johanmodin/clifs
Contrastive Language-Image Forensic Search allows free text searching through videos using OpenAI's machine learning model CLIP
This tool helps anyone who needs to find specific moments in video footage without manually watching hours of content. You input your video files and then simply type in a description of what you're looking for, like "a white BMW car" or "a bicyclist with a blue shirt." It then returns video frames that best match your text description. This is ideal for security analysts, media researchers, or anyone reviewing video for specific events or objects.
480 stars. No commits in the last 6 months.
Use this if you need to quickly locate video frames matching free-text descriptions within your video archives.
Not ideal if you need frame-by-frame precision, real-time video analysis for live feeds, or to categorize entire video clips rather than specific frames.
Stars
480
Forks
52
Language
JavaScript
License
Apache-2.0
Category
Last pushed
Mar 15, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/johanmodin/clifs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
kingyiusuen/clip-image-search
Search images with a text or image query, using Open AI's pretrained CLIP model.
aws-samples/amazon-sagemaker-clip-search
Build a machine learning (ML) powered search engine prototype to retrieve and recommend products...
NTUYWANG103/clip-image-search
This code implements a versatile image search engine leveraging the CLIP model and FAISS,...
ItzCrazyKns/Image-Search
Search for similar images using faiss & multimodal embeddings