A hybrid 3D Swin Transformer with temporal patch shift and class-masked attention improves radar object detection accuracy on CRUW at lower computational cost.
Is space-time attention all you need for video understanding? In International Conference on Machine Learning , 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Mask-RadarNet: Enhancing Transformer With Spatial-Temporal Semantic Context for Radar Object Detection in Autonomous Driving
A hybrid 3D Swin Transformer with temporal patch shift and class-masked attention improves radar object detection accuracy on CRUW at lower computational cost.