Joshua
Xenova
AI & ML interests
None yet
Recent Activity
new activity
about 19 hours ago
webml-community/smolvlm-realtime-webgpu:Upload Gens3.html
posted
an
update
2 days ago
Okay this is insane... WebGPU-accelerated semantic video tracking, powered by DINOv3 and Transformers.js! 🤯
Demo (+ source code): https://huggingface.co/spaces/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!
updated
a Space
2 days ago
webml-community/DINOv3-video-tracking