Hongtian Yu

Ph.D. candidate


University of Chinese Academy of Sciences, Academy-2 Building, Room 332
No.1 Yanqihu East Rd, Huairou District, Beijing, China, 101408

Email: yuhongtian17@mails.ucas.ac.cn
Github: https://github.com/yuhongtian17
Google Scholar: https://scholar.google.com/citations?user=J80W2-QAAAAJ

Biography

I am a Ph.D. candidate of Learning and Machine Perception Laboratory (LAMP) in School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, advised by Prof. Qixiang Ye and PostDoc. Yunfan Liu. From September 2024 to present, I am also studying at Zhongguancun Academy under the National Artificial Intelligence Program at the same time. I received my B.E. degree in University of Chinese Academy of Sciences in June 2021.

My research interests include object detection and representation learning in Computer Vision field, and I am currently working on AI for high-energy physics.

Publications

Spatial Transform Decoupling for Oriented Object Detection
Hongtian Yu, Yunjie Tian, Qixiang Ye, Yunfan Liu
The 38th Annual AAAI Conference on Artificial Intelligence, 2024
[paper] [arXiv] [code]
VMamba: Visual State Space Model
Yue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu, Lingxi Xie, Yaowei Wang, Qixiang Ye, Yunfan Liu
[arXiv] [code]
[usage example in Oriented Object Detection]
vHeat: Building Vision Models upon Heat Conduction
Zhaozhi Wang, Yue Liu, Yunfan Liu, Hongtian Yu, Yaowei Wang, Qixiang Ye, Yunjie Tian
[arXiv] [code]
Vision Calorimeter: Migrating Visual Object Detector to High-energy Particle Images
Hongtian Yu, Yangu Li, Yunfan Liu, Yunxuan Song, Xiaorui Lyu, Qixiang Ye
[arXiv] [code]