Video processing method and device, electronic equipment and storage medium

Abstract

The invention discloses a video processing method and device, electronic equipment and a storage medium, and relates to the field of artificial intelligence, in particular to the fields of deep learning, model training, knowledge maps, video processing and the like. According to the specific implementation scheme, the method comprises the following steps: acquiring a plurality of first video frames, and performing fine-grained splitting on the plurality of first video frames to obtain a plurality of second video frames; according to multi-modal information related to the plurality of second video frames, performing feature coding on the plurality of second video frames to obtain feature fusion information used for representing multi-modal information fusion; and performing similarity matching on the plurality of second video frames according to the feature fusion information, and obtaining a target video according to a similarity matching result. By adopting the method and the device,the video splitting accuracy can be improved.

Description

technical field [0001] This application relates to the field of artificial intelligence, especially the fields of deep learning, model training, knowledge graph, video processing, etc. Background technique [0002] Portable devices, mobile terminals and other electronic devices are more intelligent than before, and the analysis capability of the chip is stronger. Especially, the analysis of video information and picture rendering are faster and clearer than before, which makes the user's demand for video quality higher than that of the past. In the past, especially for high-time-sensitive scenes (such as military parade scenes, sports events, real-time live video broadcasts, etc.), users hope to capture the wonderful pictures of each video moment, and need more accurate and clear video pictures . [0003] In video processing, taking video splitting as an example, video splitting can be achieved manually, but it will not only consume a lot of labor costs, but also cannot mee...

AI Technical Summary

Problems solved by technology

[0003] In video processing, taking video splitting as an example, video splitting can be achieved manually, but it will not only consume a lot of labor costs, but also cannot meet the requirements of the above-mentioned high time-sensitive scenarios; and for some non-manual video splitting methods , unable to fully understand the content information of video frames (such as text, objects in the video, actions, etc.), and the continuity of video events (such as scene switching caused by lens changes, etc.) cannot be well controlled, resulting in interpretation of the video screen The accuracy is greatly reduced, which affects the video quality effect presented by the final target video

Images