Which episode? Using AI to streamline media content operations
summary
AWS tooling plus partner Curio turns large archives into timestamped, searchable metadata: content lands in S3, Rekognition (labels, video segment detection, content moderation and Amazon Rekognition Custom Labels) and Curio create frame‑level tags, mapable to a PoolParty knowledge graph stored in Amazon Neptune. A Sesame Street pilot on ~seven petabytes / 60,000 titles proves Muppet recognition feasible, yields a production‑ready pipeline, and cuts trailer logging work (example: editor logging goes from five days to about two hours with Nova/PromoMii).
AI-written summary · about
chapters (9)
- 0:00Introduction to AI in media
- 4:11Macro trends in media operations
- 9:11Amazon Rekognition overview
- 10:57PBS Sesame Street use case
- 17:45Next steps for PBS
- 18:52Content discovery with metadata
- 21:42Media operations workflows
- 26:59Benefits of Rekognition
- 28:29Resources and next steps
related talks
13mSpotting and solving everyday problems with machine learning
33mMaximize lifetime value of media content
29mRekognition Live Demo
44mBest practices for analytics and generative AI on AWS(ANT302)
01h 41mGetting started with Machine Learning on AWS.
48mBuilding Serverless AI powered Applications on AWS
15mIP Detection at Scale: CI/CD Meets Cloud-Native Enforcement
24mApplications of AI in news and media