Hyung Jin Chang

University of Birmingham — United Kingdom

Computer Science · Physical Sciences

31h-index5.5kcitations172works2.02yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Human Pose and Action Recognition(50), Robot Manipulation and Learning(32), Video Surveillance and Tracking Methods(28), Advanced Vision and Imaging(24), Hand Gesture Recognition Systems(22)

Publications172 total

Force-Aware 3D Contact Modeling for Stable Grasp Generation
arXiv (Cornell University)·2025Open Access
RTGaze: Real-Time 3D-Aware Gaze Redirection from a Single Image
arXiv (Cornell University)·2025Open Access
Roll Your Eyes: Gaze Redirection via Explicit 3D Eyeball Rotation
2025
The Third Visual Object Tracking Segmentation VOTS2025 Challenge Results
2025
DarkSeg: Infrared-Driven Semantic Segmentation for Garment Grasping Detection in Low-Light Conditions
2025
High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation
arXiv (Cornell University)·2025Open Access
Audio-Visual Separation with Hierarchical Fusion and Representation Alignment
arXiv (Cornell University)·2025Open Access
Towards cost-effective and safe contact-rich robotic manipulation with reinforcement learning: A review of techniques for future industrial automation
Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering·2025Open Access
Roll Your Eyes: Gaze Redirection via Explicit 3D Eyeball Rotation
arXiv (Cornell University)·2025Open Access
Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models
arXiv (Cornell University)·2025Open Access
Video-based human pose estimation via feature decoupling and multi-hypothesis calibration
Pattern Recognition·2025
Multi-Hypothesis 3D Hand Mesh Recovering from a Single Blurry Image
2025
On the design fundamentals of diffusion models: A survey
Pattern Recognition·2025· 13 citedOpen Access
3D Prior is All You Need: Cross-Task Few-shot 2D Gaze Estimation
2025· 1 cited
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation
2025
PersonaBooth: Personalized Text-to-Motion Generation
2025· 1 cited
Behavior-Aware Knowledge-Embedded Model for Driver Attention Prediction
IEEE Transactions on Circuits and Systems for Video Technology·2025· 1 cited
Foundation Model-Driven Framework for Human-Object Interaction Prediction with Segmentation Mask Integration
arXiv (Cornell University)·2025Open Access
Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics
Proceedings of the AAAI Conference on Artificial Intelligence·2025Open Access
Single-view Image to Novel-view Generation for Hand-Object Interactions
Proceedings of the AAAI Conference on Artificial Intelligence·2025Open Access
page 1 of 9Next →

Frequent Co-authors

Jin Young Choi(13), Aleš Leonardis(12), Yiannis Demiris(11), Jongwon Choi(5), Tae‐Kyun Kim(5), Tobias Fischer(5), Jinming Duan(5), Tze Ho Elden Tse(5), Matej Kristan(4), Jiřı́ Matas(4), Michael Felsberg(4), Roman Pflugfelder(4), Luka Čehovin Zajc(4), Alan Lukežič(4), Gustavo J. Fernández(4), Alireza Memarmoghadam(4), Rama Krishna Gorthi(4), Huchuan Lu(4), Martin Danelljan(4), Wonjun Hwang(4)