Shihao CHENG (程世豪)

@inproceedings{cheng2026unisonharmonizingmotionspeech,
  title = {Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation},
  author = {Cheng, Shihao and Zhang, Jiaxu and Song, Quanyue and Liu, Shansong and Guo, Zhizhi and Zhang, Xiaolei and Zhang, Chi and Li, Xuelong and Tu, Zhigang},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year = {2026},
  archiveprefix = {arXiv},
  primaryclass = {cs.CV},
  url = {https://arxiv.org/abs/2605.08729},
}

@inproceedings{Xiao_2026_CVPR,
  project_page = {https://geo-mm-agi.github.io},
  github_stars = {Shihao-Cheng/GeoMMAgent},
  dataset = {https://huggingface.co/datasets/AR-X/GeoMMBench},
  author = {Xiao, Aoran and Cheng, Shihao and Xu, Yonghao and Ren, Yexian and Chen, Hongruixuan and Yokoya, Naoto},
  title = {GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = jun,
  year = {2026},
  pages = {34843-34853}
}

@article{11250624,
  author = {Cheng, Shihao and Zhang, Jinlu and Liu, Yue and Xiao, Aoran and Tu, Zhigang},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  title = {OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition},
  year = {2025},
  volume = {36},
  number = {4},
  pages = {4550-4564},
  keywords = {Videos;Lighting;Accuracy;Visualization;Training;Brightness;Random access memory;Learning systems;Complexity theory;Biomimetics;Dark video;action recognition;biomimetic design},
  doi = {10.1109/TCSVT.2025.3632359},
}