Audio–visual collaborative representation learning for Dynamic Saliency Prediction

Computer Science

• Representation Learning 100%
• Collaborative Representation 100%
• Visual Feature 50%
• Residual Neural Network 50%
• Attention (Machine Learning) 50%
• Spatial Location 50%
• Prediction Model 50%
• Visual Modality 50%
• Visual Informations 50%
• Motion Information 50%
• Scene Understanding 50%
• Selective Attention 50%
• Surrounding Scene 50%