical and Electronics Engineers
30-09-2025
Robust Photo-Realistic Hand Gesture Generation: from Single View to Multiple ViewFu Q Chen X Asad M Yuan S Oh C Slabaugh G
In Arxiv
05-08-2025
3D Semantic Image Synthesis with Geometric and Semantic ConsistencyKim J Oh C Do H Choi S Kwanghoon S
Expert Systems With Applications, Elsevier
02-07-2025
Stereo Hand-Object Reconstruction for Human-to-Robot HandoverPang YL Xompero A Oh C Cavallaro A
IEEE Robotics and Automation Letters, Institute of Electrical and Electronics Engineers
21-04-2025
Exploring Decision Transformer for Highway Automated DrivingForneris L Bellotti F Berta R Lazzaroni L Oh C
International Conference on Applications in Electronics Pervading Industry, Environment and Society 19 Sep 2024 - 20 Sep 2024.
08-03-2025
HanDrawer: Leveraging Spatial Information to Render Realistic Hands Using a Conditional Diffusion Model in Single StageFu Q Chen X Asad M Yuan S Oh C Slabaugh G
In Arxiv
03-03-2025
Spatio-temporal graph-based self-labeling for video anomaly detectionXing M Feng Z Su Y Zhang Y Oh C Gribova V Filaretoy VF Huang D
Neurocomputing, Elsevier, 129576-129576.
04-02-2025
Adaptive Multi-modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle LossFu Q Yang X Asad M Oh C Yuan S Slabaugh G
In Computer Vision – Eccv 2024 Workshops, Springer Nature 68-84.
01-01-2025
2024
Incremental Object 6D Pose EstimationTian L Sorrenti A Pang YL Bellitto G Palazzo S Spampinato C Oh C
International Conference on Pattern Recognition.
29-11-2024
Improving image de-raining using reference-guided transformersYe Z Cho J Oh C
IEEE International Conference on Image Processing 27 Oct 2024 - 30 Oct 2024.
27-09-2024
Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle LossFu Q Yang X Asad M Oh C Yuan S Slabaugh G
In Arxiv
13-09-2024
Coming Out of the Dark: Human Pose Estimation in Low-light ConditionsSu Y Chen D Xing M Oh C Liu X Li J
Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence., 1882-1890.
01-08-2024
Sparse multi-view hand-object reconstruction for unseen environmentsPang YL Oh C Cavallaro A
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). vol. 00, 803-810.
18-06-2024
Open-vocabulary object 6D pose estimationCorsetti J Boscaini D Oh C Cavallaro A Poiesi F
IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024.
17-06-2024
Diffusion-driven GAN Inversion for Multi-Modal Face Image GenerationKim J Oh C Do H Kim S Sohn K
IEEE/CVF International Conference on Computer Vision and Pattern Recognition 2024.
17-06-2024
Learning by Erasing: Conditional Entropy Based Transferable Out-of-Distribution DetectionXing M Feng Z Su Y Oh C
AAAI Conference on Artificial Intelligence 2024.
24-03-2024
Test-time adaptation for 6D pose trackingTian L Oh C Cavallaro A
Pattern Recognition, Elsevier Bv, 110390-110390.
01-02-2024
Neuromorphic Tactile Sensing System for Textural Features ClassificationAli HAH Abbass Y Gianoglio C Ibrahim A Oh C Valle M
IEEE Sensors Journal, Institute of Electrical and Electronics Engineers (IEEE) vol. 24 (10), 17193-17207.
15-01-2024
2023
Robotic surface exploration with vision and tactile sensing for cracks detection and characterisationPalermo F Omarali B Oh C Althoefer K Farkhatdinov I
In Arxiv
13-07-2023
Implementation of a Stereo Vision System for a Mixed Reality Robot Teleoperation SimulatorSmiles AL Chavanakunakorn KD Omarali B Oh C Farkhatdinov I
In Towards Autonomous Robotic Systems, Springer Nature 494-502.
01-01-2023
2022
A WAVELET-BASED DUAL-STREAM NETWORK FOR UNDERWATER IMAGE ENHANCEMENTMa Z Oh C
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). vol. 2022-May, 8662-8666.
27-04-2022
Chapter 15 Visual adversarial attacks and defensesOh C Xompero A Cavallaro A
In Advanced Methods and Deep Learning in Computer Vision, Elsevier 511-543.
01-01-2022
IMPROVING GENERALIZATION OF DEEP NETWORKS FOR ESTIMATING PHYSICAL PROPERTIES OF CONTAINERS AND FILLINGSWang H Zhu C Ma Z Oh C
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). vol. 2022-May, 9147-9151.
01-01-2022
Boosting Video Object Segmentation Based on Scale InconsistencyWang H Oh C
2022 IEEE International Conference on Multimedia and Expo (ICME). vol. 2022-July
01-01-2022
CLUSTER-BASED 3D KEYPOINT DETECTION FOR CATEGORY-AGNOSTIC 6D POSE TRACKINGTian L Cavallaro A Oh C
2022 IEEE International Conference on Image Processing (ICIP)., 3651-3655.
01-01-2022
2021
OHPL: One-shot Hand-eye Policy LearnerOh C Pang YL Cavallaro A
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)., 3904-3910.
16-12-2021
A Suite of Robotic Solutions for Nuclear Waste DecommissioningVitanov I Farkhatdinov I Denoun B Palermo F Otaran A Brown J Omarali B Abrar T et al.
Robotics vol. 10 (4), 112-112.
07-10-2021
Multi-modal robotic visual-tactile localisation and detection of surface cracksPalermo F Rincon-Ardila L Oh C Althoefer K Poslad S Venture G Farkhatdinov I
2021 IEEE 17th International Conference on Automation Science and Engineering.
05-10-2021
Semantically Adversarial Learnable FiltersShahin Shamsabadi A Oh C Cavallaro A
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers
20-09-2021
Towards safe human-to-robot handovers of unknown containersPang YL Xompero A Oh C Cavallaro A
IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). vol. 00, 51-58.
12-08-2021
OHPL: One-shot Hand-eye Policy LearnerOh C Pang YL Cavallaro A
06-08-2021
Towards safe human-to-robot handovers of unknown containersPang YL Xompero A Oh C Cavallaro A
In Arxiv
02-07-2021
Wide and Narrow: Video Prediction from Context and MotionCho J Lee J Oh C Song W Sohn K
32nd British Machine Vision Conference Bmvc 2021.
01-01-2021
2020
Semantically Adversarial Learnable FiltersShamsabadi AS Oh C Cavallaro A
13-08-2020
An Alternative Laboratory Assessment Approach for Multimedia Modules in a Transnational Education (TNE) Programme during COVID-19Alam AS Lau E Oh C Chai KK
2020 Transnational Engineering Education using Technology (TREET). vol. 00, 1-4.
31-07-2020
View-Action Representation Learning for Active First-Person VisionOh C Cavallaro A
IEEE Transactions on Circuits and Systems For Video Technology, Institute of Electrical and Electronics Engineers, 1-1.
13-04-2020
Simultaneous Deep Stereo Matching and Dehazing with Feature AttentionSong T Kim Y Oh C Jang H Ha N Sohn K
International Journal of Computer Vision, Springer Verlag
21-01-2020
2019
EdgeFool: An Adversarial Image Enhancement FilterShamsabadi AS Oh C Cavallaro A
27-10-2019
Learning action representations for self-supervised visual explorationOH C CAVALLARO A
IEEE Int. Conference on Robotics and Automation (ICRA).
12-08-2019
OCEAN: Object-centric arranging network for self-supervised visual representations learningOh C Ham B Kim H Hilton A Sohn K
Expert Systems With Applications, Elsevier vol. 125, 281-292.
01-07-2019
Deep network for simultaneous stereo matching and dehazingSong T Kim Y Oh C Sohn K
British Machine Vision Conference 2018, BMVC 2018.
01-01-2019
2018
Multi-Task Self-Supervised Visual Representation Learning for Monocular Road SegmentationCho L Kim Y Jung H Oh C Youn J Sohn K
2018 IEEE International Conference on Multimedia and Expo (ICME). vol. 00, 1-6.
23-07-2018
Deep network for simultaneous stereo matching and dehazingSong T Kim Y Oh C Sohn K
British Machine Vision Conference 2018 Bmvc 2018.
01-01-2018
2017
Personness estimation for real-time human detection on mobile devicesKim K Oh C Sohn K
Expert Systems With Applications, Elsevier vol. 72, 130-138.
01-04-2017
Robust interactive image segmentation using structure-aware labelingOh C Ham B Sohn K
Expert Systems With Applications, Elsevier Bv vol. 79, 90-100.
27-02-2017
Depth Prediction from a Single Image with Conditional Adversarial NetworksJung H Kim Y Min D Oh C Sohn K
2017 IEEE International Conference on Image Processing (ICIP)., 1717-1721.
01-01-2017
Point-Cut: Interactive Image Segmentation Using Point SupervisionOh C Ham B Sohn K
Lecture Notes in Computer Science. vol. 10111, 229-244.
01-01-2017
2016
Structure Selective Depth Superresolution for RGB-D CamerasKim Y Ham B Oh C Sohn K
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers (IEEE) vol. 25 (11), 5227-5238.
18-08-2016
Non-parametric human segmentation using support vector machineKim K Oh C Sohn K
IEEE Transactions on Consumer Electronics, Institute of Electrical and Electronics Engineers (IEEE) vol. 62 (2), 150-158.
29-07-2016
Depth Extraction from a Single Image Based on Block-Matching and Robust RegressionJeong H Oh C Kim Y Sohn K
Electronic Imaging. vol. 2016 (5), 1-6.
14-02-2016
Edge-Aware Image Smoothing Using Commute Time DistancesKim Y Oh C Sohn K
2016 IEEE International Conference on Image Processing (ICIP)., 3304-3308.
01-01-2016
Non-Parametric Human Segmentation Using Support Vector MachineKim K Oh C Sohn K
2016 IEEE International Conference on Consumer Electronics (ICCE)., 131-132.
01-01-2016
2015
Depth Analogy: Data-Driven Approach for Single Image Depth Estimation Using Gradient SamplesChoi S Min D Ham B Kim Y Oh C Sohn K
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers (IEEE) vol. 24 (12), 5953-5966.
27-10-2015
Segment-Based Free Space Estimation Using Plane Normal Vector in Disparity SpaceSeo J Oh C Sohn K
2015 International Conference on Connected Vehicles and Expo (ICCVE)., 144-149.
01-10-2015
Structure-aware depth super-resolution using Gaussian mixture modelKim S Oh C Kim Y Sohn K
Three-Dimensional Image Processing, Measurement (3DIPM), and Applications 2015. vol. 9393
17-03-2015
Visual Fatigue Relaxation for Stereoscopic Video via Nonlinear Disparity RemappingChangjae Oh Bumsub Ham Sunghwan Choi Kwanghoon Sohn
IEEE Transactions on Broadcasting, Institute of Electrical and Electronics Engineers (IEEE) vol. 61 (2), 142-153.
02-03-2015
A Majorize-Minimize Approach for High-Quality Depth UpsamplingKim Y Choi S Oh C Sohn K
2015 IEEE International Conference on Image Processing (ICIP)., 392-396.
01-01-2015
Sparse Edit Propagation for High Resolution Image Using Support Vector MachinesOh C Ryu S Kim Y Kim J Park T Sohn K
2015 IEEE International Conference on Image Processing (ICIP)., 4042-4046.
01-01-2015
2013
Probability-Based Rendering for View SynthesisHam B Min D Oh C N. M Sohn K
IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers (IEEE) vol. 23 (2), 870-884.
20-12-2013
Disparity Search Range Estimation Based on Dense Stereo MatchingLi R Ham B Oh C Sohn K
2013 IEEE 8th Conference on Industrial Electronics and Applications (ICIEA)., 753-759.
01-06-2013
2012
Hybrid Approach for Accurate Depth Acquisition with Structured Light and Stereo CameraChoi S Ham B Oh C Choo H-G Kim J Sohn K
IEEE international Symposium on Broadband Multimedia Systems and Broadcasting., 1-4.
01-06-2012
Probabilistic Correspondence Matching using Random Walk with RestartOh C Ham B Sohn K
Procedings of the British Machine Vision Conference 2012., 37.1-37.10.
01-01-2012
Robotic Perception of Underwater Plastic Bottles for Augmented TelepresenceSmiles A Oh C Farkhatdinov I
European Robotics Forum.
Coming Out of the Dark: Human Pose Estimation in Low-light ConditionsSu Y Chen D Xing M Oh C Liu X Li J
International Joint Conference on Artificial Intelligence.
Improving Generalization of Language-Conditioned Robot ManipulationCui C Zhu C Oh C Cavallaro A
IEEE/RSJ International Conference on Intelligent Robots and Systems.
LaVA-Man: Learning Visual Action Representations for Robot ManipulationZhu C Wang H Pang YL Oh C
Conference on Robot Learning.
A Deployment-oriented Simulation Framework for Deep Learning-based Lane Change PredictionForneris L Fresta M Lazzaroni L Rojhan H Oh C Pighetti A Tango F Bellotti F
IEEE Signal Processing Letters, Institute of Electrical and Electronics Engineers
EdgeFool: An Adversarial Image Enhancement FilterShahin Shmasabadi A Oh C Cavallaro A
International Conference on Acoustics, Speech, and Signal Processing.
Investigating Adversarial Policy Learning for Robust Agents in Automated Driving Highway SimulationsPighetti A Bellotti F Oh C Lazzaroni L Forneris L Fresta M Berta R
International Conference on Applications in Electronics Pervading Industry, Environment and Society.
Grants
Grants of specific relevance to the Centre for Multimodal AIUncertainty Aware Data Attribution Of Vision-Language ModelsChangjae Oh, Shaogang Gong and Ziquan Liu
£326,000 Huawei Technologies Germany
15-10-2025 - 14-10-2027
International Collaborative Research (QMUL Korea University)Changjae Oh
£22,240 Korea University
01-03-2025 - 31-12-2027
Development of Multi-Modal Foundational Models and AI Accelerators for Zero-shot Intelligent Surveillance SystemChangjae Oh and Andrea Cavallaro
£384,699 Korea Institute for Advancement of Technology
01-08-2024 - 31-07-2027
Generative Models Based Robot Manipulation Environment for Human-to-Robot HandoverChangjae Oh
£19,751 Royal Society
01-10-2024 - 30-09-2025
Research Group
PhD Students
- Om Lbaneen Audi
Vision - Zhengqi Chen
Tactile Retrieval of Objects Buried Within Granular Materials Using a Distributed 3-Axis Tactile Sensor - Chenglin Cui
Vision-Language Models For Robot Learning and Manipulation - Luca Forneris
Closing The Loop in Automated Driving: Dataset Design, Scenario Synthesis, and Deployed Perception - Qifan Fu
Photo-Realistic Hand Gesture Generation and Communication Application - Alessandro Pighetti
Adversarial Policies For Automated Driving - Aaron Smiles
Exploring Stereo-Vision Data and Object Detection in Underwater Environments - Yazhe Wan
Vision - Yuekun Wu
Vision-Based Robot Learning For Human-to-Robot Handover - Xiaohang Yang
MMV - Sofia Zahri
Federated Learning Techniques For Malaria Prediction - Chaoran Zhu
Vision
News
No news items found.