Tatsuya Komatsu
Scholar

Tatsuya Komatsu

Google Scholar ID: o2lMlxMAAAAJ
LINE Corporation
Signal ProcessingSound Event DetectionSource Separation
Google Scholar↗
Citations & Impact
All-time
Citations
974
 
H-index
16
 
i10-index
24
 
Publications
20
 
Co-authors
62
list available
Contact
No contact links provided.
Publications
8 items
CASTELLA: Long Audio Dataset with Captions and Temporal Boundaries
2025
Cited
0
Hallucination Localization in Video Captioning
2025
Cited
0
Listening without Looking: Modality Bias in Audio-Visual Captioning
2025
Cited
0
ProLAP: Probabilistic Language-Audio Pre-Training
2025
Cited
0
Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos
2025
Cited
0
Music Tagging with Classifier Group Chains
2025
Cited
0
Language-based Audio Moment Retrieval
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2024
Cited
1
Self-Supervised Learning Method Using Multiple Sampling Strategies for General-Purpose Audio Representation
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2022
Cited
1
Resume (English only)
Co-authors
62 total
Yusuke Fujita
Yusuke Fujita
SB Intuitions
Kazuya Takeda
Kazuya Takeda
Dept. of Intelligent Systems, School of Informatics, Nagoya University
Co-author 3
Co-author 3
Co-author 4
Co-author 4
Shinji Watanabe
Shinji Watanabe
Carnegie Mellon University
Robin Scheibler
Robin Scheibler
Google Deepmind
Tomoki Toda
Tomoki Toda
Nagoya University
Co-author 8
Co-author 8