activity
20202022
most citedLearning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition

3 citations · 4 across the 7 of their papers we have counts for

collaborators

9 papers

cs.CV2022

Occluded Person Re-Identification via Relational Adaptive Feature Correction Learning

Minjung Kim, MyeongAh Cho, Heansung Lee +2

Occluded person re-identification (Re-ID) in images captured by multiple cameras is challenging because the target person is occluded by pedestrians or objects, especially in crowd…

cs.CV2022

RandomSEMO: Normality Learning Of Moving Objects For Video Anomaly Detection

Chaewon Park, Minhyeok Lee, MyeongAh Cho +1

Recent anomaly detection algorithms have shown powerful performance by adopting frame predicting autoencoders. However, these methods face two challenging circumstances. First, the…

cs.CV2021

Saliency Detection via Global Context Enhanced Feature Fusion and Edge Weighted Loss

Chaewon Park, Minhyeok Lee, MyeongAh Cho +1

UNet-based methods have shown outstanding performance in salient object detection (SOD), but are problematic in two aspects. 1) Indiscriminately integrating the encoder feature, wh…

cs.CV2021

FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation

Chaewon Park, MyeongAh Cho, Minhyeok Lee +1

Video anomaly detection has gained significant attention due to the increasing requirements of automatic monitoring for surveillance videos. Especially, the prediction based approa…

cs.CV20211 cited

A NIR-to-VIS face recognition via part adaptive and relation attention module

Rushuang Xu, MyeongAh Cho, Sangyoun Lee

In the face recognition application scenario, we need to process facial images captured in various conditions, such as at night by near-infrared (NIR) surveillance cameras. The ill…

cs.CV2020

Multi-object tracking with self-supervised associating network

Tae-young Chung, Heansung Lee, Myeong Ah Cho +2

Multi-Object Tracking (MOT) is the task that has a lot of potential for development, and there are still many problems to be solved. In the traditional tracking by detection paradi…