Comparative Analysis of Fine-Tuning I3D and SlowFast Networks for Action Recognition in Surveillance Videos^†

INIS

• surveillance 100%
• tuning 100%
• datasets 75%
• applications 50%
• data 50%
• classification 50%
• performance 25%
• computers 25%
• vision 25%
• humans 25%
• layers 25%
• availability 25%
• accuracy 25%
• learning 25%
• resources 25%
• trains 25%
• metrics 25%

Computer Science

• Action Recognition 100%
• surveillance video 100%
• Comparative Analysis 100%
• Use Case 50%
• Data Availability 50%
• Video Surveillance 50%
• Transfer Learning 50%
• Computer Vision Applications 50%
• human action recognition 50%
• Resource Availability 50%
• 3-Dimensional Convolutional Neural Networks 50%