VSP-LLM (Visual Speech Processing incorporated with LLMs)


Code: https://github.com/Sally-SH/VSP-LLM?tab=readme-ov-file

Paper: https://arxiv.org/pdf/2402.15151

@deeplearning_ai

🚀 Introducing: Face Landmark Auto-Labeling Toolkit 🧠

Tired of manually annotating facial landmarks? Here's a deep learning-powered desktop app that will change your workflow forever!

🔧 Key Features:
✅ 68-point facial landmark detection (PIPNet + ONNX)
✅ Modern GUI with theme support (Tkinter + TTKBootstrap)
✅ Smart drag-and-drop editing
✅ Batch processing of entire folders
✅ Export as .json and .pts
✅ Real-time dataset statistics

📽️ See it in action:
▶️ Demo Video #1
▶️ Demo Video #2

🌟 Star the repo & share with your community!
🔗 GitHub: https://github.com/Shohruh72/Landmark-Auto-Label

https://github.com/Shohruh72


@deeplearning_ai

🌟 SmolVLM Realtime Inference UI

On-device vision–language in your browser—webcam, video & image. Zero-config HTML/JS powered by llama.cpp.


🚀 Try it: https://github.com/Shohruh72/SmolVLM-UI

Join my channel:
👇👇👇👇👇👇
@MachineLearning_Programming

Source code: Github

🌟 Star the repo & share with your community!

🚀 Refactored HRNet Now Live! 🚀

🔥 Supercharge your computer vision projects with high-resolution HRNet models – fully refactored for easy training/testing!

✅ Multiple ImageNet-pretrained models
✅ Lightning-fast setup
✅ Top-tier accuracy

👉 Check it out & ⭐️ Star the repo if you find it useful!
GitHub: Shohruh72/HRNet

#AI #DeepLearning #OpenSource

@deeplearning_ai

🚀 Generative AI is Taking Over – Will You Lead or Follow? 🚀

⚠️ FREE TRAINING

The AI revolution is here, and top companies are hiring for roles like AI Engineers, Gen AI Experts, and Generative AI Developers.

Register Free Now:
https://live.psitrontech.com

💡 What You’ll Learn:
✅ Master Gen AI on AWS, Azure and GCP
✅ Master GPT, Claude, LLaMA & Stable Diffusion
✅ Build AI-powered applications & AI Agents
✅ Stay ahead with LLMOps & AI strategies

🔥 High demand, low competition – Now is the time to upskill!

⏳ Opportunities like this don’t last forever!

🚀 3DGazeNet: Next-Gen Gaze Estimation! - get instant results with just one click.

Discover how to train powerful gaze estimation models using only synthetic data and weak supervision—no huge real-world datasets needed.
Perfect for AR/VR, HCI, and beyond.
Cutting-edge, open-source, and ready for your next project!

👉 Try it now: https://github.com/Shohruh72/3DGazeNet

#DeepLearning #GazeEstimation #AI

@deeplearning_ai