Video Summarization

Capability Introduction

Memorable moments, intelligent summary

With multidimensional scoring based on video AI technology, aesthetic engine understands human cognitive perspectives of images, such as beauty, attraction, entertainment, impression and more. This API can be applied in photo software to deploy functions like photo album management, image auto-editing and photography aids. The algorithm of aesthetic engine supports comprehensive scoring of the image input according to multiple aesthetic principles including objectivity, subjectivity, photography skills and human beauty.

Summarizing, social media content

This API helps browse and summarize one or more videos, and can be applied in photography, classification, as well as for summarizing video clips and dynamic video covers.

Video clip summaries

Single or multiple video clips (with a max length of 10 mins) can be selected to generate 10s, 15s, or 30s highlights with the original sound for quick browsing or sharing.

Video cover summaries

Video clips can be selected as the dynamic covers for longer videos.



aestheticsScoreDetector = new AestheticsScoreDetector(MainActivity.this);
AEModelConfiguration aeModelConfiguration = new AEModelConfiguration();
Video[] videos = new Video[videoPaths.length];
for (String path: videoPaths) {
    Video video = new Video();
    videos[position++] = video;
JSONObject jsonObject;
jsonObject = aestheticsScoreDetector.getVideoSummerization(videos, null);
AEVideoResult aeVideoResult = aestheticsScoreDetector.convertVideoSummaryResult(jsonObject);


    "resultCode": 0,
    "videoSummerization": "[{\"endFrameTimeStamp\":5060000,

Start development here with Huawei

Service introduction

Service overview, application scenarios, and functions
Learn more

Access preparation

Preparation for access, such as registration, authentication, and agreement signing
Learn more

Sample code

Demonstration of sample code
Learn more

API description

Interface parameter definition, description, restrictions, and constraints
Learn more
1Can prepare() method directly use detect() method without calling the API?

Yes. In detect() method engine startup is in default. The engine will not start up again if started, please use with confidence.

2When should I call the release() method?

The release() method will uninstall a model that has been loaded to the NPU chip. If the app is no longer using face detection, uninstall the model in a timely manner to free up resources.