mvoodarla
Sieve (YC X25) is hiring researchers to build large video datasets for AI labs
Sieve (YC W22) Is Hiring Engineers to Build the Future of Video AI
Sieve (YC W22) Is Hiring Engineers to Build the Future of Video AI
Building a robust ball tracking system for sports with SAM 2
Veo 2: Our video generation model
Sieve (YC W22) Is Hiring Engineers to Build the Future of Video AI
Guide to pure-audio and audiovisual speaker recognition techniques
The model tries to copy the blinks of the original video so it's possible that in other conditions, you'd notice less of this.
Fun to see this feedback though, definitely something worth improving :)
https://www.sievedata.com/blog/eye-contact-correction-gaze-c...
Newer models have come out that allow the same thing to be done and control even more than the eyes.
See here: https://github.com/KwaiVGI/LivePortrait/blob/main/assets/doc...
For web-conferencing, local use is great so NVIDIA's tools are what we recommend in that case.
Would recommend trying it on other videos, it is surprisingly good. Although there definitely are areas to improve.
Sieve (YC W22) Is Hiring Engineers to Build AI Infrastructure for Video
SieveSync: Realistic, zero-shot lipsync pipeline using MuseTalk and LivePortrait
Sieve (YC W22) Is Hiring Engineers to Build Video AI Tools
SieveSync: High-quality, zero-shot lipsync built with MuseTalk and LivePortrait
Sieve (YC W22) Is hiring full stack engineers to build AI developer tools
Running Meta's SAM2 2x faster
Sieve (YC W22) Is hiring engineers to build AI [video] developer tools
Sieve (YC W22) is hiring product engineers to build the future of video AI
API to automate social video editing with AI
Sieve (YC W22) Is Hiring ML engineers (small team, high revenue, AI infra)
Finding highlights in long-form video automatically with custom search terms
Sieve (YC W22) Is hiring ML engineers to build the future of video AI
* Process videos up to 12x faster than realtime * Costs <$0.01 / min of video * Combines visual and audial components
The goal here is not to build a single E2E model but something that could actually be used in production while preserving relatively high quality.
You can try it out yourself here: https://www.sievedata.com/functions/sieve/describe How we built it: https://www.sievedata.com/blog/describe-video-summary-beta-l... The code: https://github.com/sieve-community/describe