Jonghwan Mun
|
M.S. & Ph.D. integrated course, Computer Vision Lab, POSTECH (Mar. 2014 – Feb. 2020)
B.S. School of Electrical and Computer Engineering, UNIST (Mar. 2010 – Feb. 2014)
Staff Engineer, Samsung Advanced Institute of Technology (Jun. 2024 – Current)
Research Scientist, Kakao Brain (Mar. 2020 – May 2024)
Research Intern, Snap Inc., Venice, California, USA (Jun. 2018 – Aug. 2018)
Honeybee: Locality-enhanced Projector for Multimodal LLM
|
Learning Pseudo-Labeler beyond Noun Concepts for Open-Vocabulary Object Detection
|
Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning
|
Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs
|
Stop or Forward: Dynamic Layer Skipping for Efficient Action Recognition
|
BaSSL: Boundary-aware Self-supervised Learning for Video Scene Segmentation
|
MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection
|
Winning the ICCV’2021 VALUE Challenge: Task-aware Ensemble and Transfer Learning with Visual Concepts
|
Local-Global Video-Text Interactions for Temporal Grounding
|
Towards Oracle Knowledge Distillation with Neural Architecture Search
|
Streamlined Dense Video Captioning |
Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
|
Learning to Specialize with Knowledge Distillation for Visual Question Answering |
Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization |
MarioQA: Answering Questions by Watching Gameplay
Video |
Text-guided Attention Model for Image Captioning
|
NICE Challenge, 3rd place, CVPR'2023 NICE Workshop
VALUE Challenge, 1st place at VALUE and QA phase, ICCV 2021'CLVL Workshop
Naver Ph.D. Fellowship, 2018
National Science and Technology Undergraduate Scholarship, Korea Student Aid Foundation, 2010 – 2013