TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: Semantic Video Understanding

3 pointsby Beefin12 months ago

1 comment

Beefin12 months ago
hey HN,<p>We&#x27;re all NLP &amp; CV engineers, and just launched what seems to be the first video embedding model: <a href="https:&#x2F;&#x2F;learn.mixpeek.com&#x2F;vuse-v1-release&#x2F;" rel="nofollow">https:&#x2F;&#x2F;learn.mixpeek.com&#x2F;vuse-v1-release&#x2F;</a><p>here are some example semantic queries:<p><a href="https:&#x2F;&#x2F;mixpeek.com&#x2F;video?q=breaking+the+ice" rel="nofollow">https:&#x2F;&#x2F;mixpeek.com&#x2F;video?q=breaking+the+ice</a> <a href="https:&#x2F;&#x2F;mixpeek.com&#x2F;video?q=human+connection" rel="nofollow">https:&#x2F;&#x2F;mixpeek.com&#x2F;video?q=human+connection</a><p>as you can see, these are not literal queries they&#x27;re colloquialisms. which can&#x27;t be done with simple transcription&#x2F;object detection models or even CLIP.<p>we deploy in our customers&#x27; VPC, and give you full control of the embeddings.