A new efficient transformer backbone, CoDAT, achieves competitive action recognition accuracy at a fraction of the latency and energy of existing models on edge hardware.
Vu: Edge computing-enabled video usefulness detection and its application in large-scale video surveillance systems,
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
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition
A new efficient transformer backbone, CoDAT, achieves competitive action recognition accuracy at a fraction of the latency and energy of existing models on edge hardware.