● Covered by 1 source · 1 reportLow impact1 neutral
Condé Nast implements AI-powered multimodal video discovery with Amazon Bedrock
Key points
- Condé Nast reduced video discovery time from 250 minutes to under 2 minutes.
- The solution uses Amazon Bedrock and OpenSearch Service.
- It performs intent-based semantic search across video transcripts, visuals, and audio.
- The TwelveLabs Marengo embedding model powers the multimodal search.
Addressing Inefficient Video Discovery
Condé Nast's editorial teams previously spent an average of 250 minutes per content discovery task, manually reviewing a library of over 140,000 videos. Their process relied on titles and descriptions, leading to operational inefficiencies and underutilized content that was not discoverable through keyword searches.
AI-Powered Solution Development
To resolve these issues, Condé Nast collaborated with the AWS Generative AI Innovation Center (GenAIIC) to build an AI-powered multimodal video discovery solution. This system is built on Amazon Bedrock and Amazon OpenSearch Service, enabling intent-based semantic search.
Multimodal Semantic Search Capabilities
The new solution integrates video transcripts, visual elements, and audio for comprehensive content discovery. It utilizes the TwelveLabs Marengo embedding model, chosen for its ability to jointly encode visual, audio, and transcript signals, allowing for a deeper understanding of video content beyond simple keywords.
Significant Time Reduction and Impact
The implementation of this AI-powered system has reduced the average content discovery time from 250 minutes to less than 2 minutes per task. This improvement addresses the limitations of traditional keyword search by understanding editorial intent, which is crucial for navigating a large video archive effectively.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
Reporting from
Condé Nast partnered with AWS to develop an AI-powered multimodal video discovery solution using Amazon Bedrock and OpenSearch Service. This system reduces content discovery time from 250 minutes to under 2 minutes per task for its 140,000-video library. The solution addresses the inefficiency of manual video scrubbing and keyword-based searches by enabling intent-based semantic search across video transcripts, visuals, and audio.