Yuxiang Lin

Yuxiang Lin

ECE@Georgia Tech


My name is Yuxiang Lin, pronounced as “You-shee-ahng Lin”. I am an MS student at Georgia Institute of Technology . I earned my B.S. degree from Shenzhen Technology University under supervision from Prof. Xiaojiang Peng. In 2023, I was a visiting student at the Shenzhen Institute of Advanced Technology (SIAT), CAS and a research intern with Prof. Chen Chen at UCF remotely. In 2024, I interned at Baidu Inc in the Group of Multimodal Retrieval, gaining experience in representation learning and big data.

Additionally, I volunteered as a Teaching Assistant for a Large Language Models/Computer Vision tutorial hosted by the Shanghai AI Laboratory .

You can find me at yuxiang.lin@gatech.edu or lin.yuxiang.contact@gmail.com.

My research interest mainly includes:

  • Foundation model: Representation Learning, Post-Pretraining, Contrastive Learning.
  • Multi-modal LLM: LLM Reasoning, LLM Application.
  • AI4Science: LLM with Medical Analysis.

🔥 News

  • 2024.07: One co-first author paper about invisible gas detection is accepted by CVIU (JCR Q1, CCF rank B). 🎉
  • 2024.03: One paper about Conversational Emotion-Cause Pair Analysis with LLM is accepted by SemEval 2024, NAACL.
  • 2024.01: I was awarded the First Prize of Research and Innovation Award (3000 CNY) and Star of Craftsmanship (3000 CNY).
  • 2023.08: My instance segmentation tutorial has been featured in MMYOLO v0.6.0 highlight! Check out the tutorial here to master the essentials of instance segmentation.
  • 2023.07: One paper on multimodal emotion recognition is accepted by ACM MM! 🎉
  • 2023.07: We are the runner up in the Grand Challenge (MER 2023) of ACM MM! 🥈

📝 Publications

📌 Pinned

CVIU
sym

Invisible Gas Detection: An RGB-Thermal Cross Attention Network and A New Benchmark

Jue Wang*, Yuxiang Lin*, Qi Zhao, Dong Luo, Shuaibao Chen, Wei Chen, Xiaojiang Peng (* denotes equal contribution)

CVIU (JCR Q1, CCF-B) | [Paper] [Code]

  • We design the RGB-Thermal Cross Attention Network for invisible gas detection, by effectively integrating texture information from RGB images and gas information from thermal images.
  • We propose the RGB-assisted Cross Attention Module and the Global Textual Attention Module for cross modality feature fusion and diverse contextual information extraction.
  • We introduce Gas-DB, the first comprehensive open-source gas detection database, including approximately 1.3K well-annotated RGB-thermal images for gas detection algorithms.
ACMMM 2023
sym

Semi-Supervised Multimodal Emotion Recognition with Expression MAE

Zebang Cheng, Yuxiang Lin, Zhaoru Chen, Xiang Li, Shuyi Mao, Fan Zhang, Daijun Ding, Bowen Zhang, Xiaojiang Peng

ACMMM 2023 (CCF-A) | [Paper] [Slides]

  • We propose expMAE (combined with MAE and VideoMAE) to build an impressive emotion recognition classifier.
  • We utilize multi-modal foundation model such as CLIP, MacBERT, and HuBERT to boost the ability of visual features from expMAE.
  • We use the semi-supervised method of pseudo-labeling to solve the skewed distribution of the training set and finally achieve rank 2th among all the participants.

👨‍💻 Experience

🏅 Selected Awards

  • 2020   Second Prize of SZTU Freshman Scholarship (6000 CNY)
  • 2022   China Undergraduate Mathematical Contest in Modeling, National Second Prize (top 2%)
  • 2023   Dahua Outstanding Scholarship (4000 CNY)
  • 2023   OpenMMLab MMSTAR I
  • 2024   First Prize of Research and Innovation Award (3000 CNY)
  • 2024   Star of Craftsmanship (3000 CNY)