IUML: Inception U-Net Based Multi-Task Learning for Density Level Classification And Crowd Density Estimation

Keyphrases

• Besides to 33%
• Classification Level 100%
• Classification Task 33%
• CNN-based 33%
• Crowd Density Estimation 100%
• Decoder 33%
• Density Level 100%
• Density Map 66%
• Density Map Estimation 33%
• Encoder 33%
• Encoder-decoder Architecture 33%
• Estimation Task 33%
• Evaluation Criteria 33%
• High-resolution 33%
• Image Resolution 33%
• Image Size 33%
• Image-based 33%
• Inception Module 33%
• Joint Feature 33%
• Learning to Learn 33%
• Multi-loss 33%
• Multi-scale Feature Representation 33%
• Multi-task Learning 100%
• Multiple Evaluation 33%
• Network Training 33%
• People Counting 66%
• Public Safety Management 33%
• Scale Issues 33%
• Scale Problem 33%
• U-Net 100%

Computer Science

• Classification Task 50%
• Convolutional Neural Network 50%
• Evaluation Criterion 50%
• Map Estimation 100%
• Multitask Learning 100%
• U-Net 100%