Video auditing method and device, equipment, storage medium and program product

The invention discloses a video auditing method and device, equipment, a storage medium and a program product, and belongs to the field of machine learning. The method comprises the following steps: acquiring n single-mode features of a target video; performing time sequence fusion on each single-mode feature in the n single-mode features to obtain n single-mode time sequence fusion features; fusing the n types of single-mode time sequence fusion features and the n types of single-mode features to obtain a multi-mode fusion feature; and performing video auditing based on the multi-modal fusion feature to obtain a violation category label of the target video. According to the method, the target video is subjected to multi-angle auditing in combination with the front and back contents through the multi-modal fusion features, so that the accuracy of auditing the violation category labels output by the target video is improved. 本申请公开了一种视频审核方法、装置、设备、存储介质及程序产品，属于机器学习领域。所述方法包括：获取目标视频的n种单模态特征；分别对所述n种单模态特征中的每种单模态特征进行时