PLUS Group @ ShanghaiTech

Perception, Learning and UnderStanding (PLUS): The research of our group is primarily focused on representation learning, including weakly-supervised learning and model generalization under small samples and/or multiple tasks, and complex reasoning for multimodal structured data in visual perception, natural language and bioinformatics.

PLUS Group @ ShanghaiTech

Perception, Learning and UnderStanding (PLUS): The research of our group is primarily focused on representation learning, including weakly-supervised learning and model generalization under small samples and/or multiple tasks, and complex reasoning for multimodal structured data in visual perception, natural language and bioinformatics.

PLUS Group @ ShanghaiTech

Perception, Learning and UnderStanding (PLUS): The research of our group is primarily focused on representation learning, including weakly-supervised learning and model generalization under small samples and/or multiple tasks, and complex reasoning for multimodal structured data in visual perception, natural language and bioinformatics.

Previous Next

Join PLUS

🚩 We are recruiting undergrad students in SIST as Research Assistant for our projects. Click for more information.

🚩 Our group is also recruiting top-caliber graduate students with strong expertise in computer vision and machine learning for 2023. Please send email to Prof. Xuming He for more information after registering your application on the school website.

News

📌 [06/2022] One paper accepted by ECCV 2022!

📌 [05/2022] One paper accepted by KDD 2022!

📌 [04/2022] One paper accepted by NAACL 2022!

📌 [03/2022] Two papers accepted by CVPR 2022!

📌 [02/2022] One paper accepted by ISBI 2022!

📌 [09/2021] One paper accepted by NeurIPS 2021!

Recent Publications

Quickly discover relevant content by filtering publications.

ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning

We propose Curriculum-Guided Bayesian Reinforcement Learning for ROI-Constrained Bidding, which obtains superior in-distribution and out-of-distribution generalization, learning efficiency and stability.
Haozhe Wang, Chao Du, Panyan Fang, Shuo Yuan, Xuming He, Liang Wang, Bo Zheng
In KDD 22.
PDF Code

KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation

Self-supervised vision-and-language pretraining (VLP) aims to learn transferable multi-modal representations from large-scale …
Yongfei Liu, Shao-yen Tseng, Chenfei Wu, Vasudev Lal, Xuming He, Nan Duan
In Findings of NAACL 2022.
PDF
KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation

General Incremental Learning with Domain-aware Categorical Representations

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum.
Jiangwei Xie, Shipeng Yan, Xuming He
In CVPR 2022.
PDF
General Incremental Learning with Domain-aware Categorical Representations
See all publications

Gallery

Contact

  • 201210 Shanghai Pudong Zhangjiang Campus:393 Middle Huaxia Road
  • SIST Building No.1 and take the stairs to Office 311 on Floor 3