About Me
Hi, my name is Gukyeong Kwon. I am a Senior Applied Scientist at Amazon Artificial General Intelligence (AGI). I completed M.S. and Ph.D. in School of Electrical and Computer Engineering at Georgia Tech in 2018 and 2021, respectively, under the supervision of Dr. Ghassan AlRegib. My research interests are broadly machine learning, computer vision, and image/video processing. Recently, I have primarily focused on multi-modal representation learning for vision and language.
Please check my CV and Google scholar profile for more information.
News:
- Nov. 29, 2023: Amazon Titan Multimodal Embeddings foundation model which I contributed is finally launched.
- Oct. 9, 2023: I am promoted to Senior Applied Scientist at Amazon.
- Jan. 20, 2023: One paper is accepted for publication at ICLR 2023.
- May 30, 2022: I receive a CSIP Outstanding Research Award in recognition of my Ph.D. research at Georgia Tech.
- Jan. 30, 2022: One paper is accepted for publication at IEEE Transactions on Image Processing.
- Jan. 11, 2021: I am joining Amazon Web Services (AWS) AI Labs as a full-time Applied Scientist.
- Oct. 28, 2020: Our paper received the Top Viewed Special Session Paper Award at ICIP 2020.
- Jul. 3, 2020: Our papers is accpeted for publication at ECCV 2020.
- May 15, 2020: Two papers are accpeted for publication at ICIP 2020.
- Sept. 24, 2019: Our paper won the Best Paper Award (top 0.1%) at the IEEE International Conference on Image Processing (ICIP) 2019.
- Apr. 30, 2019: Our paper is accepted for publication at ICIP 2019.
- May 4, 2018: Our paper is accepted for publication at ICIP 2018.
- Nov. 14, 2017: Our paper is accepted for publication at the 31st Conference on Neural Information Processing Systems (NIPS), Machine Learning for Intelligent Transportation Systems Workshop, 2017.
- Mar. 29, 2017: Our paper is selected as a Finalist of the World’s FIRST 10K Best Paper Award (top 3%) in the IEEE International Conference on Multimedia and Expo (ICME) 2017.
Experience
Amazon AGI
Senior Applied Scientist
October 2023 - Present
- Develop artificial general intelligence foundation models and services.
AWS AI Labs
Applied Scientist
January 2021 - October 2023
- Developed Amazon Titan Multimodal Embeddings foundation model which can perform accurate and contextually relevant vision language search.
- Contributed to the overall pipeline of large-scale model training including data preparation and processing, model training, and evaluation.
AWS AI Labs
Applied Scientist Intern
May 2020 - August 2020
- Conducted research on multimodal represenation learning for vision and language.
- Developed regularization techniques for two-stream BERT models and achieved improved performance in visual question answering, caption-based image retrieval, and referring expressions.
Panasonic Automotive
Deep Learning Research Intern
May 2018 - July 2018
- Developed deep learning-based algorithms for drivers’ misbehavior detection in autonomous vehicles.
- Focused on driver’s pose estimation and hand detection algorithms using Tensorflow and C++.
Georgia Tech
Graduate Research/Teaching Assistant
January 2016 - December 2020
- Developed algorithms to detect accident events occurring in driving scenes to ensure safe autonomous driving.
- Proposed abnormal object detection algorithms for autonomous vehicles.
- Introduced a large-scale traffic sign recognition dataset for robust visual understanding under challenging conditions.
- Developed a perceptual video quality assessment (VQA) metric which achieved the state-of-the-art performance in estimating the impact of visual distortions on human perception.
Publications
G. Kwon, Z. Cai, A. Ravichandran, E. Bas, R. Bhotika, and S. Soatto, “Masked Vision and Language Modeling for Multi-modal Representation Learning,” International Conference on Learning Representations (ICLR), 2023.
G. Kwon, M. Prabhushankar, D. Temel, and G. AIRegib, “Backpropagated Gradient Representations for Anomaly Detection,” In Proceedings of the European Conference on Computer Vision (ECCV), 2020.
G. Kwon*, M. Prabhushankar*, D. Temel, and G. AIRegib, “Distorted Representation Space Characterization Through Backpropagated Gradients,” 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, 2019, pp. 2651-2655. (* : equal contribution, Best Paper Award (top 0.1%))
M. A. Aabed, G. Kwon, G. AlRegib, “Power of tempospatially unified spectral density for perceptual video quality assessment,” 2017 IEEE International Conference on Multimedia and Expo (ICME), Hong Kong, 2017, pp. 1476-1481. (Finalist of the World’s FIRST 10K Best Paper Award (top 3%))