MyeongAh Cho

MyeongAh Cho

Auto-generated profile, based on publicly available information

MyeongAh Cho

Kyung Hee University

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 April 2022 in Pattern Recognition
Verified
Journal Article
Closed access
MCMyeongAh Cho
MyeongAh Cho
TKTaeoh Kim
Taeoh Kim
woo jin kimwoo jin kim
woo jin kim
SCSuhwan Cho
Suhwan Cho
SLSangyoun Lee
Sangyoun Lee

31 July 2020 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
MCMyeongAh Cho
MyeongAh Cho
TKTaeoh Kim
Taeoh Kim
Ig-Jae KimIg-Jae Kim
Ig-Jae Kim
Kyungjae LeeKyungjae Lee
Kyungjae Lee
SLSangyoun Lee
Sangyoun Lee
Heterogeneous Face Recognition (HFR) is a task that matches faces across two different domains such as visible light (VIS), near-infrared (NIR), or the sketch domain. Due to the lack of databases, HFR methods usually exploit the pre-trained features on a large-scale visual database that contain general facial information. However, these pre-trained features cause performance degradation due to the texture discrepancy with the visual domain. With this motivation, we propose a graph-structured module called Relational Graph Module (RGM) that extracts global relational information in addition to general facial features. Because each identity's relational information between intra-facial parts is similar in any modality, the modeling relationship between features can help cross-domain matching. Through the RGM, relation propagation diminishes texture dependency without losing its advantages from the pre-trained features. Furthermore, the RGM captures global facial geometrics from locally correlated convolutional features to identify long-range relationships. In addition, we propose a Node Attention Unit (NAU) that performs node-wise recalibration to concentrate on the more informative nodes arising from relation-based propagation. Furthermore, we suggest a novel conditional-margin loss function ($C$ -softmax) for the efficient projection learning of the embedding vector in HFR. The proposed method outperforms other state-of-the-art methods on five HFR databases. Furthermore, we demonstrate performance improvement on three backbones because our module can be plugged into any pre-trained face recognition backbone to overcome the limitations of a small HFR database.

10 August 2024 in Pattern Recognition
Verified
Journal Article
Closed access
CPChaewon Park
Chaewon Park
DKDonghyeong Kim
Donghyeong Kim
MCMyeongAh Cho
MyeongAh Cho
MKMinjung Kim
Minjung Kim
MLMinseok Lee
Minseok Lee
SLSangyoun Lee
Sangyoun Lee

1 January 2020
Verified
Book Chapter
Closed access
PDF file
TKTaeoh Kim
Taeoh Kim
HLHyeongmin Lee
Hyeongmin Lee
MCMyeongAh Cho
MyeongAh Cho
HLHo Seong Lee
Ho Seong Lee
DCDong Heon Cho
Dong Heon Cho
SLSangyoun Lee
Sangyoun Lee

24 May 2025 in Pattern Recognition
Verified
Journal Article
Closed access
MKMinjung Kim
Minjung Kim
MCMyeongAh Cho
MyeongAh Cho
HLHeanSung Lee
HeanSung Lee
SLSangyoun Lee
Sangyoun Lee

27 June 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
TCTae-Young Chung
Tae-Young Chung
MCMyeongAh Cho
MyeongAh Cho
HLHeanSung Lee
HeanSung Lee
SLSangyoun Lee
Sangyoun Lee
Multi-object tracking (MOT), which is crucial for computer vision and video processing, has immense potential for improvement. Traditional tracking-by-detection approaches include feature-based object re-identification methods that use trained features, but these methods suffer from a lack of suitable training data. In training datasets used for MOT, every object in a video sequence must have its own location and ID. However, assigning IDs to each object in every sequence is considerably labor-intensive, and hence current MOT datasets are unsuitable for training re-identification networks. To resolve this issue, this paper proposes a novel self-supervised learning method using several short videos that contain no human-added labels, based on the idea that each video is a set of temporally corresponding image frames. We then describe how to improve tracking performance using a re-identification network trained in a self-supervised manner. In addition, ablation studies were conducted in order to define the optimal parameters, such as number of clips, data augmentation, and appropriate matching algorithms. The proposed approach achieved competitive performance compared with current best-practice methods including supervised methods, achieving MOT accuracy = 62.0% and ID F1-score = 62.7% on the MOT17 benchmark.