About me
Hi, everyone! My name is Jianfeng He.
I am a 5th-year Ph.D. student in the CS@Virginia Tech. I research on computer vision, natural language processing. For the natural language processing, I study on the uncertainty analysis in its applications (e.g., text classification, few-shot, named entity recognition, and text summarization). For the computer vision, I focus on guided image editing. In addition, I worked on cross-modal retrieval when I was a master student in the University of Chinese Academy of Sciences.
It is exciting to announce that I will join AWS as an Applied Scientist in June 2024.
My contact: jianfenghe@vt.edu
- Uncertainty Estimation
- Natural Language Processing
- Computer Vision
- Multi-modal
PhD in Computer Science, 2019.01-2024.05
Virginia Tech
First-semester PhD study, 2018.08-2018.12
University of Pittsburg
MSc in Computer Science, 2014.09-2017.07
University of Chinese Academy of Sciences
Visiting Student, 2015.07-2017.07
Institute of Computing Technology, Chinese Academy of Sciences
BSc in Digital Media Technology, 2010.09-2014.06
Central China Normal University
Skills
Image/Text Understanding/Generation
Python, Matlab, C++, Shell
PyTorch, Numpy, Linux1
Experience
Responsibilities include:
- Address semi-supervised dialogue summarization
- Quantify the uncertainty of generated dialogues
Responsibilities include:
- Address Zero-Shot Spoken Language Understanding
- Use audio-text pairs and text-semantics pairs to learn a spoken language processing
Responsibilities include:
- Pretrained Multimodal Chinese Dialogue Model
- Embedding the words, sentences and image in to the dialogue model