Institut für Informationsverarbeitung (TNT)

Yi Yang received his B.Eng. degree in Surveying Engineering at Tongji University, China (2018), and M.Sc. degree in Data Science at Peking University, China (2021), and M.Sc. degree in Environmental Data Science & Engineering at Imperial College London, UK (with distinction, 2023).

Yi started working on the EU funded project XTREME as a PhD candidate in ITC, University of Twente, Netherlands, in February 2024. Since November 2024 he has relocated to TNT, Leibniz University Hannover, and continues to work towards his PhD. Yi is jointly supervised by Prof. Michael Ying Yang (University of Bath) and Prof. Bodo Rosenhahn.

Yi's research interests include object detection and scene graph generation for image and video data.

Publications

Show selected publications only

Yi Yang, Myrna Castillo, Bodo Rosenhahn, Michael Ying Yang
PUF: Plug-and-Play Uncertainty-Aware Fusion for Online 3D Scene Graph Generation
European Conference on Computer Vision (ECCV), September 2026
(arXiv.org, GitHub) BibTeX
John Helsby*, Yi Yang*, Bodo Rosenhahn, Michael Ying Yang, (* equal contribution)
OvDSGG: End-to-End Open-Vocabulary Dynamic Scene Graph Generation
European Conference on Computer Vision CONTEXTUS Workshop (ECCVW), September 2026
(arXiv.org, GitHub) BibTeX
Ruchen Liu*, Yi Yang*, Yiming Xu*, Michael Ying Yang, Monika Sester, Bodo Rosenhahn, (* equal contribution)
Seeing Before Answering: Training-Free Visual Layer Profiling for Vision-Language Models
European Conference on Computer Vision eXCV Workshop (ECCVW), September 2026
(arXiv.org) BibTeX
Yiming Xu, Yi Yang, Hao Cheng, Monika Sester
HiMAP: History-aware Map-occupancy Prediction with Fallback
2026 IEEE International Conference on Robotics and Automation (ICRA), IEEE, June 2026
(arXiv.org, GitHub) BibTeX
Dayou Chen, Long Chen, Yi Yang, Qiuchen Lu, Craig Hancock, Russell Lock, Simon Sølvsten
A Knowledge-driven Approach for Automated Fire Safety Compliance Checking in Operational Buildings
Knowledge-Based Systems, Elsevier, Vol. 336, p. 115156, January 2026
(DOI) BibTeX
Yi Yang, Yiming Xu, Hao Cheng, Bodo Rosenhahn, Michael Ying Yang
Multi-Object Tracking Retrieval with LLaVA-Video: A Training-Free Solution to MOT25-StAG Challenge
arXiv preprint, November 2025
(arXiv.org) BibTeX