Ji-Hoon Kim

Hyeonggon Ryu

Sooyoung Park

Arda Senocak

Dawit Mureja Argaw

Soyoon Kim

Jiu Feng

Jae Won Cho

My research focuses on multimodal learning, particularly on developing machine perception models that can learn from visual, auditory, and other sensory inputs to effectively interact with the world around them. The Multisensory Intelligence Lab focuses on Machine Learning, Audio-Visual Learning, Computer Vision, and Audio/Speech Processing.

다감각 지능 연구실은 기계 학습, 시청각 학습, 컴퓨터 비전, 오디오/음성 처리에 중점을 둡니다.

Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment

Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions

How Far Can We Go With Synthetic Data for Audio-Visual Sound Source Localization?

Cinematic Audio Source Separation Using Visual Cues

Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source Localization

Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation

Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment

Seeing Speech and Sound: Distinguishing and Locating Audios in Visual Scenes

AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models

Audio Mamba: Bidirectional State Space Model for Audio Representation Learning

ElasticAST: An Audio Spectrogram Transformer for All Length and Resolutions

Speech Guided Masked Image Modeling for Visually Grounded Speech

From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers

Can CLIP Help Sound Source Localization?

Sound Source Localization is All about Cross-Modal Alignment

FlexiAST: Flexibility is What AST Needs

Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment

Hindi As a Second Language: Improving Visually Grounded Speech with Semantically Similar Samples

MarginNCE: Robust Sound Localization with a Negative Margin

Event-Specific Audio-Visual Fusion Layers: A Simple and New Perspective on Video Understanding

Learning Sound Localization Better from Semantically Similar Samples

Less Can Be More: Sound Source Localization With a Classification Model

Learning to Localize Sound Source in Visual Scenes: Analysis and Applications

Learning to Localize Sound Source in Visual Scenes

Part-based Player Identification using Deep Convolutional Representation and Multi-scale Pooling

Learning to localize sound source in visual scenes

Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications

Sound to visual scene generation by audio-to-visual latent alignment

Audio mamba: Bidirectional state space model for audio representation learning

Learning Sound Localization Better From Semantically Similar Samples

Sound source localization is all about cross-modal alignment

Less can be more: Sound source localization with a classification model

Avhbench: A cross-modal hallucination benchmark for audio-visual large language models

Hindi as a Second Language: Improving Visually Grounded Speech with Semantically Similar Samples

Aligning sight and sound: Advanced sound source localization through audio-visual alignment

Speech guided masked image modeling for visually grounded speech

Sound2vision: Generating diverse visuals from audio through cross-modal latent alignment

Toward Interactive Sound Source Localization: Better Align Sight and Sound!

Tae-Hyun Oh

Junsik Kim

In So Kweon

Joon Son Chung

Ming-Hsuan Yang

Kim Sung-Bin

Andrew Owens

Dingzeyu Li

Professor

Associate Professor / Assistant Professor

M.Eng. (B.A.) in Engineering, Economics and Management

Associate Professor

Youngjoon Jang

Postdoctoral Researcher

Kangwook Jang

Ph.D. Student

Jeongsoo Choi

Postdoctoral Research Associate

Hyeongkeun Lee

Kyeongha Rho

Ph.D. Candidate

Kihyun Nam

Suyeon Lee

Chaeyoung Jung

Jaehun Kim

Tan Dat Nguyen

Seungwoo Lee

Jaemin Jung

Youkyum Kim

MS/PhD Students

Doyeop Kwak

Junseok Ahn

Jong-Bin Woo

Seongyu Kim

Kang Zhang

Jihoo Jung

MS Students

Jongmin Choi

Suho Yoo

Jaewook Jeong

Tae Wook Haam

Arda Senocak's Lab

교수님 소개

아르다 세노카크

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions

How Far Can We Go With Synthetic Data for Audio-Visual Sound Source Localization?

Cinematic Audio Source Separation Using Visual Cues

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

아르다 세노카크

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions

How Far Can We Go With Synthetic Data for Audio-Visual Sound Source Localization?

Cinematic Audio Source Separation Using Visual Cues

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집