Event Voxel Set Transformer for Spatiotemporal Representation Learning on Event Streams

Computer Science

• Local Information 100%
• Representation Learning 100%
• Action Recognition 100%
• Feature Interaction 100%
• Computational Complexity 50%
• Evaluation Models 50%
• Information Aggregation 50%
• Model Complexity 50%
• Global Feature 50%
• Sparse Representation 50%
• Motion Pattern 50%
• Art Performance 50%
• Challenging Scenario 50%
• Attention (Machine Learning) 50%
• Event Processing 50%
• Embedding Layer 50%
• Self-Attention 50%