Keji He 何科技

Assistant Professor

School of Artificial Intelligence
Shandong University

Email: keji.he@sdu.edu.cn

News

2024.12, One paper was published on NeurIPS 2024.
2024.06, We won the CVPR2024 NTIRE Challenge on Efficient Super-Resolution competition (2 champions) and the related paper has been accepted by the CVPR2024 NTIRE.

Biography

Dr. Keji He is an assistant professor at the School of Artificial Intelligence, Shandong University (SDU). He finished his PhD at the Institute of Automation, Chinese Academy of Sciences, supervised by Prof. Liang Wang (IEEE Fellow) and Prof. Yan Huang. He is also a jointly PhD at the National University of Singapore (NUS), supervised by Prof. Xinchao Wang.

His research interests include vision-and-language understanding, generative AI, and embodied AI.

Join Us

I am actively seeking self-motivated Master students(MSC)/Research Assistants(RA) in AI.
The research topics mainly include but are not limited to the following:

Vision-and-Language Understanding
Embodied AI
Multimodal Large Language Model
Large Language Model
AI Safety

If you’re interested, please feel free to reach out via email (keji.he@sdu.edu.cn) with your curriculum vitae. [英雄不问出处].

Selected Publications

Keji He*, Kehan Chen*, Jiawang Bai, Yan Huang, Qi Wu, Shu-Tao Xia, and Liang Wang, Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor, Neural Information Processing Systems (NeurIPS), 2024. PDF
Keji He, Ya Jing, Yan Huang, Zhihe Lu, Dong An, and Liang Wang, Memory-Adaptive Vision-and-Language Navigation, Pattern Recognition (PR), 2024. PDF
Dong An, Hanqing Wang, Wenguan Wang, Zun Wang, Yan Huang, Keji He, and Liang Wang, Etpnav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments, IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2024. PDF
Keji He, Chenyang Si, Zhihe Lu, Yan Huang, Liang Wang, and Xinchao Wang, Frequency-Enhanced Data Augmentation for Vision-and-Language Navigation, Neural Information Processing Systems (NeurIPS), 2023. PDF
Keji He, Yan Huang, Qi Wu, Jianhua Yang, Dong An, Shuanglin Sima, and Liang Wang, Landmark-Rxr: Solving Vision-and-Language Navigation with Fine-Grained Alignment Supervision, Neural Information Processing Systems (NeurIPS), 2021. PDF

Competitions

CVPR2024 New Trends in Image Restoration and Enhancement workshop and associated challenges (NTIRE). Our team (Hongyuan Yu, Wan Cheng, Yuxin Hong, Binnan Han, Zhuoyuan Wu, Yajun Zou, Yuqing Liu, Jizhe Li, Keji He, Chao Fan, Heng Zhang, Xiaolin Zhang, Xuanwu Yin, Kunlong Zuo) is the champion of Efficient Super-Resolution competition (Main-Track and Runtime). See details here: Results.

1st Learning and Mining with Noisy Labels Challenge. Our team (Weichen Yu, Hongyuan Yu, Yan Huang, Dong An, Keji He, Zhipeng Zhang, Xiuchuan Li, Liang Wang) is the runner-up of task 1-1 and 2nd runner-up of task 1-2. See details here: Results.

Professional Activities

Chair, IEEE Student Branch, University of Chinese Academy of Sciences (2021-2022)
Reviewer, CVPR, ICCV, NeurIPS, ICML, ICLR, AAAI, ACM MM, PR, TMM, TCSVT, etc