Chia-Wen Kuo (郭佳文)

Current Research Focus: Vision and Language; Knowledge Augmentation; Semi-Supervised Learning; Self-Supervised Learning; Zero-Shot Learning

Contact: albert.cwkuo[AT]

Chia-Wen Kuo (郭佳文) is currently a Ph.D. candidate at Georgia Tech specializing in deep learning for vision and language research. He joined RobotIcs Perception and Learning (RIPL) lab led by Dr. Zsolt Kira in 2017. His recent works center on how to efficiently and effectively leverage external knowledge for VL tasks. Additionally, he is interested in learning with less supervision including semi-supervised learning, self-supervised learning, and zero-shot learning. 

Prior to joining Georgia Tech, he worked with Dr. Yu-Chiang Frank Wang on 3D shape generation and pose estimation. Before that, he earned his Master's and Bachelor's degrees in Electrical Engineering at National Taiwan University.

🔥 Expected graduation date: Dec 2023. Actively looking for a research position in the industry. 🔥



HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning

[CVPR 2023] Chia-Wen Kuo and Zsolt Kira

We propose HAAV to efficiently and effectively leverage multiple sources of knowledge for image captioning.

[Paper] [GitHub] [Project] [Video]

Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image

[CVPR 2022] Chia-Wen Kuo and Zsolt Kira

We propose Xmodal-Ctx to incorporate text descriptions of the input image via CLIP cross-modal retrieval for image captioning.

[Paper] [GitHub] [Project] [Video]

Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigation

[WACV 2023] Chia-Wen Kuo, Chih-Yao Ma, Judy Hoffman, Zsolt Kira

We propose SEA to improve the visual representation through a series of self-supervised tasks for vision-and-language navigation.

[Paper] [GitHub] [Project]

Unbiased Teacher for Semi-Supervised Object Detection

[ICLR 2021] Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, Peter Vajda

We propose Unbiased Teacher using focal loss and teacher-student training to reduce the bias in pseudo-labeling for semi-supervised object detection.

[arXiv] / [GitHub] / [Project]

FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

[ECCV 2020] Chia-Wen Kuo, Chih-Yao Ma, Jia-Bin Huang, Zsolt Kira

We propose FeatMatch using feature-based augmentation for semi-supervised image classification.

[arXiv] / [GitHub] / [Project]

Who2com: Collaborative Perception via Learnable Handshake Communication

[ICRA 2020] Yen-Cheng Liu, Junjiao Tian, Chih-Yao Ma, Nathaniel Glaser, Chia-Wen Kuo, Zsolt Kira

[arXiv] / [Project]

Data-Efficient Graph Embedding Learning for PCB Component Detection

[WACV 2019] Chia-Wen Kuo, Jacob D. Ashmore, David Huggins, Zsolt Kira

We improve few-shot PCB component detection by leveraging the similarity relationship between detected components and component prototypes via graph neural network.

[arXiv] / [Project]

Research Experiences

Microsoft Research

Role: Research intern

Advisor: Chunyuan Li; Collaborator: Jianwei Yang

Project: Knowledge augmentation for large-scale pre-trained vision-and-language models.

Rekognition team @ Amazon AWS AI

Role: Applied scientist intern

Advisor: Yuting Zhang

Project: Leveraging cross-modal pre-trained models for vision-and-language tasks.

May '20 - Aug '20

Computer Vision team @ Facebook AI & Applied Research

Role: Research intern

Advisor: Zeki Yalniz

Project: Learned data augmentation for self-supervised learning.

Jan '17 – Aug '17

Research Center for Information Technology Innovation @ Academia Sinica

Role: Research assistant

Advisor: Yu-Chiang Frank Wang

Project: 3D object reconstruction and pose estimation via generative models.


Aug '17 - Present

Ph.D. @ Georgia Institute of Technology (Atlanta, USA)

Major: Robotics, working on computer vision and deep learning

Advisor: Dr. Zsolt Kira

Research interests: vision and language; learning with less supervision.

Sep '13 - Jun '15

M.S. @ National Taiwan University (Taipei, Taiwan)

Major: Electrical Engineering

Advisor: Prof. Ren C. Luo

Thesis title: Robot Integrated 3D Object Recognition and Fetching System for Factory Automation

Sep '09 - Jun '13

B.S. @ National Taiwan University (Taipei, Taiwan)

Major: Electrical Engineering