Comparing LSTM and Transformer for Video Depth Estimation

Keyphrases

• Transformer 100%
• Video Depth Estimation 100%
• Memory Models 40%
• Depth Estimation 40%
• Monocular Depth Estimation 20%
• Transformer Encoder 20%
• Modeling Techniques 20%
• Prediction Task 20%
• Network Architecture 20%
• Sequence Modeling 20%
• Robotic Applications 20%
• Sequence Prediction 20%
• Long Sequence 20%
• Memory Network 20%
• Simultaneous Localization and Mapping 20%
• Long-range Dependence 20%
• Transformer Architecture 20%
• Transformer Module 20%
• Depth Map Prediction 20%
• Memory Module 20%
• Similar Sequences 20%
• Depth Prediction 20%
• Depth Map Estimation 20%
• Temporal Cues 20%
• Monocular Video 20%
• Spatial Perception 20%
• Two-potential Approach 20%
• Temporal Signal 20%
• Optical Flow Features 20%

Computer Science

• Long Short-Term Memory Network 100%
• Depth Estimation 100%
• Memory Model 33%
• Robotics Application 16%
• Temporal Information 16%
• Simultaneous localization and mapping 16%
• Range Dependency 16%
• Map Estimation 16%
• Lstm 16%