Top all-time · #11246
Sieve
Company blog · sievedata.com/blog · on HN as mvoodarlaaidata
Sieve is the company blog at sievedata.com, writing about ai and data. Since 2022, 6 different Hacker News readers have linked it 26 times. No feed was found, so read it on the site itself.
High-quality video, audio, image, and interaction data for frontier AI.
Most-linked posts?
- /3 people · 4 mentions · first linked 2024-04-30
What Hacker News says?
Congrats on the launch! I work at Sieve ( https://www.sievedata.com/ ). We do a bunch of stuff with AI and video. Excited to check this out :)
Comment linking /
on “Show HN: Revideo – Create Videos with Code”Submitted Eye Contact Correction: Redirecting the eyes to look at the camera as a story · 164 points
HN discussionReally cool application. Just a heads up – your main website is showing an error. You might want to fix it since your post is gaining traction. Here's the link: https://www.sievedata.com/ The error message reads: 'Application error: a client-side exception has occurred (check the browser console for more details).'
Comment linking /
on “Eye Contact Correction: Redirecting the eyes to look at the camera”Submitted Show HN: Processing 24 hours of video in ten minutes as a story · 77 points
HN discussionBTW your main site is throwing an error. Probably want to edit since your post is growing. https://www.sievedata.com/ Application error: a client-side exception has occurred (see the browser console for more information).
Comment linking /
on “Eye Contact Correction: Redirecting the eyes to look at the camera”Submitted Launch HN: Sieve (YC W22) – Pluggable APIs for Video Search as a story · 71 points
HN discussionOriginal dev here. That's right, NVIDIA has a version available which we reference in our blog. 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…
Comment linking /blog/eye-contact-correction-gaze-correction-api
on “Eye Contact Correction: Redirecting the eyes to look at the camera”Submitted SieveSync: High-quality, zero-shot lipsync built with MuseTalk and LivePortrait as a story · 4 points
HN discussionhttps://sievedata.com seems very promising, a search engine for videos, with specific tags, sounds like a very good idea. I'd like the same for all my photos and videos: that would be so much easier to find specific pictures by keywords
Comment linking /
on “The YC Winter 2022 Batch”Submitted Show HN: State of the art audio enhance (open source AudioSR and DeepFilterNet) as a story · 4 points
HN discussionHey HN! I’m one of the creators of Sieve ( https://sievedata.com/ ), and we’re happy to be sharing this with all of you! Sieve is an API that helps you store, process, and automatically search your video data–instantly and efficiently. Just think 10 cameras recording footage at 30 FPS, 24/7. That would be 27 million frames generated in a single day. The videos might be searchable by timestamp, but finding moments of…
Comment linking /faq
on “Show HN: Processing 24 hours of video in ten minutes”Submitted Running Meta's SAM2 2x faster as a story · 3 points
HN discussionThanks for the thoughtful questions! 1. People have definitely tried this in the past in terms of having similar tech, but I don't think anyone has sanely approached it at the same angle. We're seeing so many more companies like EquipmentShare ( https://www.equipmentshare.com/ ), UpKeep ( https://www.upkeep.com/ ), Spot AI ( https://www.spot.ai/ ) and others which are building core software for industries without ne…
Comment linking /faq
on “Launch HN: Sieve (YC W22) – Pluggable APIs for Video Search”Submitted AI active speaker detection on video with a 90% speedup as a story · 3 points
HN discussionYoutube Video Transcriptions Submit a link to generate a PDF with AI-generated summary and a full transcription. Please consider contributing: https://github.com/technoabsurdist/transcript.ai Thanks Sieve for the credits. Check them out here: https://www.sievedata.com/
Comment linking /
on “YouTube Transcriptions with AI-Generated Summaries”Submitted The most cost-effective audio transcription API as a story · 3 points
HN discussionHey folks! We just built a cost-effective, lightweight way to generate audiovisual summaries for videos. * 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.sie…
Comment linking /blog/describe-video-summary-beta-launch
on “Describe Beta: The most descriptive audiovisual summaries for videos”Submitted State of the art AI dubbing, built for developers as a story · 2 points
HN discussionSubmitted Building a robust ball tracking system for sports with SAM 2 as a story · 1 points
HN discussionSubmitted Guide to pure-audio and audiovisual speaker recognition techniques as a story · 1 points
HN discussionSubmitted Finding highlights in long-form video automatically with custom search terms as a story · 1 points
HN discussionSubmitted AI-generated sound effects for stock videos using CogVLM and AudioLDM as a story · 1 points
HN discussionSubmitted Improving on open-source for fast, high-quality AI lipsyncing as a story · 1 points
HN discussion