home
Home
home
Members
International Papers
Domestic Papers
Under Review
Gallary
Seminar
Conference Schedule
Course
home

Members

Professor

Publication

(* indicates first author, † indicates corresponding author)

Submitted

1.
Seong-Hun Jeong*, Kyeongbo Kong†, “Embedding-Space Localization for Robust 3D TDOA Estimation”, (Submitted)
2.
Dongkyu Kim*, Eunho Shin*, Kyeongbo Kong†, Suk-Ju Kang†, “Anonymized Title”, (Submitted)
3.
Changwoo Baek*, Sohyeon Kim*, Jouwon Song*, Kyeongbo Kong†, “Efficient Token Pruning for Vision-Language Models in Multi-turn Scenarios”, (Submitted)
4.
Joonsoo Kim*, Kugjin Yun, Hyon-Gon Choo, Hyeongju Mun, Kyeongbo Kong†, “3D Gaussian rasterization for rendering of view-multiplexed image for multiview displays“, (Submitted)
5.
Seong-Hun Jeong*, Inhwan Jin*, Haesoo Choo*, Hyunjun Na*, Kyeongbo Kong†, “Motion-to-Attention: Enhancing Attention Maps to Improve Performance of Text-Guided Video Editing Models”, (Submitted)
6.
Joseph Kihoon Kim*, Kyeongbo Kong*, Suk-Ju Kang†, “UA-UNet: Quantifying Uncertainty and Improving Segmentation through Uncertainty-Aware Learning”, (Revision)
7.
In-Hwan Jin*, Hyeongju Mun*, Joonsoo Kim, Kyeongbo Kong†, “Anonymized Title”, (Submitted)
8.
Suwoong Yeom*, Jimin Roh*, Eunho Shin*, Songju Na, Joonsoo Kim, Kyeongbo Kong†, Suk-Ju Kang†, “Enhancing Monocular Dynamic Gaussian Splatting via Adaptive Pipeline Integration”, (Submitted)
9.
Yubin Cho*, Hyunwoo Yu*, Kyeongbo Kong, Suk-Ju Kang†, “Anonymized Title”, (Submitted)
Kyeongbo Kong

Postdoctoral researcher

Publication

International Journal Papers

[J2] Dimension-Specific Margins and Element-Wise Gradient Scaling for Enhanced Matryoshka Speaker Embedding Sunchan Park*, Hyung Soon Kim† IEEE Access, Mar. 2025. [J1] Reverberant environment embedding using dereverberation autoencoder Sunchan Park*, Hyung Soon Kim† Electronics Letters, Jan. 2025.

International Conference Papers

[C2] Linear prediction-based dereverberation with very deep convolutional neural networks for reverberant speech recognition Sunchan Park*, Yongwon Jeong, Min Sik Kim, Hyung Soon Kim† ICEIC, Jan. 2018. [C1] Multiresolution CNN for reverberant speech recognition Sunchan Park*, Yongwon Jeong, Hyung Soon Kim† O-COCOSDA, Nov. 2017.

Domestic Journal Papers

[J3] 부분 요소 공유를 통한 마트료시카 화자 임베딩 향상 박순찬*, 김형순† 말소리와 음성과학, Jun. 2025. [J2] 음성감정인식 성능 향상을 위한 트랜스포머 기반 전이학습 및 다중작업학습 박순찬*, 김형순† 한국음향학회지, Sep. 2021. [J1] 잔향 환경 음성인식을 위한 다중 해상도 DenseNet 기반 음향 모델 박순찬*, 정용원, 김형순† 말소리와 음성과학, Mar. 2018.

Domestic Conference Papers

[C3] 종단간 음성인식 모델의 다층 특징을 활용한 화자인식 박순찬*, 김형순† 한국음성학회 가을 학술대회, Nov. 2022. [C2] 상호의존정보를 이용한 임베딩 기반 음성감정인식 박순찬*, 김형순† 한국음성학회 가을 학술대회, Nov. 2021. [C1] 음성 감정 인식에서 운율 특징의 영향 분석 박순찬*, 김형순† 한국음성학회 가을 학술대회, Nov. 2020.

Patents

Sunchan Park

Ph.D Courses

MS Courses

Publication

(* indicates first author, † indicates corresponding author)

International Conference Papers

[C4] Human Motion Aware Text-to-Video Generation with Explicit Camera Control Taehoon Kim*, Chanhee Kang*, Jaehyuk Park*, Daun Jeong*, ChangHee Yang*, Suk-Ju Kang†, Kyeongbo Kong†
WACV, Jan. 2024. (Second-tier AI conference)
[C3] Text-Based Video Generation With Human Motion and Controllable Camera Taehoon Kim*, Chanhee Kang*, Jaehyuk Park*, Daun Jeong*, ChangHee Yang*, Suk-Ju Kang†, Kyeongbo Kong†
ICCVw, Oct. 2023. (Top-tier AI conference workshop)

Domestic Conference Papers

[C5] 오픈셋 이미지 복원을 위한 프롬프트 기반 적응
김태훈*, 정다운*, 공경보† 대한임베디드공학회 ICT 대학생 논문 경진대회, June 2025.
[C2] 휴먼 모션 생성을 통한 텍스트 기반 비디오 생성 알고리즘에 관한 연구 김태훈*, 정다운*, 박재혁*, 공경보† 대한전자공학회 하계학술대회, Jun. 2023.
Daun Jeong

Publication

(* indicates first author, † indicates corresponding author)

Submitted

[C1] Anonymized Title
In-Hwan Jin*, Hyeongju Mun*, Joonsoo Kim, Kyeongbo Kong†
[J1] Motion-to-Attention: Enhancing Attention Maps to Improve Performance of Text-Guided Video Editing Models Seong-Hun Jeong*, In-Hwan Jin*, Haesoo Choo*, Hyunjun Na*, Kyeongbo Kong†

International Conference Papers

[C4] Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images In-Hwan Jin*, Haesoo Choo*, Seong-Hun Jeong, Heemoon Park, Junghwan Kim, Oh-joon Kwon, Kyeongbo Kong†
ICLR 2025, Apr, 2025 (Top-tier AI conference, Acceptance Rate: 32.08%)
[C3] Dynamic Scene Reconstruction from Single Landscape Image Using 4D Gaussian in the Wild
In-Hwan Jin

Publication

(* indicates first author, † indicates corresponding author)

International Conference Papers

[C3] Human Motion Aware Text-to-Video Generation with Explicit Camera Control Taehoon Kim*, Chanhee Kang*, Jaehyuk Park*, Daun Jeong*, ChangHee Yang*, Suk-Ju Kang†, Kyeongbo Kong†
WACV, Jan. 2024. (Second-tier AI conference)
[C2] Text-Based Video Generation With Human Motion and Controllable Camera Taehoon Kim*, Chanhee Kang*, Jaehyuk Park*, Daun Jeong*, ChangHee Yang*, Suk-Ju Kang†, Kyeongbo Kong†
ICCVw, Oct. 2023. (Top-tier AI conference workshop)

Domestic Conference Papers

[C4] 오픈셋 이미지 복원을 위한 프롬프트 기반 적응
김태훈*, 정다운*, 공경보† 대한임베디드공학회 ICT 대학생 논문 경진대회, June 2025.
[C1] 휴먼 모션 생성을 통한 텍스트 기반 비디오 생성 알고리즘에 관한 연구 김태훈*, 정다운*, 박재혁*, 공경보† 대한전자공학회 하계학술대회, Jun. 2023.
Taehoon Kim

Integrated BS-MS Courses

Project

•
홈로봇 환경을 고려한 야간 사람 인식 기술 개발 및 주간 얼굴 인식 성능 개선, LG Electronics, Korea /공동연구원
•
홈로봇 환경을 고려한 VLM 기반시각 인식 기술 개발 및 상황 인지·추론 성능 개선, LG Electronics, Korea /공동연구원
Changwoo Baek

Publication

(* indicates first author, † indicates corresponding author)

Submitted

1.
In-Hwan Jin*, Hyeongju Mun*, Joonsoo Kim, Kyeongbo Kong†, “Anonymized Title”, (Submitted)
2.
Joonsoo Kim*, Kugjin Yun, Hyon-Gon Choo, Hyeongju Mun, Kyeongbo Kong†, “3D Gaussian rasterization for rendering of view-multiplexed image for multiview displays“, (Submitted)

Project

LIG 넥스원(2023.11~Present)

•
다중송신원 환경 TDOA Hybrid 위치추정 기술, LIG Nex1, Korea/ 공동연구원 (Nov. 2023 ~ Present)

ETRI(2024.08~Present)

HyeongJu Mun

Publication

(* indicates first author, † indicates corresponding author)
[J1] 동적 이미지 합성을 위한 4D Gaussian Splatting 기법 비교 및 연구 동향
우민수*, 진인환*, 김준수, 윤국진, 공경보†
방송공학회논문지, 2025년 1월.

Project

ETRI(2024.08~Present)

•
4D 공간표현 생성 및 라이트필드 비디오 렌더링 SW 구현, ETRI, Korea/ 참여연구원 (Aug. 2024 ~ Present)

LG Electronics(2025.06~Present)

•
홈로봇 환경을 고려한 이상 상황·환경 감지 기술 개발, LG Electronics, Korea /공동연구원
MinSoo Woo

Project

•
홈로봇 환경을 고려한 이상 상황·환경 감지 기술 개발, LG Electronics, Korea /공동연구원
Woojin Lee

Publication

(* indicates first author, † indicates corresponding author)

Submitted

[C1] Efficient Token Pruning for Vision-Language Models in Multi-turn Scenarios Changwoo Baek*, Sohyeon Kim*, Jouwon Song*, Kyeongbo Kong†

Project

•
홈로봇 환경을 고려한 VLM 기반시각 인식 기술 개발 및 상황 인지·추론 성능 개선, LG Electronics, Korea /공동연구원
Sohyeon Kim

Research Interns

Publication

(* indicates first author, † indicates corresponding author)

Submitted

[J1] Motion-to-Attention: Enhancing Attention Maps to Improve Performance of Text-Guided Video Editing Models Seong-Hun Jeong*, Inhwan Jin*, Haesoo Choo*, Hyunjun Na*, Kyeongbo Kong†

International Conference Papers

[C4] Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images In-Hwan Jin*, Haesoo Choo*, Seong-Hun Jeong, Heemoon Park, Junghwan Kim, Oh-joon Kwon, Kyeongbo Kong†
ICLR 2025, Apr, 2025 (Top-tier AI conference, Acceptance Rate: 32.08%)
[C3] Dynamic Scene Reconstruction from Single Landscape Image Using 4D Gaussian in the Wild
In-Hwan Jin*, Haesoo Choo*, Seong-Hun Jeong, Heemoon Park, Junghwan Kim, Oh-joon Kwon, Kyeongbo Kong†
ECCVW 2024, Sep, 2024
Haesoo Choo

Publication

Sohyeong Kim

Publication

Jihoon Choi