CinematicT2vData/t2v_style_captions_ablation

这是一个包含视频元数据和场景分割信息的视频描述数据集，它包含了视频ID、视频URL、场景名称、提示文本、字幕、场景数量、起始帧、结束帧等信息。数据集被划分为多个子集，每个子集包含不同数量的示例和大小。数据集可用于视频理解和描述生成任务。This is a video description dataset containing metadata and scene segmentation information, including video ID, video URL, scene name, prompt text, captions, scene count, start frame, end frame, etc. The dataset is divided into multiple subsets, each containing a different number of examples and size. The dataset can be used for video understanding and description generation tasks.