Knowledge-Augmented Vision Language Models for Underwater Bioacoustic Spectrogram Analysis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915483077312512 |
|---|---|
| author | Nihal, Ragib Amin Yen, Benjamin Ashizawa, Takeshi Nakadai, Kazuhiro |
| author_facet | Nihal, Ragib Amin Yen, Benjamin Ashizawa, Takeshi Nakadai, Kazuhiro |
| contents | Marine mammal vocalization analysis depends on interpreting bioacoustic spectrograms. Vision Language Models (VLMs) are not trained on these domain-specific visualizations. We investigate whether VLMs can extract meaningful patterns from spectrograms visually. Our framework integrates VLM interpretation with LLM-based validation to build domain knowledge. This enables adaptation to acoustic data without manual annotation or model retraining. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05703 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Knowledge-Augmented Vision Language Models for Underwater Bioacoustic Spectrogram Analysis Nihal, Ragib Amin Yen, Benjamin Ashizawa, Takeshi Nakadai, Kazuhiro Computer Vision and Pattern Recognition Artificial Intelligence Information Retrieval Marine mammal vocalization analysis depends on interpreting bioacoustic spectrograms. Vision Language Models (VLMs) are not trained on these domain-specific visualizations. We investigate whether VLMs can extract meaningful patterns from spectrograms visually. Our framework integrates VLM interpretation with LLM-based validation to build domain knowledge. This enables adaptation to acoustic data without manual annotation or model retraining. |
| title | Knowledge-Augmented Vision Language Models for Underwater Bioacoustic Spectrogram Analysis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2509.05703 |