The latest service changes have not yet been reflected in this content. We will update the content as soon as possible. Please refer to the Korean version for information on the latest updates.
Available in VPC
Media Intelligence offers scene-level analysis and automatic metadata extraction. This enables easy video search and enhances indexing efficiency. While you can explore the service in detail with our Getting Started and Using Media Intelligence guides, we recommend starting with this quickstart overview to understand the complete workflow.
1. Upload video files to Object Storage for analysis
Upload the video files you want to analyze to the Object Storage bucket integrated with Media Intelligence. For detailed instructions, see:
2. Access workspace
Access the Media Intelligence workspace, where all tasks are performed. For detailed instructions, see:
3. Create project
Create a project, a space to manage video assets and analysis results. For detailed instructions, see:
4. Add video asset
After uploading the files to the Object Storage bucket, add these files to the Media Intelligence project. The original files are converted to low-resolution versions and stored in the Media Intelligence database. These low-resolution versions are called video assets. For detailed instructions, see:
5. Video analysis
Analyze the video asset with the multimodal engine (Sinossi) and extract metadata. Based on the analysis results, metadata such as main keywords, scene summaries, and character information is automatically generated. You can analyze the same video multiple times and create various indexes based on the analysis settings. For detailed instructions, see:
6. View analysis results
Check keywords, people, and caption information for each scene on a separate webpage to find desired edit points quickly and easily. You can export the results as a JSON file for various purposes. For detailed instructions, see: