Hyungtae Lee

I am a research scientist and federal employee at DEVCOM Army Research Laboratory.

I received my PhD from University of Maryland, where I was supervised by Prof. Larry S. Davis. I received my MS from KAIST under the supervision of HyunWook Park and my BS from Sogang University.

Email / CV / Google Scholar / Github

Research Interests

I'm interested in the fields of computer vision and machine learning, including but not limited to the development of recognition approaches in various tasks such as 2D/3D object detection, segmentation, human pose estimation, hyperspectral image classification, etc. Currently, I am very interested in studying how to leverage virtual images in model training based on domain adaptation, transfer learning, and generative AI, etc.

Selected Publications

	Progressive Transformation Learning for Leveraging Virtual Images in Training Yi-Ting Shen, Hyungtae Lee, Heesung Kwon, Shuvra S. Bhattacharyya (* indicates equal contribution) CVPR, 2023 (Highlight) PDF
	Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification Hyungtae Lee, Sungmin Eum, Heesung Kwon ECCV, 2022 PDF · Supple · Code
	Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification Hyungtae Lee, Sungmin Eum, Heesung Kwon IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2022 PDF
	Self-supervised Contrastive Learning for Cross-domain Hyperspectral Image Representation Hyungtae Lee, Heesung Kwon ICASSP, 2022 PDF
	DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors Hyungtae Lee, Heesung Kwon IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 (An extension of WACV 2016 paper) PDF
	Generating Hard Examples for Pixel-wise Classification Hyungtae Lee, Heesung Kwon, Wonkook Kim IEEE Journals of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 2021 PDF
	S-DOD-CNN: Doubly Injecting Spatially-Preserved Object Information for Event Recognition Hyungtae Lee, Sungmin Eum, Heesung Kwon ICASSP, 2020 PDF
	ME R-CNN: Multi-Expert R-CNN for Object Detection Hyungtae Lee, Sungmin Eum, Heesung Kwon IEEE Transactions on Image Processing (TIP), 2020 PDF
	DOD-CNN: Doubly Injecting Spatially-Preserved Object Information for Event Recognition Hyungtae Lee, Sungmin Eum, Heesung Kwon ICASSP, 2019 PDF
	Exploitation of Semantic Keywords for Malicious Event Classification Hyungtae Lee, Sungmin Eum, Joel Levis, Heesung Kwon, James Michaelis, Michael Kolodny ( indicates equal contribution) ICASSP, 2018 PDF
	Going deeper with contextual CNN for hyperspectral image classification Hyungtae Lee, Heesung Kwon IEEE Transactions on Image Processing (TIP), 2017 PDF
	IOD-CNN: Integrating Object Detection Networks for Event Recognition Sungmin Eum, Hyungtae Lee, Sungmin Eum, Heesung Kwon, David Doermann ( indicates equal contribution) ICIP, 2017 PDF
	Enhanced Object Detection via Fusion with Prior Beliefs from Image Classification Yilun Cao, Hyungtae Lee, Heesung Kwon (* indicates equal contribution) ICIP, 2017 PDF
	Deep heterogeneous face recognition networks based on cross-modal distillation and an equitable distance metric Chris Reale, Hyungtae Lee, Heesung Kwon CVPR Workshops, 2017 PDF
	Weakly Supervised Localization Using Deep Feature Maps Archith J. Bency, Heesung Kwon, Hyungtae Lee, S. Karthikeyan, B. S. Manjunath ECCV, 2016 PDF
	Task-Conversions for Integrating Human and Machine Perception in a Unified Task Hyungtae Lee, Heesung Kwon, Ryan M. Robinson, Daniel Donavanik, William D. Nothwang, Amar R. Marathe IROS, 2016 PDF
	DTM: Deformable template matching Hyungtae Lee, Heesung Kwon, Ryan M. Robinson, William D. Nothwang, Amar R. Marathe ICASSP, 2016 PDF
	Dynamic Belief Fusion for Object Detection Hyungtae Lee, Heesung Kwon, Ryan M. Robinson, William D. Nothwang, Amar R. Marathe WACV, 2016 PDF
	Human-Autonomy Sensor Fusion for Rapid Object Detection Ryan M. Robinson, Hyungtae Lee, Michael J. McCourt, Amar R. Marathe, Heesung Kwon, Chau Ton, William D. Nothwang IROS, 2015 PDF
	JH2R: Joint Homography Estimation for Highlight Removal Sungmin Eum, Hyungtae Lee, David Doermann BMVC, 2015 PDF · Abstract
	Clauselets: Leveraging Temporally Related Actions for Video Event Analysis Hyungtae Lee, Vlad I. Morariu, Larry S. Davis WACV, 2015 PDF
	Robust Pose Features for Action Recognition Hyungtae Lee, Vlad I. Morariu, Larry S. Davis CVPR Workshops, 2014 PDF
	Qualitative Pose Estimation by Discriminative Deformable Part Models Hyungtae Lee, Vlad I. Morariu, Larry S. Davis ACCV, 2012 PDF
	A Large-Scale Benchmark Dataset for Event Recognition in Surveillance Video Sangmin Oh, Anthony Hoogs, Amitha Perera, Naresh Cuntoor, Chia-Chih Chen, Jong Taek Lee, Saurajit Mukherjee, J.K. Aggarwal, Hyungtae Lee, Larry Davis, Eran Swears, Xioyang Wang, Qiang Ji, Kishore Reddy, Mubarak Shah, Carl Vondrick, Hamed Pirsiavash, Deva Ramanan, Jenny Yuen, Antonio Torralba, Bi Song, Anesco Fong, Amit Roy-Chowdhury, Mita Desai CVPR, 2011 PDF

Services

· Area Chair, Associate Editor, Guest Editor, or Senior Progream Committee
- AAAI 2022
- Remote Sensing (2 special issues)

· Reviewer or Program Committee
- Computer Vision Conferences: CVPR 2020~, ECCV 2020~, ICCV 2019~, WACV 2014, 21-2, ACCV 2020, BMVC 2022
- AI Conferences: NeurIPS 2016, 20~, ICLR 2021~, ICML 2021~, AAAI 2020-1
- Document Analysis Conference: ICDAR 2019
- IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
- IEEE Transactions on Image Processing (TIP)
- Transactions on Machine Learning Research (TMLR)
- IEEE Transactions on Cybernetics (TCYB)
- IEEE Transactions on Geoscience and Remote Sensing (TGARS)
- IEEE Transactions on Artifical Intelligence (TAI)
- IEEE Transactions on Aerospace and Electronic Systems (TAES)
- Computer Vision and Image Understanding (CVIU)
- IEEE Transactions on Geoscience and Remote Sensing Letters (GRSL)

Scholarship, Award, and Honorship

- Selected as one of top 10 army technologies (ME R-CNN), 2020
- National scholarship, KAIST, 2006-8
- Summa Cum Laude, Sogang University, 2006
- 6 times academic scholarships, Sogang University, 1999-2006

Text alignment

Source code credit to Dr. Jon Barron