Jinbin Bai

"Do not go gentle into that good night,
Old age should burn and rave at close of day;
Rage, rage against the dying of the light."

This is Jinbin Bai, a research intern in TikTok (ByteDance Intelligent Creation).

I have research experience in self-supervised learning, video representation, video-language pre-training and image translation. In the future, I am interested in solving the modality gap problem, and I'm also interested in text-guided image generation and video generation.

I received the B.S. degree from Department of Computer Science, Nanjing University in 2021.

I am looking for a Ph.D. position starting in 2023 fall or 2024 fall (Spring is also available).

Email / Linkedin / Github / CV / v2

News

[03/2021] Awarded as an outstanding graduate of Nanjing University.

Professional Services

Reviewer: ECCV 2022

Publications

Mind the Gap! Bidirectional Generation Between Image and Text with Few-shot Learning
Jinbin Bai, et al.
Technical Report, 2022 (under review)
[Paper][Code]
A lightweight image and text bidirectional generation framework.

LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval
Jinbin Bai, Chunhui Liu, Feiyue Ni, Haofan Wang, Mengying Hu, Xiaofeng Guo, Lele Cheng
Technical Report, 2022 (under review)
[Paper][Code]
A novel latent translation framework for solving the modality gap problems.

Semantic-aware Cartoon Style Transfer
Jinbin Bai
Technical Report, 2021
[Paper][Code]
A new semantic-aware framework by matching the same semantic regions for cartoon style transfer.

Classification of Acoustic Scenes Using Convolutional Neural Networks
Jinbin Bai, Yuwei Hu, Shihan Huang, Zhenyu Chen
Technical Report, 2020
[Paper]
We predict acoustic scenes that are provoked by audios. Our techniques include MFCCs acoustic feature extraction and convolutional nerual networks.

Honors & Awards

2021: Outstanding Graduate, Nanjing University
2020: Shanyuan Overseas Exchange Scholarship (Top 1%, 20 recipients in Nanjing Univeristy), Nanjing University
2019: National Excellent Undergraduate Innovation Project, Ministry of Education of P.R.China.
2019: National Scholarship for Encouragement, Ministry of Education of P.R.China.
2019: Yangzhou Scholarship, Nanjing University
2019: Peer Mentor, Nanjing University
2019: Outstanding Student, Nanjing University
2018: Heren Scholarship (Top 1%, 2 recipients in CS department), Nanjing University

Courses I've taken

Computer Vision: Representation and Recognition, Limin Wang (including my homework implementation)
Online Courses
- Deep Learning Specialization, Andrew Ng
- Deep Neural Networks with PyTorch, IBM
- CS231n: Convolutional Neural Networks for Visual Recognition, Stanford University
- Generative Adversarial Network, Hung-yi Lee
Nanjing University's Courses (Some course links are in Chinese)
- Principles and Techniques of Compilers, Chang Xu (including my homework and compiler implementation)
- Probability Theory and Statistics, Wei Gao
- Game Theory, Wei Gao
- Machine Learning, Han-Jia Ye and Zhi-Hua Zhou (including my homework implementation)
- Pattern Recognition and Computer Vision, Jianxin Wu
- Data Mining, Ming Li (including my homework implementation)
- Digital Image Processing, Lijun Zhang (including my homework implementation)
- AI Programming (Python), Li Zhang (including my homework implementation)
- Big Data Parallel Processing with MapReduce, Rong Gu (including my homework implementation)

Hobbies

I like reading the Sci-Fi, playing the piano, traveling and exploring the world. I also have a board interest in PC games and I was addicted to Pal3, QQ Speed and Mabinogi.

Friends

Zhimeng Guo, CS PhD@Pennsylvania State University

Last updated on Nov. 2021