Dr Changjae Oh

Changjae OhPhD, Yonsei University, Korea

Lecturer in Multimedia

Electronic Engineering and Computer Science

Google Scholar


computer vision, robot perception, deep learning


Publications of specific relevance to Advanced Robotics


Oh C, Xompero A and Cavallaro A (2022). Chapter 15 Visual adversarial attacks and defenses. Advanced Methods and Deep Learning in Computer Vision  10.1016/b978-0-12-822109-9.00024-2


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 (2021). A Suite of Robotic Solutions for Nuclear Waste Decommissioning. Robotics  vol. 10, (4) 112-112. 10.3390/robotics10040112
Palermo F, Rincon-Ardila L, Oh C, Althoefer K, Poslad S, Venture G and Farkhatdinov I (2021). Multi-modal robotic visual-tactile localisation and detection of surface cracks. Conference: 2021 IEEE 17th International Conference on Automation Science and Engineering  10.1109/CASE49439.2021.9551553
Shahin Shamsabadi A, Oh C and Cavallaro A (2021). Semantically Adversarial Learnable Filters. IEEE Transactions on Image Processing  10.1109/TIP.2021.3112290
Pang YL, Xompero A, Oh C and Cavallaro A (2021). Towards safe human-to-robot handovers of unknown containers. Conference: IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)  10.1109/ro-man50785.2021.9515350
Oh C, Pang YL and Cavallaro A (2021). OHPL: One-shot Hand-eye Policy Learner. IEEE International Conference on Intelligent Robots and Systems  3904-3910. 10.1109/IROS51168.2021.9636835


Alam AS, Lau E, Oh C and Chai KK (2020). An Alternative Laboratory Assessment Approach for Multimedia Modules in a Transnational Education (TNE) Programme during COVID-19. 2020 Transnational Engineering Education using Technology, TREET 2020  10.1109/TREET50959.2020.9189756
Shamsabadi AS, Oh C and Cavallaro A (2020). Edgefool: An Adversarial Image Enhancement Filter. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings  vol. 2020-May, 1898-1902. 10.1109/ICASSP40776.2020.9054368
Oh C and Cavallaro A (2020). View-Action Representation Learning for Active First-Person Vision. IEEE Transactions on Circuits and Systems for Video Technology  1-1. 10.1109/tcsvt.2020.2987562
Song T, Kim Y, Oh C, Jang H, Ha N and Sohn K (2020). Simultaneous Deep Stereo Matching and Dehazing with Feature Attention. International Journal of Computer Vision  10.1007/s11263-020-01294-2


OH C and CAVALLARO A (2019). Learning action representations for self-supervised visual exploration. Conference: IEEE Int. Conference on Robotics and Automation (ICRA)  10.1109/ICRA.2019.8794401
Song T, Kim Y, Oh C and Sohn K (2019). Deep network for simultaneous stereo matching and dehazing. British Machine Vision Conference 2018, BMVC 2018 


Oh C, Ham B and Sohn K (2017). Robust interactive image segmentation using structure-aware labeling. Expert Systems with Applications  vol. 79, 90-100. 10.1016/j.eswa.2017.02.031


Kim Y, Ham B, Oh C and Sohn K (2016). Structure Selective Depth Superresolution for RGB-D Cameras. IEEE Transactions on Image Processing  vol. 25, (11) 5227-5238. 10.1109/tip.2016.2601262
Kim K, Oh C and Sohn K (2016). Non-parametric human segmentation using support vector machine. IEEE Transactions on Consumer Electronics  vol. 62, (2) 150-158. 10.1109/tce.2016.7514714


Choi S, Min D, Ham B, Kim Y, Oh C and Sohn K (2015). Depth Analogy: Data-Driven Approach for Single Image Depth Estimation Using Gradient Samples. IEEE Transactions on Image Processing  vol. 24, (12) 5953-5966. 10.1109/tip.2015.2495261
Changjae Oh , Bumsub Ham , Sunghwan Choi and Kwanghoon Sohn (2015). Visual Fatigue Relaxation for Stereoscopic Video via Nonlinear Disparity Remapping. IEEE Transactions on Broadcasting  vol. 61, (2) 142-153. 10.1109/tbc.2015.2402471