For full functionality of this site it is necessary to enable JavaScript. Here are the instructions how to enable JavaScript in your web browser.

Position within the page tree

Home
Team
Hu, Zhiming

Zhiming Hu

PhD

Research associate
Institut für Modellierung und Simulation Biomechanischer Systeme

Contact

Pfaffenwaldring 5a
70569 Stuttgart
Deutschland

Office Hours

upon request

Subject

Biorobotics
Motor Control
Pneumatic Actuators

Publications

Publications:

Jiao C, Hu Z, Bâce M, Bulling A. SUPREYES: SUPer Resolutin for EYES Using Implicit Neural Representation Learning. In: Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology [Internet]. San Francisco, CA, USA: Association for Computing Machinery; 2023. (UIST ’23). Available from: https://doi.org/10.1145/3586183.3606780
- BibTeX
BibTeX
@inproceedings{10.1145/3586183.3606780, abstract = {We introduce SUPREYES – a novel self-supervised method to increase the spatio-temporal resolution of gaze data recorded using low(er)-resolution eye trackers. Despite continuing advances in eye tracking technology, the vast majority of current eye trackers – particularly mobile ones and those integrated into mobile devices – suffer from low-resolution gaze data, thus fundamentally limiting their practical usefulness. SUPREYES learns a continuous implicit neural representation from low-resolution gaze data to up-sample the gaze data to arbitrary resolutions. We compare our method with commonly used interpolation methods on arbitrary scale super-resolution and demonstrate that SUPREYES outperforms these baselines by a significant margin. We also test on the sample downstream task of gaze-based user identification and show that our method improves the performance of original low-resolution gaze data and outperforms other baselines. These results are promising as they open up a new direction for increasing eye tracking fidelity as well as enabling new gaze-based applications without the need for new eye tracking equipment.}, address = {New York, NY, USA}, articleno = {81}, author = {Jiao, Chuhan and Hu, Zhiming and B\^{a}ce, Mihai and Bulling, Andreas}, booktitle = {Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology}, doi = {10.1145/3586183.3606780}, isbn = {9798400701320}, location = {San Francisco, CA, USA}, numpages = {13}, publisher = {Association for Computing Machinery}, series = {UIST '23}, title = {SUPREYES: SUPer Resolutin for EYES Using Implicit Neural Representation Learning}, url = {https://doi.org/10.1145/3586183.3606780}, year = 2023 }
Hu Z, Zhang G, Yin Z, Haeufle D, Schmitt S, Bulling A. HaHeAE: Learning Generalisable Joint Representations of Human Hand and Head Movements in Extended Reality. IEEE Transactions on Visualization and Computer Graphics. 2025;
- BibTeX
BibTeX
@article{hu25haheae, author = {Hu, Zhiming and Zhang, Guanhua and Yin, Zheming and Haeufle, Daniel and Schmitt, Syn and Bulling, Andreas}, journal = {IEEE Transactions on Visualization and Computer Graphics}, title = {HaHeAE: Learning Generalisable Joint Representations of Human Hand and Head Movements in Extended Reality}, year = 2025 }
Hu Z, Yin Z, Haeufle D, Schmitt S, Bulling A. HOIMotion: Forecasting Human Motion During Human-Object Interactions Using Egocentric 3D Object Bounding Boxes. IEEE Transactions on Visualization and Computer Graphics (TVCG) [Internet]. 2024;1–11. Available from: https://arxiv.org/abs/2407.02633
- BibTeX
BibTeX
@article{hu24hoimotion, abstract = {We present HOIMotion – a novel approach for human motion forecasting during human-object interactions that integrates information about past body poses and egocentric 3D object bounding boxes. Human motion forecasting is important in many augmented reality applications but most existing methods have only used past body poses to predict future motion. HOIMotion first uses an encoder-residual graph convolutional network (GCN) and multi-layer perceptrons to extract features from body poses and egocentric 3D object bounding boxes, respectively. Our method then fuses pose and object features into a novel pose-object graph and uses a residual-decoder GCN to forecast future body motion. We extensively evaluate our method on the Aria digital twin (ADT) and MoGaze datasets and show that HOIMotion consistently outperforms state-of-the-art methods by a large margin of up to 8.7% on ADT and 7.2% on MoGaze in terms of mean per joint position error. Complementing these evaluations, we report a human study (N=20) that shows that the improvements achieved by our method result in forecasted poses being perceived as both more precise and more realistic than those of existing methods. Taken together, these results reveal the significant information content available in egocentric 3D object bounding boxes for human motion forecasting and the effectiveness of our method in exploiting this information.}, archiveprefix = {arXiv}, author = {Hu, Zhiming and Yin, Zheming and Haeufle, Daniel and Schmitt, Syn and Bulling, Andreas}, eprint = {2407.02633}, journal = {IEEE Transactions on Visualization and Computer Graphics (TVCG)}, note = {spotlight}, pages = {1--11}, primaryclass = {cs.CV}, title = {HOIMotion: Forecasting Human Motion During Human-Object Interactions Using Egocentric 3D Object Bounding Boxes}, url = {https://arxiv.org/abs/2407.02633}, year = 2024 }
Hu Z, Haeufle D, Schmitt S, Bulling A. HOIGaze: Gaze Estimation During Hand-Object Interactions in Extended Reality Exploiting Eye-Hand-Head Coordination. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers [Internet]. New York, NY, USA: Association for Computing Machinery; 2025. (SIGGRAPH Conference Papers ’25). Available from: https://doi.org/10.1145/3721238.3730692
- BibTeX
BibTeX
@inproceedings{10.1145/3721238.3730692, abstract = {We present HOIGaze – a novel learning-based approach for gaze estimation during hand-object interactions (HOI) in extended reality (XR). HOIGaze addresses the challenging HOI setting by building on one key insight: Eye, hand, and head movements are closely coordinated during HOIs and this coordination can be exploited to identify samples that are most useful for gaze estimator training – as such, effectively denoising the training data. This denoising approach is in stark contrast to previous gaze estimation methods that treated all training samples as equal. Specifically, we propose: 1) a novel hierarchical framework that first recognises the hand currently visually attended to and then estimates gaze direction based on the attended hand; 2) a new gaze estimator that uses cross-modal Transformers to fuse head and hand-object features extracted using a convolutional neural network and a spatio-temporal graph convolutional network; and 3) a novel eye-head coordination loss that upgrades training samples belonging to the coordinated eye-head movements. We evaluate HOIGaze on the HOT3D and Aria digital twin (ADT) datasets and show that it significantly outperforms state-of-the-art methods, achieving an average improvement of 15.6\% on HOT3D and 6.0\% on ADT in mean angular error. To demonstrate the potential of our method, we further report significant performance improvements for the sample downstream task of eye-based activity recognition on ADT. Taken together, our results underline the significant information content available in eye-hand-head coordination and, as such, open up an exciting new direction for learning-based gaze estimation.}, address = {New York, NY, USA}, articleno = {17}, author = {Hu, Zhiming and Haeufle, Daniel and Schmitt, Syn and Bulling, Andreas}, booktitle = {Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers}, doi = {10.1145/3721238.3730692}, isbn = {9798400715402}, numpages = {10}, publisher = {Association for Computing Machinery}, series = {SIGGRAPH Conference Papers '25}, title = {HOIGaze: Gaze Estimation During Hand-Object Interactions in Extended Reality Exploiting Eye-Hand-Head Coordination}, url = {https://doi.org/10.1145/3721238.3730692}, year = 2025 }
Yan H, Hu Z, Schmitt S, Bulling A. GazeMoDiff: Gaze-guided Diffusion Model for Stochastic Human Motion Prediction. In: Proceedings of the 2024 Pacific Conference on Computer Graphics and Applications. 2024.
- BibTeX
BibTeX
@inproceedings{yan24gazemodiff, author = {Yan, Haodong and Hu, Zhiming and Schmitt, Syn and Bulling, Andreas}, booktitle = {Proceedings of the 2024 Pacific Conference on Computer Graphics and Applications}, title = {GazeMoDiff: Gaze-guided Diffusion Model for Stochastic Human Motion Prediction}, year = 2024 }
Hu Z, Xu J, Schmitt S, Bulling A. Pose2Gaze: Eye-body Coordination during Daily Activities for Gaze Prediction from Full-body Poses. IEEE Transactions on Visualization and Computer Graphics (TVCG). 2024;
- BibTeX
BibTeX
@article{hu24pose2gaze, archiveprefix = {arXiv}, author = {Hu, Zhiming and Xu, Jiahui and Schmitt, Syn and Bulling, Andreas}, eprint = {2312.12042}, journal = {IEEE Transactions on Visualization and Computer Graphics (TVCG)}, primaryclass = {cs.CV}, title = {Pose2Gaze: Eye-body Coordination during Daily Activities for Gaze Prediction from Full-body Poses}, year = 2024 }
Hu Z, Schmitt S, Haeufle D, Bulling A. GazeMotion: Gaze-guided Human Motion Forecasting. In: Proceedings of the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2024.
- BibTeX
BibTeX
@inproceedings{hu24gazemotion, author = {Hu, Zhiming and Schmitt, Syn and Haeufle, Daniel and Bulling, Andreas}, booktitle = {Proceedings of the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems}, title = {GazeMotion: Gaze-guided Human Motion Forecasting}, year = 2024 }

Vita

Scientific Education

Electrical Engineering with focus on Power Electronics and Control Engineering in major
Sportscience with focus on Biomechanics in minor

Zhiming Hu

Contact

Office Hours

Subject

Publications

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

Vita

Audience

Formalities

Services

Organization

Zhiming Hu

Contact

Office Hours

Subject

Publications

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

BibTeX

Vita

Here you can reach us

Audience

Formalities

Services

Organization