Taegyeong Lee

Hello, I am a master's student in MVLLAB at Artificial Intelligence Graduate School (UNIST). I am fortunate to be advised by Taehwan Kim.

My main research areas are Generative Models and Multimodal Learning. I am specifically interested in novel research that generates images or videos from audio or text (various modalities). Just as humans can think and infer from various senses, I believe that the various modalities and generative models can have a significant impact on our community in the future. Also i am interested in Quantitative Trading on cryptocurrency market. Now, I am open to internships.

Email : taegyeonglee[at]unist[dot]ac[dot]kr

Business Email : apdo[at]apdoprivate[dot]com

Github, Google Scholar

• NEWS: Our paper for text-to-video generation was accepted to CVPR 2024. 

• NEWS: Our paper for sound-to-image generation was accepted to ICCV 2023.  

Education

• M.S in Artificial Intelligence Graduate School at Ulsan National Institute of Science and Technology (UNIST), Korea. (Aug 2022-present), Prof Taehwan Kim.

• HELP University, (English summer course, Jul 2021)

• B.S in Computer Engineering at Pukyong National University, Korea. / GPA : 4.17 / Rank 2/30 (Mar 2016- Aug 2022)

Experiences

• M.S student in MVLLAB, UNIST (Aug 2022-present) : Generative Models, Multimodal learning

• APDOPRIVATE CEO (Cryptocurrency Quantitative Trading Platform) (Mar 2021 - Present) : Quantitative trading

• Research Intern in Artificial Intelligence Lab, Pukyong National University (Oct 2021 - Aug 2022)

• Software Developer Soldier, Army Promotion Data Management Department (Mar 2019 - Oct 2021) : Oracle, VB6, C#

• Research Intern in ETRI, Busan. (Jan 2019 - Feb 2019) : Semi-supervised learning, Object Detection

• Intern in Incon, Busan (Sep 2018 - Dec 2018) : Amazon AI speaker software developer

• SW Maestro 8th Korea Ministry of Science and ICT (Jun 2017 - Dec 2017) : Object Detection, Computer Vision, Deep learning

International publications

• Taegyeong Lee*, Soyeong Kwon* and Taehwan Kim, Grid Diffusion Models for Text-to-Video Generation, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 [pdf][project page]

• Taegyeong Lee, Jeonghun Kang, Hyeonyu Kim and Taehwan Kim, Generating Realistic Images from In-the-wild Sounds, IEEE/CVF International Conference on Computer Vision (ICCV), 2023 [pdf][project page]

Domestic publications

• Taegyeong Lee, HyeRin Uhm, Chi Yoon Jeong and Chae-Kyu Kim, Generating Emotional Face Images using Audio Information for Sensory Substitution, JOURNAL OF KOREA MULTIMEDIA SOCIETY (KCI), 2023, Paper

• Taegyeong Lee, HyeRin Uhm, Chi Yoon Jeong and Chae-Kyu Kim, Audio-Guided Face Image Generation For Sensory Substitution, KOREA MULTIMEDIA SOCIETY Annual Academic Conference (Outstanding Paper Award), 2022

• Hyerin Uhm, Yehyeon Ahn, Seonguk Ju, Taegyeong Lee, Yun-Kyung Park, Kyeong-Deok Moon, Chae-Kyu Kim, Multi-modal Sensory Substitution Study Based on Image and Sound, KOREA MULTIMEDIA SOCIETY Annual Academic Conference, 2022

• GyuBin Park, HyeJin Seo,Taegyeong Lee, SuHwa Jo, YunKyung Park, KyeongDeok Moon, ChaeKyu Kim, A Study of Visual to Auditory Sensory Substitution using Music with Emotion, KOREA MULTIMEDIA SOCIETY Annual Academic Conference, 2022

• Taegyeong Lee, Gyubin Park, HyeJin Seo, Su-Hwa Jo, Bok-Deuk Song and Chae-Kyu Kim, An enhanced model of Face Reenactment and Transformation Models based on Head pose vector, KOREA MULTIMEDIA SOCIETY Annual Academic Conference (Artificial Intelligence Capstone Design Grand Award), 2021

• HyeJin Seo, Taegyeong Lee, Gyubin Park, Su-Hwa Jo,Bok-Deuk Song,Chae-Kyu Kim, A study on metadata of 3D spatial gesture recognition for realizing immersive interaction of interactive media, KOREA MULTIMEDIA SOCIETY Annual Academic Conference (Outstanding Paper Award), 2021