User profiles for Seung-Ik Lee
Seung-Ik LeeElectronics and Telecommunications Research Institute Verified email at etri.re.kr Cited by 1706 |
Generative cooperative learning for unsupervised video anomaly detection
Video anomaly detection is well investigated in weakly supervised and one-class classification
(OCC) settings. However, unsupervised video anomaly detection is quite sparse, likely …
(OCC) settings. However, unsupervised video anomaly detection is quite sparse, likely …
Old is gold: Redefining the adversarially learned one-class classifier training paradigm
A popular method for anomaly detection is to use the generator of an adversarial network to
formulate anomaly score over reconstruction loss of input. Due to the rare occurrence of …
formulate anomaly score over reconstruction loss of input. Due to the rare occurrence of …
Small object detection using context and attention
There are many limitations applying object detection algorithm on various environments.
Specifically, detecting small objects is still challenging because they have low-resolution and …
Specifically, detecting small objects is still challenging because they have low-resolution and …
Claws: Clustering assisted weakly supervised learning with normalcy suppression for anomalous event detection
Learning to detect real-world anomalous events through video-level labels is a challenging
task due to the rare occurrence of anomalies as well as noise in the labels. In this work, we …
task due to the rare occurrence of anomalies as well as noise in the labels. In this work, we …
OPRoS: A New Component‐Based Robot Software Platform
…, SI Lee, SW Jung, B Song, R Kim, S Kim, CH Lee - ETRI …, 2010 - Wiley Online Library
… Seung-Ik Lee received his MS and PhD in computer science from Yonsei University,
Seoul, Korea, in 1997 and 2001, respectively. He is currently working for ETRI, Korea. He has …
Seoul, Korea, in 1997 and 2001, respectively. He is currently working for ETRI, Korea. He has …
A self-reasoning framework for anomaly detection using video-level labels
Anomalous event detection in surveillance videos is a challenging and practical research
problem among image and video processing community. Compared to the frame-level …
problem among image and video processing community. Compared to the frame-level …
Cp-decomposition with tensor power method for convolutional neural networks compression
Convolutional Neural Networks (CNNs) has shown a great success in many areas including
complex image classification tasks. However, they need a lot of memory and computational …
complex image classification tasks. However, they need a lot of memory and computational …
Synthetic temporal anomaly guided end-to-end video anomaly detection
Due to the limited availability of anomaly examples, video anomaly detection is often seen as
one-class classification (OCC) problem. A popular way to tackle this problem is by utilizing …
one-class classification (OCC) problem. A popular way to tackle this problem is by utilizing …
High-resolution CT findings of varicella-zoster pneumonia.
JS Kim, CW Ryu, SI Lee, DW Sung… - AJR. American journal …, 1999 - Am Roentgen Ray Soc
OBJECTIVE: The purpose of this study is to describe the high-resolution CT findings of
varicella-zoster pneumonia in three immunocompetent patients. CONCLUSION: High-resolution …
varicella-zoster pneumonia in three immunocompetent patients. CONCLUSION: High-resolution …
Smoothmix: a simple yet effective data augmentation to train robust classifiers
Data augmentation has been proven effective which, by preventing overfitting, can not only
enhances the performance of a deep neural network but also leads to a better generalization …
enhances the performance of a deep neural network but also leads to a better generalization …