Research Interests

My research interests lie in Artificial Intelligence, Computer Vision (CV) and Interdisciplinary Applications. (*bold: first-authored papers) 

• Machine Perception : Segmentation [ICPR'20, SPL'21a, PRL'22b, 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, Preparations for ECCV2024]

• 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'22]

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

Education

• 2022.08 - 2024.08        M.S., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), South Korea  

          - Computation Intelligence Lab (시각지능연구실), Advisor : Changick Kim

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

         * Kwanjeong 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. Dep. of Electrical and Computer Engineering, Ulsan National Institute of Science and Technology (UNIST), South Korea
  - Valedictorian in ECE (Ranked 1/131)

           - Summa Cum Laude, CGPA:4.06/4.3, major GPA: 4.17/4.3

-2018-2019, Undergraduate Research Intern, CSAIL, Advisor: Jaesik Choi (Was at UNIST, moved to KAIST AI Graduate School)

-2018, Uzbekistan, TUIT(타슈켄트정보통신대학교), ALgorithm Lecturer (English), fully funded by Worlds Friends IT 

-2017, Hong Kong, HKUST(홍콩과학기술대학교), Exchange Student, fully funded by government scholarships

-2016, Singapore, NTU(난양공과대학교), Singapore, Participated Global Startup Acceleration Program, fully funded by NIA (winning the Startup Competition)

Research Experience

Agency for Defense Development (국방과학연구소), Defence AI Center (DAIC), 현역연구원,                                               (2019.06-2022.05, Mandatory military Service) 

• Projects:  Autonomous driving 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)

• Action Recognition, object tracking, semantic segmentation 

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

• 3rd Place, 2022 CVPRW SpaceNet 8 Challenge (link, See sianalytics)

• Beat the winner @ 2018 CVPRW  DeepGlobe Challenge [GRSL'21] 

International Publications 

• first-author 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

Preparation for ECCV 2024 

[C6] Super Resolution Approach, 

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

Preprint

[C5] Group Activity Recognition Approach,

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

 Under review in CVPR 2024 (Human Recognition) 

[J10] FCGNet: Foreground and Class Guidd Network for Human Parsing (Human Recognition) 

J. Jang, Yooseung Wang, Changick Kim

Under review in Pattern Recognition (SCIE, IF: 8.5), 2023 [Paper]

[J9] CAFS: Class Adative Framework for Semi-Supervised Semantic Segmentation (Data Minimization)
Jingi Ju*, H. Noh*, Yooseug Wang*, M. Seo, D. Choi (*Equal Contributions), 

IEEE ACCESS (SCIE, IF: 3.9), 2024 [Paper]

[J8] Subdivided Mask Dispersion Framework for Semi-Supervised Semantic Segmentation, (Data Minimization)

Yooseung Wang, J. Jang, Changick Kim

Pattern Recognition Letters (SCIE, IF: 5.1), 2024 [Preprint, Paper]

[C4] Toward Robust Multimodal Prompting with Missing Modalities, (Multimodal Learning) 

J. Jang, Yooseung Wang, Changick Kim

ICASSP 2024 [Paper]

[C3] Noise-Augmented Missing Modality Aware Prompt based Learning for Robust Visual Recognition, (Multimodal Learning)

Yooseung  Wang, J. Jang, Changick Kim

IEEE VCIP 2023 [Paper, Poster, Conference]

2020-2022 (Defense AI Center, ADD)

[J7] Occlusion-Aware Spatial Attention Transformer for Partially Occluded Object Recognition, (Machine Perception)

J. Heo, Yooseung Wang, J. Park, 

Pattern Recognition Letters (SCIE, IF: 5.1), 2022 [Paper]

[J6] Angular Margin Mining Softmax for Face Recognition, (Human Recognition) 

J. Lee, Yooseung  Wang, S. Cho, 

IEEE ACCESS (SCIE, IF:3.5), 2022 [Paper] 

[J5] Zero-shot Semantic Segmentation via Spatial and Multi-Scale Aware Visual Class Embedding, (Data Minimization)

 S. Cha*, Yooseung  Wang*, 

Pattern Recognition Letters (SCIE, IF:5.1), 2022 [arXiv, Paper, News] 

[J4] Drivable Dirt Road Region Identification Using Image and Point Cloud Seemantic Segmentation Fusion, (Multimodal Learning) (Machine Perception)

 J. Park, H. Yoo, Yooseung  Wang,  

IEEE Transactions on Intelligent Transportation System (SCIE, IF:9.6), 2022 [Paper] [News]

[J3] NL-LinkNet : Toward Lighter but More Accurate Road Extraction with Non-Local Operations, (Network Minimization) 

Yooseung  Wang, J. Seo, T. Jeon, 

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

• Beat the winner @ CVPRW DeepGlobe Challenge, Citations > 50

• Pioneered a self-attention based operation into a segmentation task. (All the previous works were convolution-based methods)

[J2] Memory-free Stochastic Weight Averaging by One-way Variational Pruning, (Network Minimization)

Yooseung  Wang, H. Park, J. Lee, 

IEEE Signal Processing Letters (SCIE, IF:3.9, Acceptance ≈ 20% ), 2021 [Paper] 

[J1]  One-shot Summary Prototypical Network Toward Accurate Unpaved Road Semantic Segmentation, (Data Minimization) (Machine Perception)

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

IEEE Signal Processing Letters (SCIE, IF:3.9, Acceptance ≈ 20% ), 2021 [Paper] 

[C2] Transitional Asymmetric Non-local Neural Network for Real-World Dirt Road Segmentation, (Network Minimization) (Machine Perception)

Yooseung Wang, J. Park, 

ICPR 2020 [Paper] [Poster] [Slides] [Video]

[C1] Occlusion Data Augmentation for Object detectors based on Random Erasing and Bounding Box Tailoring, (Data Minimization) (Machine Perception)

J. Heo, Yooseung Wang, J. Park, 

ICCAS 2020 [Paper] 

DOMESTIC PUBLICATIONS 

• [D6] 왕유승, 우상민, 김창익, "엣지 장치를 위한 경량화된 한국어 음성인식 모델 분석", 대한전자공학회 추계학술대회, 2023 

• [D5] 이동혁, 왕유승, 허지성, 조선영, 유현성, 박지훈, "전차 부위별 인식 정확도 분석", 한국군사과학기술학회 종합학술대회, 2022

• [D4] 왕유승, 조영걸, "은닉 물체 탐지를 위한 자가주의 탐색인지 네트워크", 제 17회 한국로봇종합학술대회 (KRoC), 2022

• [D3] 왕유승, 박지훈, "콘볼루션 인공신경망 기반 군용 기동장비 은닉 물체 탐지 기술 연구", 제 31회 영상처리 및 이해에 관한 워크샵 (IPIU), 2022

• [D2] 김민수, 김석종, 이기성, 왕유승, "군의 정비능력 향상을 위한 딥러닝 기반의 고장예측체계 활용 연구", 한국군사과학기술학회 종합학술대회, 2021 

• [D1] 허지성, 이동혁, 왕유승, 임형우, "시뮬레이터를 이용한 자율주행 강화학습 방법 연구", 한국군사과학기술학회 종합학술대회, 2021 

PATENT 

• [PT1] Jihun Park, Hyeonsung 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) 

• [PT2,] Jihun Park, Hyeonsung 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)

• [PT3] Byeong-Su Kim, Ha-Lin Choi, Yooseung Wang, Sang-Yun Lee, Hee-Seok Kang, “Entry-level 3D Scanner Kit” (Korea - Application No. 10-2017-0179216)

• 2021 : IEEE GRSL / 2022: IEEE RA-L / 2023: IEEE ICRA, IEEE RA-L, IEEE TGRS 

Awards & Honors
2024, Graduate Presidential Science Scholarship, 

2023, Kwanjeong Lee Jong-Hwan Educational Foundation Scholarship (관정이종환교육재단 장학금)
-Top 1 in KAIST EE&CS MS/PhD freshmen

2022, Kwon Yeong-Se Scholarship
      - Top 2 in KAIST EE MS freshmen
2022, 3rd Place, SpaceNet 8 Challenge on CVPRW

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

2018, Top 1%, NAVER CEO Award, Han-ium ICT Competition

2018-2019, National Science & Technology Scholarship

2017, UNIST Overseas Studies Scholarship, (5,000 USD)      

2016, (Top 2%) 13th place, ACM ICPC Daejeon Regional                     

2015 4th Place, Global Startup Competition

2015 (Top 2%) 57th out of 2300, LG Code Challenger
2015-2019 UNIST Academic Performance Scholarship (Full Scholarship)    

2015 Honorable mention, Korea Super-computing Challenge

Project  

• 2023.02 - Present, Group Activity Recognition, 그룹 행동 인식 연구 

• 2022.08 - 2023.06 Present, Samsung Electronics, Samsung Advanced Institute of Technology (SAIT), 나노 광학 구조 이미지 센서 해상도 개선 알고리즘 연구

• 2022.01-2022.05, Agency for Defense Development (ADD), Face Recognition  

Related Works : IEEE ACCESS (AMM-Softmax)

• 2019.06-2021.09 [News], Agency for Defense Development (ADD), AI-based Military Autonomous Driving Car for Unpaved Road (무인체계용 지능형 학습/추론엔진기술)

Related Works : ICPR20 (TANNet), T-ITS’21, SPL21 (SWA-OVP), SPL21 (OSPNet)

• 2019.06-2022.05, Agency for Defense Development (ADD), Occluded Military Vehicle Detection (인공지능 기반 시각적 부분 가림 물체 자동 식별 기술)

Related Works : PRL22 (OSAT), ICCAS20 (ODA)

• 2018.07-2018.08, Electronics and Telecommunications Research Institute (ETRI), Development of High Performance Visual Discovery Platform for Realtime and Large-Scale Data Analysis and Prediction (실시간 대규모 영상 데이터 이해·예측을 위한 고성능 비주얼 디스커버리 플랫폼 개발)

• 2018.04-2018.06, UNIST, A machine learning and statistical inference framework for explainable artificial intelligence (의사결정 이유를 설명할 수 있는 인간 수준의 학습·추론 프레임워크 개발)

Related Works : PRL22(SM-VCENet)