AI & ML interests

None defined yet.

Recent Activity

Xenova  updated a Space 14 days ago
webml-community/nanochat-webgpu
Xenova  published a Space 14 days ago
webml-community/nanochat-webgpu
Xenova  published a Space about 1 month ago
webml-community/mdbr-embedding-webgpu
View all activity

Update files

#2 opened about 2 months ago by
Xenova
Xenova 
posted an update 2 months ago
view post
Post
8685
Okay this is insane... WebGPU-accelerated semantic video tracking, powered by DINOv3 and Transformers.js! 🤯
Demo (+ source code): webml-community/DINOv3-video-tracking

This will revolutionize AI-powered video editors... which can now run 100% locally in your browser, no server inference required (costs $0)! 😍

How does it work? 🤔
1️⃣ Generate and cache image features for each frame
2️⃣ Create a list of embeddings for selected patch(es)
3️⃣ Compute cosine similarity between each patch and the selected patch(es)
4️⃣ Highlight those whose score is above some threshold

... et voilà! 🥳

You can also make selections across frames to improve temporal consistency! This is super useful if the object changes its appearance slightly throughout the video.

Excited to see what the community builds with it!
  • 1 reply
·

link from main model

#1 opened 3 months ago by
victor