Hawk Bo Wang

I am an Assistant Professor in Computer Science at Ole Miss. My research interests in computer vision, deep learning, and multimodal models focus on enhancing the robustness and generalization of models, with applications to human-centric tasks such as human pose estimation and human-object interaction. I obtained my PhD from the School of Computing at the University of Utah. After that, I spent nearly a decade in industry research labs at GE Global Research, Tencent US, and CtrsVision. In both industry and academia, I regularly serve as a Program Committee member and Area Chair for leading computer vision and AI venues, including CVPR, ICCV, ECCV, NeurIPS, and WACV, among others. For more information about computer vision and deep learning research in general, check out my blog post.

Office: 209-C Weir Hall, University, MS 38677

news

Sep, 2026	An affordance grounding paper accepted at ECCV 2026.
Jul, 2026	Outstanding Reviewer at ECCV 2026.
Jun, 2026	Serving as Area Chair for WACV 2027.
Jun, 2026	Maja’s paper received the Best Paper Award at GRAIL-V, CVPR 2026 (photos).
Jun, 2026	Keynote speaker at CVPR 2026 10th ABAW Workshop (Behavior Analysis in the Wild).
Jun, 2026	Two papers (HOI and human pose) accepted at CVPR 2026.
May, 2026	Received NAIRR support for evaluating HOI understanding (paper).
Mar, 2026	Received an M2AIR grant AI-based research on aging and social well-being (news).
Mar, 2026	Serving as Area Chair for NeurIPS 2026.
Sep, 2025	A 3D texture transfer paper accepted at NeurIPS 2025.
Aug, 2025	Serving as Area Chair for WACV 2026.
Jun, 2025	An HOI detection paper accepted at ICCV 2025.
May, 2025	Received a Mississippi Impact Grant for vision-based research on pedestrian safety.
Sep, 2024	A zero-shot HOI paper accepted at NeurIPS 2024.
Jul, 2024	A human pose paper accepted at ECCV 2024.

recent publications

Token-Based Affordance Grounding with Large Vision-Language Models

Seung il Lee , Qinqian Lei , Daguang Xu , Dong Yang , and 3 more authors

In European Conference on Computer Vision (ECCV) , 2026

arXiv Bib Code Website

@inproceedings{Lee_2026_ECCV,
  author = {Lee, Seung il and Lei, Qinqian and Xu, Daguang and Yang, Dong and Tan, Robby T. and Chen, Yixin and Wang, Bo},
  title = {Token-Based Affordance Grounding with Large Vision-Language Models},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year = {2026},
}

UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation

Haopeng Chen , Yihao Ai , Kabeen Kim , Robby T. Tan , and 2 more authors

In Computer Vision and Pattern Recognition (CVPR) , 2026

arXiv Bib Code

@inproceedings{Chen_2026_CVPR,
  author = {Chen, Haopeng and Ai, Yihao and Kim, Kabeen and Tan, Robby T. and Chen, Yixin and Wang, Bo},
  title = {UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation},
  booktitle = {Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
}

CrossHOI-Bench: A Unified Benchmark for HOI Evaluation across Vision-Language Models and HOI-Specific Methods

Qinqian Lei , Bo Wang, and Robby T. Tan

In Computer Vision and Pattern Recognition (CVPR) , 2026

arXiv Bib Code Website

@inproceedings{Lei_2026_CVPR,
  author = {Lei, Qinqian and Wang, Bo and Tan, Robby T.},
  title = {CrossHOI-Bench: A Unified Benchmark for HOI Evaluation across Vision-Language Models and HOI-Specific Methods},
  booktitle = {Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
}

3DOTT: Texture Transfer for 3D Objects from a Single Reference Image

Xiao Cao , Beibei Lin , Bo Wang, Zhiyong Huang , and 1 more author

In Neural Information Processing Systems , 2025

arXiv Bib Website

@inproceedings{xiao2025texture,
  title = {3DOTT: Texture Transfer for 3D Objects from a Single Reference Image},
  author = {Cao, Xiao and Lin, Beibei and Wang, Bo and Huang, Zhiyong and Tan, Robby T},
  booktitle = {Neural Information Processing Systems},
  year = {2025},
}

HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation

Qinqian Lei , Bo Wang, and Robby T Tan

In International Conference on Computer Vision , 2025

arXiv Bib Code Website

@inproceedings{lei2025zeroshot,
  title = {HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation},
  author = {Lei, Qinqian and Wang, Bo and Tan, Robby T},
  booktitle = {International Conference on Computer Vision},
  year = {2025},
}

EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection

Qinqian Lei , Bo Wang, and Robby T Tan

In Neural Information Processing Systems , 2024

arXiv Bib Code Website

@inproceedings{lei2024zeroshot,
  title = {EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection},
  author = {Lei, Qinqian and Wang, Bo and Tan, Robby T},
  booktitle = {Neural Information Processing Systems},
  year = {2024},
}

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 Code

@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},
}