Audiovisual Aerial Scene Recognition Dataset

This dataset provides 5075 paired images and sound clips categorized to 13 scenes, for exploring the aerial scene recognition task. For more details, please refer to our paper and code.本数据集包含5075组配对图像与音频片段，共划分为13个场景类别，旨在支持航拍场景识别（aerial scene recognition）任务的相关研究。如需了解更多细节，请参阅我们的论文与代码。