Bo (Hawk) Wang

I am an Assistant Professor in Computer Science at Ole Miss. My research focuses on computer vision and deep learning, particularly in human-centric tasks such as human pose and human-objection interaction. For more information about computer vision and deep learning research in general, check out my blog post.

I obtained my PhD from the School of Computing at the University of Utah. After completing my PhD, I spent nearly a decade in industry research labs, with positions from Research Scientist to Principal Researcher at GE Global Research, Tencent US, and CtrsVision.

Contact

214 Weir Hall, University, MS 38677

Information for Prospective Students

Current Ole Miss students: I encourage you to email me your CV and schedule a meeting to discuss opportunities in person.

Prospective students: If you are interested in pursuing a PhD at Ole Miss and would like to work with me, please email your CV and transcripts with the subject line “[25Spring (or other semester you plan to start) PhD Application - Your Name].”

For more information about computer vision and deep learning research and its impact, I encourage you to read my blog post.

news

Sep, 2024	A zero-shot HOI detection paper accepted at NeurIPS 2024.
Jul, 2024	A domain-adaptive human pose estimation paper accepted at ECCV 2024.
Jan, 2024	Outstanding Reviewer Award at WACV 2024.
Dec, 2023	An HOI detection paper accepted at AAAI 2024.
Nov, 2023	Serve as Area Chair for ECCV 2024.
Feb, 2023	A 3D Dense Face Alignment paper accepted at CVPR 2023.
Feb, 2023	A 2D human pose estimation paper accepted to Pattern Recognition journal.
Oct, 2022	Outstanding Reviewer Award at ECCV 2022.
Apr, 2022	A 3D multi-person pose estimation paper accepted to TPAMI.

selected publications

ECCV

Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions

Yihao Ai , Yifei Qi , Bo Wang, Yu Cheng , and 2 more authors

In European Conference on Computer Vision , 2024

arXiv Bib

@inproceedings{ai2024domain,
  title = {Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions},
  author = {Ai, Yihao and Qi, Yifei and Wang, Bo and Cheng, Yu and Wang, Xinchao and Tan, Robby T},
  booktitle = {European Conference on Computer Vision},
  year = {2024},
}

AAAI

Few-Shot Learning from Augmented Label-Uncertain Queries in Bongard-HOI

Qinqian Lei , Bo Wang, and Robby T Tan

In Proceedings of the AAAI Conference on Artificial Intelligence , 2024

arXiv Bib Code Website

@inproceedings{lei2024fewshot,
  title = {Few-Shot Learning from Augmented Label-Uncertain Queries in Bongard-HOI},
  author = {Lei, Qinqian and Wang, Bo and Tan, Robby T},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
}

CVPR

DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment

Heyuan Li , Bo Wang, Yu Cheng , Mohan Kankanhalli , and 1 more author

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2023

arXiv Bib HTML Code

@inproceedings{li2023dsfnet,
  title = {DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment},
  author = {Li, Heyuan and Wang, Bo and Cheng, Yu and Kankanhalli, Mohan and Tan, Robby T},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {4531--4540},
  year = {2023},
}

PR journal

Bottom-up 2D pose estimation via dual anatomical centers for small-scale persons

Yu Cheng* , Yihao Ai* , Bo Wang, Xinchao Wang , and 1 more author

Pattern Recognition, 2023

arXiv Bib HTML

@article{cheng2023bottom,
  title = {Bottom-up 2D pose estimation via dual anatomical centers for small-scale persons},
  author = {Cheng*, Yu and Ai*, Yihao and Wang, Bo and Wang, Xinchao and Tan, Robby T},
  journal = {Pattern Recognition},
  volume = {139},
  pages = {109403},
  year = {2023},
  publisher = {Elsevier},
}

TPAMI

Dual networks based 3d multi-person pose estimation from monocular video

Yu Cheng , Bo Wang, and Robby T Tan

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022

arXiv Bib HTML Code

@article{cheng2022dual,
  title = {Dual networks based 3d multi-person pose estimation from monocular video},
  author = {Cheng, Yu and Wang, Bo and Tan, Robby T},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume = {45},
  number = {2},
  pages = {1636--1651},
  year = {2022},
  publisher = {IEEE},
}

CVPR

Monocular 3D multi-person pose estimation by integrating top-down and bottom-up networks

Yu Cheng , Bo Wang, Bo Yang , and Robby T Tan

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2021

arXiv Bib HTML Code

@inproceedings{cheng2021monocular,
  title = {Monocular 3D multi-person pose estimation by integrating top-down and bottom-up networks},
  author = {Cheng, Yu and Wang, Bo and Yang, Bo and Tan, Robby T},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {7649--7659},
  year = {2021},
}

AAAI

Graph and temporal convolutional networks for 3d multi-person pose estimation in monocular videos

Yu Cheng , Bo Wang, Bo Yang , and Robby T Tan

In Proceedings of the AAAI Conference on Artificial Intelligence , 2021

arXiv Bib HTML Code

@inproceedings{cheng2021graph,
  title = {Graph and temporal convolutional networks for 3d multi-person pose estimation in monocular videos},
  author = {Cheng, Yu and Wang, Bo and Yang, Bo and Tan, Robby T},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {35},
  number = {2},
  pages = {1157--1165},
  year = {2021},
}

AAAI

3d human pose estimation using spatio-temporal networks with explicit occlusion training

Yu Cheng* , Bo Yang* , Bo Wang*, and Robby T Tan

In Proceedings of the AAAI Conference on Artificial Intelligence , 2020

arXiv Bib HTML

@inproceedings{cheng20203d,
  title = {3d human pose estimation using spatio-temporal networks with explicit occlusion training},
  author = {Cheng*, Yu and Yang*, Bo and Wang*, Bo and Tan, Robby T},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {34},
  number = {07},
  pages = {10631--10638},
  year = {2020},
}

ICCV

Occlusion-aware networks for 3d human pose estimation in video

Yu Cheng* , Bo Yang* , Bo Wang, Wending Yan , and 1 more author

In Proceedings of the IEEE/CVF International Conference on Computer Vision , 2019

Bib HTML

@inproceedings{cheng2019occlusion,
  title = {Occlusion-aware networks for 3d human pose estimation in video},
  author = {Cheng*, Yu and Yang*, Bo and Wang, Bo and Yan, Wending and Tan, Robby T},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages = {723--732},
  year = {2019},
}