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:

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 }
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. (Proceedings of the 2024 Pacific Conference on Computer Graphics and Applications).
- 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 [Internet]. 2024. Available from: https://arxiv.org/abs/2403.09885
- BibTeX
BibTeX
@misc{hu2024gazemotiongazeguidedhumanmotion, archiveprefix = {arXiv}, author = {Hu, Zhiming and Schmitt, Syn and Haeufle, Daniel and Bulling, Andreas}, eprint = {2403.09885}, primaryclass = {cs.CV}, title = {GazeMotion: Gaze-guided Human Motion Forecasting}, url = {https://arxiv.org/abs/2403.09885}, 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

Vita

Audience

Formalities

Services

Organization

Zhiming Hu

Contact

Office Hours

Subject

Publications

BibTeX

BibTeX

BibTeX

BibTeX

Vita

Here you can reach us

Audience

Formalities

Services

Organization