Wentao BAO (包文韬)  

Research Scientist

Meta Reality Labs
322 Airport Blvd., Burlingame, CA 94010, USA
Email: wtbao2018 at gmail dot com



About Me

I am a Research Scientist at Meta Reality Labs. I obtained my Ph.D. (2019-2024) from the Department of Computer Science and Engineering (CSE), Michigan State University (MSU), working with Prof. Yu Kong. Prior to MSU, I spent three Ph.D. years (2019-2022) at the B. Thomas Golisano College of Computing and Information Sciences (GCCIS) of Rochester Institute of Technology (R.I.T), working with Prof. Yu Kong and Prof. Qi Yu. I received my Master's degree (2016-2019) and Bachelor's degree (2012-2016) at the School of Remote Sensing and Information Engineering, Wuhan University (WHU) where I was advised by Prof. Daiqin Yang and Prof. Zhenzhong Chen at the Lab. of Intelligent Information Processing (IIP). I have research internship collaborations with excellent industrial researchers from Apple, OPPO US Research Center, and NEC Lab America.

I develop AI to understand the open visual world. I am broadly interested in using images/videos/text to solve real-world challenges including the visual recognition, prediction, understanding, and reasoning. My Ph.D. research works are related to open-set, video understanding, vision-language and 3D vision. Recently, I am particularly interested in multi-modal LLM and generative AI for fantastic vision applications on product.

News []

  • 2024.07: I joined Meta Reality Labs as a research scientist.
  • 2024.07: I successfuly passed the Ph.D. dissertation defense at CSE Department of MSU.
  • 2024.07: Three papers are accepted by ECCV 2024 (two co-authored)!
  • 2024.03: I am selected to present in CVPR 2024 Doctoral Consortium and chat with Prof. Jason Corso.
  • 2024.02: I successfuly passed the MSU PhD Comprehensive Exam, being a Ph.D. candidate!
  • 2023.07: One paper is accepted by ICCV 2023.
  • 2023.05: I am invited to deliver a talk on open-set recognition at the the 2nd MSU-ND workshop.
  • 2023.02: I will be a research intern at NEC Laboratories America, Inc. (Princeton, NJ) in this summer.
  • 2023.02: One co-authored paper is accepted by CVPR 2023.
  • 2022.08: I started my second journey of Ph.D. study at the CSE department at MSU!
  • 2022.07: One co-authored paper is accepted by ECCV 2022.
  • 2022.06: Start my internship at OPPO U.S. Research Center at Palo Alto, CA. (on-site)
  • 2022.05: I attended the conference ICRA 2022 on-site at Philadelphia, PA.
  • 2022.04: I received the CVPR 2022 Travel Award to attend the conference at New Orleans, LA.
  • 2022.03: One paper is accepted by CVPR 2022 for Oral presentation!
  • 2021.10: One co-authored paper is accepted by BMVC 2021.
  • 2021.07: Two papers are accepted by ICCV 2021, with one paper for Oral presentation!
  • 2021.06: Start my internship at Apple Inc., 3D Vision Team at Apple Maps. (remote)
  • 2021.04: One co-authored paper is accepted by IJCNN 2021.
  • 2020.07: Two papers are accepted by ACM MM 2020 (one co-authored).
  • 2020.07: One co-authored paper is accepted by ECCV 2020.
  • 2020.06: One paper is accepted by IROS 2020.
  • 2020.06: One co-authored paper is accepted by ICPR 2020.
  • 2020.05: I passed the Ph.D. Research Potential Assessment!
  • 2019.08: Start my new journey at RIT, Rochester, NY.

Selected Publications

Preprints

MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos
Junyi Ma, Xieyuanli Chen, Wentao Bao, Jingyi Xu, Hesheng Wang
Preprint, 2024
arXiv Code Project BibTeX
Latent Space Energy-based Model for Fine-grained Open Set Recognition
Wentao Bao, Qi Yu, Yu Kong
Preprint, 2023
arXiv BibTeX
On Model Explanations with Transferable Neural Pathways
Xinmiao Lin, Wentao Bao, Qi Yu, Yu Kong
Preprint, 2023
arXiv BibTeX

Conferences

Prompting Language-Informed Distribution for Compositional Zero-Shot Learning
Wentao Bao, Lichang Chen, Heng Huang, Yu Kong
European Conference on Computer Vision (ECCV), 2024
arXiv Code BibTeX
Facial Affective Behavior Analysis with Instruction Tuning
Yifan Li, Anh Dao, Wentao Bao, Zhen Tan, Tianlong Chen, Huan Liu, Yu Kong
European Conference on Computer Vision (ECCV), 2024
arXiv Project BibTeX
Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment
Yuxiao Chen, Kai Li, Wentao Bao, Deep Patel, Yu Kong, Martin Renqiang Min, Dimitris N. Metaxas
European Conference on Computer Vision (ECCV), 2024
BibTeX
Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting
Wentao Bao, Lele Chen, Libing Zeng, Zhong Li, Yi Xu, Junsong Yuan, Yu Kong
International Conference on Computer Vision (ICCV), 2023
PDF Code Project arXiv BibTeX
3D-aware Facial Landmark Detection via Multiview Consistent Training on Synthetic Data
Libing Zeng, Lele Chen, Wentao Bao, Zhong Li, Yi Xu, Junsong Yuan, Nima Khademi Kalantari
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
PDF Code Project BibTeX
Towards Open Set Video Anomaly Detection
Yuansheng Zhu, Wentao Bao, Qi Yu
European Conference on Computer Vision (ECCV), 2022
PDF arXiv Code BibTeX
OpenTAL: Towards Open Set Temporal Action Localization
Wentao Bao, Qi Yu, Yu Kong
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022 (Oral)
PDF arXiv Poster Code BibTeX
Gradient Frequency Modulation for Visually Explaining Video Understanding Models
Xinmiao Lin, Wentao Bao, Matthew Wright, Yu Kong
British Machine Vision Conference (BMVC), 2021
arXiv PDF BibTeX
Evidential Deep Learning for Open Set Action Recognition
Wentao Bao, Qi Yu, Yu Kong
International Conference on Computer Vision (ICCV), 2021 (Oral)
PDF arXiv Poster Code BibTeX
DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation
Wentao Bao, Qi Yu, Yu Kong
International Conference on Computer Vision (ICCV), 2021
PDF arXiv Poster Code BibTeX
Multiple Instance Relational Learning for Video Anomaly Detection
Xiwen Dengxiong, Wentao Bao, Yu Kong
International Joint Conference on Neural Network (IJCNN), 2021
DOI BibTeX
Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning
Wentao Bao, Qi Yu, Yu Kong
The 28th ACM International Conference on Multimedia (MM), 2020
arXiv DOI Code Dataset BibTeX
Activity-driven Weakly-Supervised Spatio-Temporal Grounding from Untrimmed Videos
Junwen Chen, Wentao Bao, Yu Kong
The 28th ACM International Conference on Multimedia (MM), 2020
DOI BibTeX
Group Activity Prediction with Sequential Relational Anticipation Model
Junwen Chen, Wentao Bao, Yu Kong
European Conference on Computer Vision (ECCV), 2020
PDF arXiv Code BibTeX
Object-Aware Centroid Voting for Monocular 3D Object Detection
Wentao Bao, Qi Yu, Yu Kong
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
PDF arXiv Demo BibTeX
Privacy Attributes-aware Message Passing Neural Network for Visual Privacy Attributes Classification
Hanbin Hong, Wentao Bao, Yuan Hong, Yu Kong
International Conference on Pattern Recognition (ICPR), 2020
DOI BibTeX

Journals

Human Scanpath Prediction based on Deep Convolutional Saccadic Model
Wentao Bao, Zhenzhong Chen
Elsevier Journal of Neurocomputing (Neurocomputing), 2020
DOI BibTeX
MonoFENet: Monocular 3D Object Detection with Feature Enhancement Networks
Wentao Bao, Bin Xu, Zhenzhong Chen
IEEE Transactions on Image Processing (TIP), 2019
DOI BibTeX
Group Lasso based Band Selection for Hyperspectral Image Classification
Daiqin Yang, Wentao Bao
IEEE Geoscience and Remote Sensing Letters (GRSL), 2017
DOI Code Dataset BibTeX

Selected Awards & Honors

Awards

Honors

Academic Services

Conference Reviewer

Journal Reviewer

Membership

Volunteer

Teaching

Academic Talks


Last Updated on Sept. 8, 2024
Published with GitHub Pages