Fangjian Lin林方坚Education
Bachelor: North China Electric Power University, 2016-2020
Baidu Research (IDL), 2020.12-2021.12 |
|
I graduated from North China Electric Power University for my undergraduate degree and Xinjiang University for my master's degree (2016-2023). I have conducted research internships at Baidu Research, Shanghai AI Lab and Alibaba Group.
My research interests lie in the fields of deep learning, computer vision, and visual perception for autonomous driving. Specifically, I focus on 1) designing general-purpose models for various tasks (classification, detection, and segmentation); 2) developing multimodal architectures for large-scale models; and 3) exploring prompt engineering techniques.
[07/2023] A paper submitted to ACM MM was accepted.
[04/2023] A paper submitted to IEEE TCSVT was accepted.
[03/2023] A paper submitted to IJCAI 2023 received a score of 7764.
[03/2023] Completed my master's thesis.
[02/2023] A paper submitted to IEEE ICASSP 2023 was accepted.
Summary: ACM MM, ACCV, ICASSP, TCSVT.
*: Equal contributions.
2023
UniNeXt: Exploring A Unified Architecture for Vision Recognition
Fangjian Lin, Jianlong Yuan, Sitong Wu, Fan Wang, Zhibin Wang
Proceedings of the 31th ACM International Conference on Multimedia (ACM MM), Accepted, 2023.
[arXiv]
PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation
Yizhe Ma*, Fangjian Lin*, Sitong Wu, Shengwei Tian, Long Yu.
IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT).
[paper]
StructToken: Rethinking semantic segmentation with structural prior
Fangjian Lin, Zhanhao Liang, Sitong Wu, Junjun He, Kai Chen, Shengwei Tian.
IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT).
[paper]
[arXiv]
[code]
Exploring vision transformer layer choosing for semantic segmentation
Fangjian Lin, Yizhe Ma, Shengwei Tian.
IEEE International Conference on Acoustics, Speech, and Signal Processing (IEEE ICASSP), Accepted, 2023.
[arXiv]
[paper]
2022
Full-scale Selective Transformer for Semantic Segmentation
Fangjian Lin, Sitong Wu, Yizhe Ma, Shengwei Tian.
Proceedings of the Asian Conference on Computer Vision (ACCV).
[paper]
[supp]
AxWin Transformer: A Context-Aware Vision Transformer Backbone with Axial Windows
Fangjian Lin, Yizhe Ma, Sitong Wu, Long Yu, Shengwei Tian
Arxiv Tech Report, 2022.
[arXiv]
Cross-scale sampling transformer for semantic image segmentation
Yizhe Ma, Long Yu, Fangjian Lin, Shengwei Tian
Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2895-2907, 2023
[paper]
2021
Fully transformer networks for semantic image segmentation
Sitong Wu*, Tianyi Wu*, Fangjian Lin*, Shengwei Tian, Guodong Guo
Arxiv Tech Report, 2021.
[arXiv]