Ji Woo Hong

Mr. Ji Woo Hong

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
29 October 2022
Verified
Book Chapter
Closed access
PDF file
SYSunjae Yoon
Sunjae Yoon
JHJi Woo Hong
Ji Woo Hong
EYEunseop Yoon
Eunseop Yoon
DKDahyun Kim
Dahyun Kim
JKJunyeong Kim
Junyeong Kim
CYChang D. Yoo
Chang D. Yoo

21 November 2024
Verified
Book Chapter
Closed access
PDF file
GKGwanhyeong Koo
Gwanhyeong Koo
SYSunjae Yoon
Sunjae Yoon
JHJi Woo Hong
Ji Woo Hong
CYChang D. Yoo
Chang D. Yoo

19 October 2023 in IEEE Access
Verified
Journal Article
Open access
TPTrung Pham
Trung Pham
ANAxi Niu
Axi Niu
KZKang Zhang
Kang Zhang
TJTee Joshua Tian Jin
Tee Joshua Tian Jin
JHJi Woo Hong
Ji Woo Hong
CYChang D. Yoo
Chang D. Yoo
Self-supervised learning (SSL) has emerged as a promising approach for learning representations from unlabeled data. Momentum-based contrastive frameworks such as MoCo-v3 have shown remarkable success among the many SSL methods proposed in recent years. However, a significant gap in encoder representation exists between the online encoder (student) and the momentum encoder (teacher) in these frameworks, limiting the performance on downstream tasks. We identify this gap as a bottleneck often overlooked in existing frameworks and propose “residual momentum” that explicitly reduces the gap during training to encourage the student to learn representations closer to the teacher’s. We also reveal that a similar technique, knowledge distillation (KD), to reduce the distribution gap with cross-entropy-based loss in supervised learning is useless in the SSL context and demonstrate that the intra-representation gap measured by cosine similarity is crucial for EMA-based SSLs. Extensive experiments on different benchmark datasets and architectures demonstrate the superiority of our method compared to state-of-the-art contrastive learning baselines. Specifically, our method outperforms MoCo-v3 0.7% top-1 in ImageNet, 2.82% on CIFAR-100, 1.8% AP, and 3.0% AP75 on VOC detection pre-trained on the COCO dataset; it also improves DenseCL with 0.5% AP (800ep) and 0.6% AP75 (1600ep). Our work highlights the importance of reducing the teacher-student intra-gap in momentum-based contrastive learning frameworks and provides a practical solution for improving the quality of learned representations.

27 April 2023 in IEEE Access
Verified
Journal Article
Open access
JHJi Woo Hong
Ji Woo Hong
SYSunjae Yoon
Sunjae Yoon
JKJunyeong Kim
Junyeong Kim
CYChang D. Yoo
Chang D. Yoo
3D human pose and shape estimation (3D-HPSE) from video aims to generate sequence of 3D mesh that depict human body in the video. Current deep learning based 3D-HPSE networks that takes video input have focused on improving temporal consistency among sequence of 3D joints by supervising acceleration error between predicted and ground-truth human motion. However, these methods overlooked the geometric misalignments of persistent discrepancy between geometric paths drawn by sequence of predicted joints and that of ground-truth joints. To this end, we propose Joint Path Alignment (JPA) framework, a model-agnostic approach that mitigates geometric misalignments by introducing Temporal Procrustes Alignment Regularization (TPAR) loss that performs group-wise sequence learning of joint movement paths. Unlike previous methods that rely solely on per-frame supervision for accuracy, our framework adds sequence-level accuracy supervision with TPAR loss by performing Procrustes analysis on the geometric paths drawn by sequences of predicted joints. Our experiments show that JPA framework advances the network to exceed the previous state-of-the-art performances on benchmark datasets in both per-frame accuracy and video smoothness metric.

27 November 2024
Verified
Book Chapter
Closed access
PDF file
SYSunjae Yoon
Sunjae Yoon
GKGwanhyeong Koo
Gwanhyeong Koo
JHJi Woo Hong
Ji Woo Hong
CYChang D. Yoo
Chang D. Yoo

24 August 2022 in Sensors
Verified
Journal Article
Open access
PDF file
SYSunjae Yoon
Sunjae Yoon
DKDahyun Kim
Dahyun Kim
JHJi Woo Hong
Ji Woo Hong
JKJunyeong Kim
Junyeong Kim
CYChang D. Yoo
Chang D. Yoo
This paper considers a Deep Convolutional Neural Network (DCNN) with an attention mechanism referred to as Dual-Scale Doppler Attention (DSDA) for human identification given a micro-Doppler (MD) signature induced as input. The MD signature includes unique gait characteristics by different sized body parts moving, as arms and legs move rapidly, while the torso moves slowly. Each person is identified based on his/her unique gait characteristic in the MD signature. DSDA provides attention at different time-frequency resolutions to cater to different MD components composed of both fast-varying and steady. Through this, DSDA can capture the unique gait characteristic of each person used for human identification. We demonstrate the validity of DSDA on a recently published benchmark dataset, IDRad. The empirical results show that the proposed DSDA outperforms previous methods, using a qualitative analysis interpretability on MD signatures.