Chroma-Actions Dataset: Acoustic Images

Chromagram-based representation of audio extracted from videos. These representations were extracted from the UCF-101 Human Action Recognition dataset. Only videos with audio channels were considered.针对从视频中提取的音频，构建基于色度频谱图（Chromagram）的表征形式。该类表征均提取自UCF-101人类动作识别数据集，且仅纳入带有音频声道的视频进行处理。