Jangho Kim

Education

(Sep 2017 ~) Ph.D. Student in Graduate School of Convergence Science and Technology, Seoul National University, Korea.

• Advisor: Prof. Nojun Kwak
• Machine Intelligence Pattern Analysis Lab.

Feb 2017, MSc, Computer Science and Engineering , Pohang University of Science and Technology, Korea.

• Advisor: Prof. Daijin Kim
• Intelligent Media Lab.

Feb 2015, BSc, Information and Communication Engineering, dongguk University, Korea.

Research Interests

• Artificial Intelligence
• Deep Learning
• Computer Vision

Publication

International Conferences

• Jangho Kim, Jeesoo Kim, and Nojun Kwak, "HC-Net: Memory-based Incremental Dual-Network System for Continual learning", arXiv, September 2018.
• Jangho Kim, SeoungUK Park, and Nojun Kwak, "Paraphrasing Complex Network: Network Compression via Factor Transfer", Thirty-second Conference on Neural Information Processing Systems (NIPS 2018) poster
• Jeesoo Kim, Jangho Kim, Jaeyoung Yoo, Deasik Kim and Nojun Kwak, "Vehicle Image Generation Going Well with The Surroundings", arXiv, July 2018.
• Jangho Kim, Yong-Joong Kim, Yonghyun Kim and Daijin Kim, "Detecting Korean characters in natural scenes by alphabet detection and agglomerative character construction", Systems, Man, and Cybernetics 2016 (SMC 2016) oral presentation

Domestic Conferences

• 김장호, 김용중, 김대진, "굴삭기의 Machine Guidance System과 착용 가능한 스마트기기 간 작업정보 전송을 위한 프로토콜과 Display 개발", 2015년 동계학술발표회

Projects

• Development of health information estimation algorithm using bio-signal and machine learning

funded by Samsung IM (Mobile Communication Business), 2019.01 ~ current

- Health care with Deep learning.

• Deep learning model compression using knowledge transfer

funded by Samsung DS (Semiconductor R&D Center), 2018.07 ~ current

- Knowledge transfer, Ensemble model.

• Development of transfer learning technology for improving traffic object detection performance

funded by Ministry of Science and ICT of Korea, 2018.05 ~ 2018.11

- Knowledge transfer.

• Development of Real-time Image Recognition Defense Big Data Platform ("D-Net")

funded by Agency for Defense Development, 2017.7 ~ 2018.11

- Deep Model compression.

• Development of Danger/Abnormal Situation Recognition and Prediction Technology for Intelligent systems

funded by the Ministry of Science and ICT of Korea, under the ICT Consilience Creative program, 2016.1 ~ 2016.12

- Car detection, license plate, text detection, and text recognition.

• KT-POSTECH Open R&D Development of Object Analysis Technology for Media Intelligence

funded by KT, 2016.1. ~ 2016.12.

- Abandoned and Removed Object Detection and English Text Detection methods.

• Development of Image Analysis Technology for General Product Recognition System

funded by Samsung DMC (R&D), 2015. 12. ~ 2016.12.

- Object Recognition method using deep convolutional neural networks to classify products and logos.

• Development of wearable display device technology to display information on efficient excavator work

funded by Doosan Infracore ,2015. 02.~ 2015. 11.

- Google glass application.