# Video search Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/video-search
> Markdown URL: https://aitinkerers.org/technologies/video-search.md
> Technology record last updated: 2026-05-01T16:32:55Z
> Generated: 2026-09-22T21:33:57Z

Video search uses AI and machine learning to analyze video content—audio, visuals, and text—for precise, time-stamped retrieval.

This technology moves beyond simple metadata and transcripts: it leverages computer vision and deep learning to process raw audiovisual data at the frame and shot level. The system indexes rich features like object recognition (e.g., identifying over 20,000 entities: people, places, actions), speech-to-text conversion, and optical character recognition (OCR). This process converts petabytes of footage into searchable vector embeddings, enabling natural language queries like “find the scene where the car turns left”. Key benefits include rapid incident resolution, content moderation, and generating time-specific metadata for applications like contextual advertising or creating intelligent media archives.

- Official technology site: https://cloud.google.com/video-intelligence
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Enhancing Video Search: Exploring Embedding Techniques and Feedback-Driven Optimization](https://boston.aitinkerers.org/talks/rsvp_O_zCGa8Nsk8)

We will demonstrate two methods for video search: one using video embeddings and another employing a thumbs-up/thumbs-down feedback system. This presentation highlights how vector search embeddings can be dynamically adjusted based on user input through the thumbs-up/thumbs-down approach.

- Event context: AI Tinkerers September Meetup Sponsored by BasisTech — 2024-09-23 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_O_zCGa8Nsk8

## Related Technologies

- [Reinforcement Learning](https://aitinkerers.org/technologies/reinforcement-learning) ([Markdown](https://aitinkerers.org/technologies/reinforcement-learning.md)) — 6 public demos
- [Vector Search](https://aitinkerers.org/technologies/vector-search) ([Markdown](https://aitinkerers.org/technologies/vector-search.md)) — 12 public demos
- [Video embeddings](https://aitinkerers.org/technologies/video-embeddings) ([Markdown](https://aitinkerers.org/technologies/video-embeddings.md)) — 2 public demos