Towards Temporal Change Explanations from Bi-Temporal Satellite Images
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917721449431040 |
|---|---|
| author | Tsujimoto, Ryo Ouchi, Hiroki Kamigaito, Hidetaka Watanabe, Taro |
| author_facet | Tsujimoto, Ryo Ouchi, Hiroki Kamigaito, Hidetaka Watanabe, Taro |
| contents | Explaining temporal changes between satellite images taken at different times is important for urban planning and environmental monitoring. However, manual dataset construction for the task is costly, so human-AI collaboration is promissing. Toward the direction, in this paper, we investigate the ability of Large-scale Vision-Language Models (LVLMs) to explain temporal changes between satellite images. While LVLMs are known to generate good image captions, they receive only a single image as input. To deal with a par of satellite images as input, we propose three prompting methods. Through human evaluation, we found the effectiveness of our step-by-step reasoning based prompting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_09548 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Temporal Change Explanations from Bi-Temporal Satellite Images Tsujimoto, Ryo Ouchi, Hiroki Kamigaito, Hidetaka Watanabe, Taro Computer Vision and Pattern Recognition Artificial Intelligence Explaining temporal changes between satellite images taken at different times is important for urban planning and environmental monitoring. However, manual dataset construction for the task is costly, so human-AI collaboration is promissing. Toward the direction, in this paper, we investigate the ability of Large-scale Vision-Language Models (LVLMs) to explain temporal changes between satellite images. While LVLMs are known to generate good image captions, they receive only a single image as input. To deal with a par of satellite images as input, we propose three prompting methods. Through human evaluation, we found the effectiveness of our step-by-step reasoning based prompting. |
| title | Towards Temporal Change Explanations from Bi-Temporal Satellite Images |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.09548 |