y0news
← Feed
Back to feed
🧠 AI NeutralImportance 4/10

HSEmotion Team at ABAW-10 Competition: Facial Expression Recognition, Valence-Arousal Estimation, Action Unit Detection and Fine-Grained Violence Classification

arXiv – CS AI|Andrey V. Savchenko, Kseniia Tsypliakova|
🤖AI Summary

HSEmotion Team developed a fast approach for facial emotion analysis using pre-trained EfficientNet models for the ABAW-10 competition. Their method combines confidence-based predictions with multi-layered perceptrons and sliding window smoothing, achieving significant improvements over existing baselines across four emotion recognition tasks.

Key Takeaways
  • HSEmotion Team presented results for the 10th Affective Behavior Analysis in-the-Wild competition focusing on facial emotion understanding.
  • The approach uses pre-trained EfficientNet-based models with confidence thresholds to determine prediction methods.
  • When model confidence is low, facial embeddings are processed through multi-layered perceptrons trained on AffWild2 dataset.
  • The system applies sliding window smoothing to reduce noise in frame-wise predictions.
  • Experimental results showed significant improvements over existing baselines across four ABAW challenge tasks.
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