Hongchen Wei

I am currently a second-year Ph.D. student in School of Remote Sensing and Information Engineering from Wuhan University, under the supervision of Prof. Zhenzhong Chen.

I received my M.E. degree in School of Computer Science and Engineering from Nanjing University of Science and Technology, China, in 2023.

I received my B.Sc. degree in School of Materials Science and Engineering from Xi'an Shiyou University, China, in 2020.

Email  /  Google Scholar  /  Github

profile photo
Main Research Interests
  • Image/Video Captioning
  • Long Video Understanding
  • Spatial-Temporal Video Grounding
  • Large Multimodal Model
News
  • [2024-10] We propose the visual context window extension for long video understanding that enables the direct and easy scaling of pre-trained LMMs to 1024 frames, and significantly reducing memory usage.
Pre-prints
Visual Context Window Extension: A New Perspective for Long Video Understanding
Hongchen Wei, Zhenzhong Chen
arXiv Preprint, 2024
Project page
Improving Generalization of Image Captioning with Unsupervised Prompt Learning
Hongchen Wei, Zhenzhong Chen
arXiv Preprint, 2023
Publications
Exploiting Cross-Modal Prediction and Relation Consistency for Semisupervised Image Captioning
Yang Yang, Hongchen Wei , Hengshu Zhu, Dianhai Yu, Hui Xiong, Jian Yang
TCYB, 2022 (学生一作)
Code
S2OSC: A Holistic Semi-Supervised Approach for Open Set Classification
Yang Yang, Hongchen Wei , Zhenqiang Sun, Guangyu Li, Yuanchun Zhou, Hui Xiong, Jian Yang
TKDD, 2021 (学生一作)
Activities
  • Reviewer: ICLR25

Last updated in Jun. 2024.

Homepage credits: Jon Barron.