Dr Hyung Jin Chang PhD, FHEA

Hyung Jin Chang

School of Computer Science
Associate Professor in Computer Science
Head of External Partnerships of Computer Science

Contact details

Email
h.j.chang@bham.ac.uk
View my research portal
Address
The School of Computer Science
University of Birmingham
Edgbaston
Birmingham
B15 2TT
UK

Dr Hyung Jin Chang is an Associate Professor in Computer Science at the University of Birmingham. His research focuses on human-centred AI and computer vision for intelligent and interactive robotic systems.

Qualifications

  • PhD in Electrical Engineering and Computer Science, Seoul National University, South Korea, 2013
  • BSc in Electrical and Computer Engineering, Seoul National University, South Korea, 2006
  • Fellow of the Higher Education Academy (FHEA)

Biography

Dr Hyung Jin Chang is an Associate Professor in the School of Computer Science at the University of Birmingham and is affiliated with the Institute of Data and Artificial Intelligence (IDAI). He was also a University Turing Fellow of the Alan Turing Institute, the UK’s national institute for data science and artificial intelligence.

He received his BSc in Electrical and Computer Engineering and PhD in Electrical Engineering and Computer Science from Seoul National University in 2006 and 2013, respectively. Before joining the University of Birmingham, he worked as a Post-Doctoral Research Associate at Imperial College London, where he participated in several European research projects focusing on computer vision, machine learning, and human-robot interaction.

Dr Chang’s research lies at the intersection of artificial intelligence, computer vision, robotics, and human-robot interaction, with a particular emphasis on human-centred AI. His work aims to build intelligent robotic systems capable of understanding human perception, action, and intention through visual and multimodal learning.

He is especially interested in human-centred visual learning, including the estimation of human hand pose, body pose, and gaze, and the modelling of human actions and internal states. His broader goal is to advance robot vision and learning for intelligent and natural human–robot interaction.

His research has been supported by national and international funding agencies and industrial partners, and his work has appeared in leading venues such as CVPR, ICCV, ECCV, ICRA, IROS, NeurIPS, and AAAI. He also serves regularly as Area Chair and reviewer for top-tier AI and robotics conferences. He is currently an Associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

For more information, please visit his personal webpage.

Postgraduate supervision

Dr Chang supervises doctoral research in the following areas:

  • Human-centred AI and visual learning
  • Computer vision for human understanding
  • Robot perception and dexterous manipulation
  • Human–robot interaction

He welcomes PhD applicants interested in the intersection of computer vision, robotics, and human-centred intelligence.

Research

Dr Chang’s research combines artificial intelligence, computer vision, and robotics to enable intelligent and interactive robotic systems. His work explores both fundamental visual learning problems and applied robotic perception.

Research themes

  • Human-Centred Visual Learning – Modelling human perception and behaviour through hand, body, and gaze estimation
  • Robot Vision and Dexterity – Enabling robots to perceive and manipulate objects intelligently in dynamic environments
  • Multimodal Learning for Interaction – Integrating vision, touch, and force information for adaptive and safe robot control

He collaborates closely with industrial and academic partners and contributes to UK and EU-funded research programmes on intelligent robot perception.

Publications

Recent publications

Article

Chen, Z, Zheng, L, Zhang, K, Chang, HJ, Zhang, W, Yu, H & Chen, H 2026, 'AISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Prior', IEEE Robotics and Automation Letters, vol. 11, no. 7, 11489497, pp. 7996-8003. https://doi.org/10.1109/LRA.2026.3686704

Chun, S, Kim, B, Chang, HJ & Chang, JY 2026, 'Bidirectional regression for monocular 6DoF head pose estimation and reference system alignment', Pattern Recognition, vol. 179, no. Part A, 113585. https://doi.org/10.1016/j.patcog.2026.113585

Conference contribution

Zhong, H, Tang, F, Chang, HJ & Gao, Y 2026, AMDANet: Attention-Driven Multi-Perspective Discrepancy Alignment for RGB-Infrared Image Fusion and Segmentation. in 2025 IEEE/CVF International Conference on Computer Vision (ICCV). International Conference on Computer Vision (ICCV), Institute of Electrical and Electronics Engineers (IEEE), pp. 10645-10655, International Conference on Computer Vision 2025, Honolulu, Hawaii, United States, 19/10/25. https://doi.org/10.1109/ICCV51701.2025.00991

Wang, S, Huang, Y, Cui, C, Wong, D, Cheng, Y, Neophytou, A & Chang, HJ 2026, Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following. in Advances in Neural Information Processing Systems (NeurIPS 2026). Advances in Neural Information Processing Systems, NeurIPS, 40th Conference on Neural Information Processing Systems, Paris, France, 9/12/26.

Chen, Z, Zhang, Z, Cheng, Y, Leonardis, A & Chang, HJ 2026, Force-Aware 3D Contact Modeling for Stable Grasp Generation. in S Koenig, C Jenkins & ME Taylor (eds), Proceedings of the 40th AAAI Conference on Artificial Intelligence: AAAI-26 Technical Tracks 5. Proceedings of the AAAI Conference on Artificial Intelligence, no. 5, vol. 40, Association for the Advancement of Artificial Intelligence, pp. 3219-3227, 40th AAAI Conference on Artificial Intelligence, Singapore, Singapore, 20/01/26. https://doi.org/10.1609/aaai.v40i5.37316

Hou, Y, Chen, Z, Hu, H, Kim, JW, Jiao, J & Chang, HJ 2026, Gaze-Anchored Social Net: Decoding Implicit Relations via Joint Modeling. in I-M Sintorn, U Pal & S Lu (eds), Pattern Recognition. ICPR 2026 International Workshops: Lyon, France, August 17–22, 2026, Proceedings, Part I. 1st edn, Lecture Notes in Computer Science, vol. 17110, Springer, Cham, Cham, 2nd Workshop on Eye Tracking Techniques, Applications and Challenges, Lyon, France, 21/08/26.

Zhong, H, Han, W, Wang, Z, Feng, R, Tang, F, Lee, T-Y, Fan, Z, Wu, R, Wang, Y, Dong, H, Chen, H, Chang, HJ & Gao, Y 2026, GraspALL: Adaptive Structural Compensation from Illumination Variation for Robotic Garment Grasping in Any Low-Light Conditions. in 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Conference on Computer Vision and Pattern Recognition (CVPR), Institute of Electrical and Electronics Engineers (IEEE), 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Denver, Colorado, United States, 3/06/26.

Feng, R, Chang, HJ, Tse, THE, Kim, B, Chang, Y & Gao, Y 2026, High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation. in 2025 IEEE/CVF International Conference on Computer Vision (ICCV). International Conference on Computer Vision (ICCV), Institute of Electrical and Electronics Engineers (IEEE), pp. 8929-8938, International Conference on Computer Vision 2025, Honolulu, Hawaii, United States, 19/10/25. https://doi.org/10.1109/ICCV51701.2025.00835

Jin, H, Chang, HJ & Kim, E 2026, Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models. in 2025 IEEE/CVF International Conference on Computer Vision (ICCV). International Conference on Computer Vision (ICCV), Institute of Electrical and Electronics Engineers (IEEE), pp. 3466-3476, International Conference on Computer Vision 2025, Honolulu, Hawaii, United States, 19/10/25. https://doi.org/10.1109/ICCV51701.2025.00331

Hu, H, Lin, D, Hou, Y, Li, H, Chang, HJ & Jiao, J 2026, Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence. in P Favaro, Z Kukelova, A Maki, A Rohrbach, K Schindler & F Tombari (eds), Computer Vision – ECCV 2026: 19th European Conference, Malmö, Sweden, September 8–12, 2026, Proceedings, Part LXIV. 1st edn, Lecture Notes in Computer Science, vol. 17064, Springer, pp. 210-228, The 19th European Conference on Computer Vision, Malmö, Sweden, 8/09/26. https://doi.org/10.1007/978-3-032-37196-6_12

Gao, Y, Ma, X, Feng, R & Chang, HJ 2026, Learning Motion Representations in Trajectory Space for Video-based 3D Human Pose Estimation. in 2025 China Automation Congress (CAC)., 11487031, Chinese Automation Congress, ACM/IEEE, pp. 3266-3271, 2025 China Automation Congress, Harbin, China, 26/09/25. https://doi.org/10.1109/CAC67268.2025.11487031

Preprint

Sung, J, Kim, B, Xin, C, Chang, HJ, Kim, C, Choi, S-I & Choi, Y 2026 'Context-Aware Autoregressive Diffusion for Gloss-Wise Sign Language Production' arXiv. https://doi.org/10.48550/arXiv.2606.21234

Wang, S, Huang, Y, Cui, C, Wong, D, Cheng, Y, Neophytou, A & Chang, HJ 2026 'Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following' arXiv. https://doi.org/10.48550/arXiv.2605.22607

Hou, Y, Chen, Z, Hu, H, Kim, JW, Jiao, J & Chang, HJ 2026 'Gaze-Anchored Social Net: Decoding Implicit Relations via Joint Modeling' arXiv. https://doi.org/10.48550/arXiv.2607.22847

Zhong, H, Han, W, Wang, Z, Feng, R, Tang, F, Lee, T-Y, Fan, Z, Wu, R, Wang, Y, Dong, H, Chen, H, Chang, HJ & Gao, Y 2026 'GraspALL: Adaptive Structural Compensation from Illumination Variation for Robotic Garment Grasping in Any Low-Light Conditions' arXiv. https://doi.org/10.48550/arXiv.2603.14789

View all publications in research portal