Yooseung Wang (왕유승)

Research Interests

My research interests lie in Artificial Intelligence, Computer Vision (CV) and Interdisciplinary Applications.

• Machine Perception : Segmentation [ICPR'20, SPL'21a, PRL'2a, PRL'23, PR'24, ACCESS'24], Detection [ICCAS'20, PRL'22b], EO/Lidar Sensor Fusion [TITS'22]

• Human Recognition  : Human Parsing [PR'24], Face Recognition [ACCESS'22], Group Action Recognition [under review in CVPR24]

• Data Minimization : Few-Shot Learning [SPL'21a], Zero-Shot Learning [PRL'22b], Semi-Supervised Learning [PRL'24, ACCESS'24]

• Network Minimization : Network Pruning [SPL'21b], Light-Weighted Network [ICPR'20, GRSL'21]

• Multimodal Learning : Prompt-based Learning [VCIP'23, ICASSP'24]

Education

• 2022.08 - Present        M.S., School of Electrical Engineering, KAIST, South Korea  

-Entered with the highest honors, GPA:4.25/4.3

    * Kwan-Jeong Lee Jong-Hwan Educational Foundation Scholarship (Top 1 in KAIST EE&CS&AI, MS & PhD) 

            * Kwon Young-Se Scholarship (Top 2 in KAIST EE, MS) 

• 2015.03 - 2019.02    B.S. School of Electrical and Computer Engineering, UNIST, South Korea

               * Valedictorian in ECE (Top 1 among 131 students), Summa Cum Laude 

Research Experience

• Agency for Defense Development (ADD), Defence Artificial Intelligence Center (DAIC), Research Officer, 현역연구원, 과학기술전문사관                   (2019.06 - 2022.05)

Projects: Autonomous car perception [J1, J2, J4, D1, D2, PT1, PT2] (News) / Occluded object detection [C1, J7, D3, D4, D5] / Face Recognition [J6]

25 students selected nationwide

• Electronics and Telecommunications Research Institute (ETRI),Visual Intelligence Lab, Undergraduate Researcher                                                (2018.06 - 2018.08)

• Satrec Initiative Analytics (SIA), Research Center, Image Processing Team, Research Intern                                                       (2018.12 - 2019.02, 2022.06 - 2022.08)

 3rd Place, SpaceNet 8 Challenge on CVPR2022 / Beat the winner on DeepGlobe Challenge on CVPR2018

Award

• • 2024, Graduate Presidential Science Scholarship 

  • 2023, Kwanjeong Educational Foundation Scholarship 

  • 2022, 3rd Place, SpaceNet 8 Challenge on CVPRW2022

  • 2022, Kwon Yeong-Se Scholarship 

  • 2021, 1st Place, AI Idea Competition for Brain Hemorrhage Diagnosis Track 

  • 2018, (Top 1%), NAVER CEO Award, Han-Ium ICT Competition    

  • 2016, Honorable Mention, ACM-ICPC Asia Daejeon Regional 

  • 2015, Honorable mention, Korean Super-Computing Challenge 

International Publications

first-authored papers : ACCESS24, PRL24, VCIP23, PRL22b, GRSL22, SPL21a, SPL21b, ICPR20 

co-authored papers : ICASSP24, PRL23, ACCESS23, T-ITS23, ICCAS20 

Under Reviews: CVPR24b, CVPR24a, PR24, ACCESS24, PRL24

2022-2024 (KAIST)

• • [C7] Group Activity Recognition Approach, 

S. Lee, Yooseug Wang, S. Woo, Changick Kim

Submitted to ECCV 2024 

• • [C7] Group Activity Recognition Approach, 

M. A. Nugroho, S. Woo, S. Lee, J. Park, Yooseung Wang, D. Kim, Changick Kim, 

Submitted to ECCV 2024 (Human Recognition)

• • [C6] Super-resolution Approach, 

S. Jung, J. Jang, B. Park, Yooseung Wang, Changick Kim, 

Preprint

• • [J10] FCGNet: Foreground and Class Guided Network for Human Parsing

J. Jang, Yooseung Wang, Changick Kim, 

Under Review in Pattern Recognition (SCIE, IF: 8.5) [Paper] (Human Recognition)

• • [J9] CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentation,

Jingi Ju*, H. Noh*, Yooseung Wang*, M. Seo, D. Choi (*Equal Contributions), 

IEEE ACCESS (SCIE, IF: 3.5) [Paper] (Machine Perception)

• • [C4] Towards Robust Multimodal Prompting With Missing Modalities, 

J. Jang, Yooseung Wang, Changick Kim, 

ICASSP 2024 (Multimodal Learning) [Paper]

• • [J8] Subdivided Mask Dispersion Framework for Semi-Supervised Semantic Segmentation,  

Yooseung Wang, J. Jang, Changick Kim, 

Pattern Recognition Letters (SCIE, IF: 5.1) [Paper] 2024 (Machine Perception, Data Minimization)

• • [C3] Noise-Augmented Missing Modality Aware Prompt Based Learning for Robust Visual Recognition,

Yooseung Wang, J. Jang, Changick Kim, 

IEEE VCIP 2023 (Multimodal Learning, Network Minimization) 

2020-2022 (Defense AI Center, ADD)

• • [J7] Occlusion-Aware Spatial Attention Transformer for Partially Occluded Object Recognition,

J. Heo, Yooseung Wang, J. Park, 

Pattern Recognition Letters (SCIE, IF: 5.1), 2023 [paper] (Machine Perception)

• • [J6] Angular Margin Mining Softmax for Face Recognition,

J. Lee, Yooseung Wang, S. Cho, 

IEEE ACCESS (SCIE, IF:3.5), 2022 [paper] (Human Recognition)

• • [J5] Camera and Lidar Sensor Fusion and Global Mapping for Autonomous Car, 

J. Park, H. Yoo, Yooseung Wang, 

IEEE Transactions on Intelligent Transportation System (SCIE, IF: 9.6), 2022 [paper] (Multimodal Learning, Machine Perception)

• • [J4] Zero-shot Semantic Segmentation via Spatial and Multi-Scale Aware Visual Class Embedding,

S. Cha*, Yooseung Wang* (*Equal Contributions), 

Pattern Recognition Letters (SCIE, IF: 5.1), 2022 [paper] (Machine Perception, Data Minimization)

• • [J3] NL-LinkNet : Toward Lighter but More Accurate Road Extraction with Non-Local Oper()ations

Yooseung Wang, J. Seo, T. Jeon, 

IEEE Geoscience and Remote Sensing Letters (SCIE, IF: 4.8), 2022 [paper] (Network Minimization)

• Citation > 50, Beat the 1st place of 2018CVPRW DeepGlobe Challenge 

• • [J2] Memory-free Stochastic Weight Averaging by One-way Variational Pruning,

Yooseung Wang, H. Park, J. Lee, 

IEEE Signal Processing Letters (SCIE, IF:3.9, acceptance rate ~= 20%), 2021 [paper] (Network Minimization)

• • [J1] One-shot Summary Prototypical Network Toward Accurate Unpaved Road Semantic Segmentation 

Yooseung Wang, D. Lee, J. Heo, J. Park*, 

IEEE Signal Processing Letters (SCIE, IF:3.9, acceptance rate ~= 20%),  2021 [paper] (Machine Perception, Data Minimization)

• • [C2] Transitional Asymmetric Non-local Neural Network for Real-World Dirt Road Segmentation 

Yooseung Wang, J. Park, 

ICPR 2020 [paper] [poster] [slides] [video] (Machine Perception, Network Minimization)

• • [C1] Occlusion Data Augmentation for Object detectors based on Random Erasing and Bounding Box Tailoring, 

J. Heo, Yooseung Wang, J. Park, 

ICCAS 2020 [paper] (Machine Perception, Data Minimization)

Patent

• • J. Park, H. Yoo, Yooseung Wang, 의사-레이블 데이터 생성 방법 및 장치, 의사-레이블 데이터를 이용한 심층 신경망 학습 방법 및 장치, "Method and appratus for identifying a driving area of a vehicle using an image and a lidar." (Korea - Registration No. 102336500 / Application No. 10-2021-0015700)  (Machine Perception)

  • J. Park, H. Yoo, Yooseung Wang, 영상 및 라이다를 활용한 차량의 주행 가능 영역 식별 장치 및 방법 "Cyclic learning method using heterogeneous sensors and heterogeneous identification algorithms", (Korea - Registration No. 10-2306083 / Application No. 10-2020-0000439)  (Machine Perception)

  • B. Kim, H. Choi, Yooseung Wang, S. Lee, H. Kang, “Entry-level 3D Scanner Kit” (Korea - Application No. 10-2017-0179216)

Domestic Publication

• • 왕유승, 우상민, 김창익, "엣지 장치를 위한 경량화된 한국어 음성인식 모델 분석", 대한전자공학회 추계학술대회, 2023

  • 이동혁, 왕유승, 허지성, 조선영, 유현성, 박지훈, "전차 부위별 인식 정확도 분석", 한국군사과학기술학회 종합학술대회, 2022

  • 왕유승, 조영걸, "은닉 물체 탐지를 위한 자가주의 탐색인지 네트워크", 제 17회 한국로봇종합학술대회 (KRoC), 2022

  • 왕유승, 박지훈, "콘볼루션 인공신경망 기반 군용 기동장비 은닉 물체 탐지 기술 연구", 제 31회 영상처리 및 이해에 관한 워크샵 (IPIU), 2022

  • 김민수, 김석종, 이기성, 왕유승, "군의 정비능력 향상을 위한 딥러닝 기반의 고장예측체계 활용 연구", 한국군사과학기술학회 종합학술대회, 2021

  • 허지성, 이동혁, 왕유승, 임형우, "시뮬레이터를 이용한 자율주행 강화학습 방법 연구", 한국군사과학기술학회 종합학술대회, 2021

Projects

• 2022.08 - Present / Samsung Advanced Institute of Technology (SAIT) 

Title : 나노 광학 구조 이미지 센서 해상도 개선 알고리즘 연구 

•  2022.01-2022.05 / Agency for Defense Development (ADD) 

    Title : Face Recognition (Provided upon Request, Security Issue) 

• 2019.06-2021.09 [News] / Agency for Defense Development (ADD) 

Title : AI-based Military Autonomous Driving Car for Unpaved Road (무인체계용 지능형 학습/추론엔진기술)

• 2019.06-2022.05  / Agency for Defense Development (ADD)

Title : Occluded Military Vehicle Detection (인공지능 기반 시각적 부분 가림 물체 자동 식별 기술)