23-06-2023 дата публикации
Номер: CN116310934A
Принадлежит:
The invention belongs to the technical field of video processing, and particularly relates to a video relation prediction method and device based on dual attention, equipment and a medium, and the method comprises the steps: obtaining a to-be-predicted video; preprocessing the video to obtain a preprocessed video; predicting a target object in the preprocessed video based on a dual attention mechanism, and outputting an action predicate prediction result and a position predicate prediction result of the target object; and combining the action predicate prediction result and the position predicate prediction result, and performing optimization according to a preset weight adjustment parameter to obtain an optimized prediction result. According to the method, the video is analyzed and predicted, the action predicate and the position predicate of the target object in the video are accurately predicted, and the action predicate and the position predicate are combined and optimized, so that ...
Подробнее