Arda Senocak

I am a Postdoctoral Research Associate working with Joon Son Chung at Multimodal AI Lab @ KAIST. I am interested in Audio-Visual Learning and Understanding.

Previously, I was a Ph. D student at KAIST advised by In So Kweon.

E-mail Scholar Github Twitter

News

  • December 2023: Two papers are accepted to ICASSP 2024.
  • October 2023: One paper is accepted to WACV 2024.
  • October 2023: Selected as an Outstanding Reviewer at ICCV 2023.
  • July 2023: One paper is accepted to ICCV 2023.
  • May 2023: FlexiAST is accepted to INTERSPEECH 2023.
  • Jan 2023: Sound2Scene is accepted to CVPR 2023.
  • Jan 2023: Two papers are accepted to ICASSP 2023.
  • Oct 2022: One paper is accepted to WACV 2023.
  • Sep 2022: I have joined Multimodal AI Lab.@KAIST as a Postdoctoral Research Associate.

Publications

From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers

From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers

Jiu Feng*, Mehmet Hamza Erol*, Joon Son Chung, Arda Senocak
ICASSP, 2024 (Corresponding Author)

Project Page PDF arXiv Code
Can CLIP Help Sound Source Localization?

Can CLIP Help Sound Source Localization?

Sooyoung Park*, Arda Senocak*, Joon Son Chung
WACV, 2024 (* Equal Contribution)

Project Page PDF arXiv Code
Sound Source Localization is All about Cross-Modal Alignment

Sound Source Localization is All about Cross-Modal Alignment

Arda Senocak*, Hyeonggon Ryu*, Junsik Kim*, Tae-Hyun Oh, Hanspeter Pfister, Joon Son Chung
ICCV, 2023 (* Equal Contribution)

Project Page PDF arXiv Code
FlexiAST: Flexibility is What AST Needs

FlexiAST: Flexibility is What AST Needs

Jiu Feng*, Mehmet Hamza Erol*, Joon Son Chung, Arda Senocak
INTERSPEECH, 2023 (Corresponding Author)

Project Page PDF arXiv Code
Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment

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

Sung Bin Kim, Arda Senocak, Hyunwoo Ha, Andrew Owens, Tae-Hyun Oh
CVPR, 2023

Project Page PDF arXiv Code
Hindi As a Second Language: Improving Visually Grounded Speech with Semantically Similar Samples

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

Hyeonggon Ryu*, Arda Senocak*, In So Kweon, Joon Son Chung
ICASSP, 2023 (* Equal Contribution)

Project Page PDF arXiv
MarginNCE: Robust Sound Localization with a Negative Margin

MarginNCE: Robust Sound Localization with a Negative Margin

Sooyoung Park*, Arda Senocak*, Joon Son Chung
ICASSP, 2023 (* Equal Contribution)

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

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

Arda Senocak*, Junsik Kim*, Tae-Hyun Oh, Dingzeyu Li, In So Kweon
WACV, 2023 (* Equal Contribution)

Project Page PDF arXiv
Learning Sound Localization Better from Semantically Similar Samples

Learning Sound Localization Better from Semantically Similar Samples

Arda Senocak*, Hyeonggon Ryu*, Junsik Kim*, In So Kweon
ICASSP, 2022 Oral Presentation (* Equal Contribution)

Short Version at Sight and Sound Workshop @ CVPR 2022

Project Page PDF arXiv
Less Can Be More: Sound Source Localization With a Classification Model

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

Arda Senocak*, Hyeonggon Ryu*, Junsik Kim*, In So Kweon
WACV, 2022 (* Equal Contribution)

Received Honorable Mention, 28th HumanTech Paper Award, Samsung Electronics Co., Ltd. ($2000)

Project Page PDF arXiv
Learning to Localize Sound Source in Visual Scenes: Analysis and Applications

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

Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon
TPAMI, 2019 Impact Factor: 24.314

Project Page PDF arXiv Code
Learning to Localize Sound Source in Visual Scenes

Learning to Localize Sound Source in Visual Scenes

Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon
CVPR, 2018 Received Qualcomm Innovation Awards ($5000)

Invited talk at VisionMeetsCognition @ CVPR 2018 and Short Version at Sight and Sound Workshop @ CVPR 2018

Project Page PDF arXiv Code
Part-based Player Identification using Deep Convolutional Representation and Multi-scale Pooling

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

Arda Senocak, Tae-Hyun Oh, Junsik Kim, In So Kweon
CVSports Workshop @CVPR , 2018 Oral Paper

Project Page PDF arXiv Code