Video hard cut detection is used for separating a video stream into a set of individual scenes by detecting camera hard-transitions automatically. Based on the result the user can obtain a fast overvi
1X World Model Challenge数据集是为1X World Model Challenge设计的，包含训练和验证数据集，分为100个独立的分片。每个分片包含视频数据（8x8x8图像块，30hz，17帧时间窗口）、状态数据（np.float32格式）和元数据（metadata.json）。数据集的变化包括新增了100小时的训练和验证数据集，应用了面部模糊处理，并共享了一个新的原始视频
Indonesian Sign Language Dataset: Alphabet Video is a dataset that consists of a video showing the hand movement of the 26 alphabets in Indonesian Sign Language. There are 40 videos for the alphabet '
