y0news
← Feed
Back to feed
🧠 AI Neutral

Micro-expression Recognition Based on Dual-branch Feature Extraction and Fusion

arXiv – CS AI|Mingjie Zhang, Bo Li, Wanting Liu, Hongyan Cui, Yue Li, Qingwen Li, Hong Li, Ge Gao||1 views
🤖AI Summary

Researchers developed a dual-branch neural network for micro-expression recognition that combines residual and Inception networks with parallel attention mechanisms. The method achieved 74.67% accuracy on the CASME II dataset, significantly outperforming existing approaches like LBP-TOP by over 11%.

Key Takeaways
  • New dual-branch network architecture combines residual and Inception networks for better micro-expression detection.
  • Adaptive feature fusion module integrates features from both network branches to improve recognition accuracy.
  • Method achieved 74.67% accuracy on CASME II dataset, beating LBP-TOP by 11.26% and MSMMT by 3.36%.
  • Residual network component addresses gradient vanishing problems in deep learning architectures.
  • Research focuses on detecting subtle, transient facial expressions that are difficult for existing optical flow methods.
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Connect Wallet to AI →How it works
Related Articles