Menu
Home
Google Scholar
GitHub
Linkedin
CV

Wan, Bo (万博)

alt text 

Ph.D. candidate,
PSI, ESAT,
KU Leuven,
Belgium
E-mail: bwan@esat.kuleuven.be

About me

I am currently a last year Ph.D. student supervised by Prof. Tinne Tuytelaars at KU Leuven, Belgium. Before that, I received the B.S. degree from the Beijing University of Posts and Telecommunications, in 2017, and the M.S. degree from ShanghaiTech University, in 2020. I also obtained a double bachelor's degree in Economics from Peking University in 2017. Currently, my main research interests focus on machine learning, especially on:

  • Vision-Language Pretraining and Understanding

  • Unsupervised and Weakly-supervised Learning

  • Text to Image and Video Generation

Internship

Student Researcher @ DeepMind, 7.2023-12.2023

  • Work on large-scale location-aware vision-language pretraining.

Student Researcher @ Google Brain, 10.2022-2.2023

  • Explore a encoder-decoder trasnformer structure for vision-language multitasking.

Research Intern @ Tencent AI Lab, 08.2020-10.2020

  • Concentrate on human-centric video understanding.

Algorithm Intern @ Microsoft, 03.2017-06.2017

  • Develop algorithms for Bing Search Question Answering system in Chinese.

Publications

  • B. Wan, M. Tschannen, Y. Xian, F. Pavetic, I. Alabdulmohsin, X. Wang, A.S. Pinto, A. Steiner, L. Beyer, X. Zhai, "LocCa: Visual Pretraining with Location-aware Captioners", Arxiv, 2024. [pdf]

  • M. Li*, B. Wan*, S. Moens, T. Tuytelaars, "Animate Your Motion: Turning Still Images into Dynamic Videos", Arxiv, 2024. [pdf]

  • H. Diao, B. Wan, Y. Zhang, X. Jia, H. Lu, L. Chen, "UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory Exploitation", CVPR, 2024. [pdf]

  • B. Wan, T. Tuytelaars, "Exploiting CLIP for Zero-shot HOI Detection Requires Knowledge Distillation at Multiple Levels", WACV, 2024. [pdf]

  • B. Wan*, Y. Liu*, D. Zhou, T. Tuytelaars, X. He, "Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning", ICLR, 2023. [pdf]

  • L. Beyer*, B. Wan*, G. Madan*, F. Pavetic*, A. Steiner*, A. Kolesnikov, A.S. Pinto, E. Bugliarello, X. Wang, Q. Yu, L. Chen, X. Zhai*, "A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision", Arxiv, 2023. [pdf]

  • B. Wan, W. Han, Z. Zheng, and T. Tuytelaars, "Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling", ICLR Oral, 2022. [pdf]

  • Y. Liu*, B. Wan*, L. Ma, and X. He, "Relation-aware Instance Refinement for Weakly Supervised Visual Grounding", CVPR, 2021. [pdf][code]

  • R. Li, S. Zhang, B. Wan, and X. He, "Bipartite graph network with adaptive message passing for unbiased scene graph generation", CVPR, 2021. [pdf][code]

  • Q. He, D. Zhou, B. Wan, and X. He, "Single Image 3D Object Estimation with Primitive Graph Networks", ACMMM, 2021. [pdf]

  • Y. Liu*, B. Wan*, L. Ma, and X. He, "Learning cross-modal context graph for visual grounding", AAAI, 2020. [pdf][code]

  • B. Wan*, D. Zhou*, Y. Liu, R. Li, and X. He, "Pose-aware multi-level feature network for human object interaction detection", ICCV Oral, 2019. [pdf][code]

Note: * indicates equal contribution. Full list of publications in Google Scholar.

Academic service

Reviewer for TPAMI, ICML, ICLR, NeurIPS, CVPR, ICCV, ECCV, WACV, ICIP