A wavelet backbone with ray-origin attention encoding improves efficiency and self-comparison accuracy for human-object interaction detection, but remains below the FGAHOI baseline in accuracy despite fewer parameters.
Hier r-cnn: Instance- level human parts detection and a new benchmark,
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Conceptualizing Multi-scale Wavelet Attention and Ray-based Encoding for Human-Object Interaction Detection
A wavelet backbone with ray-origin attention encoding improves efficiency and self-comparison accuracy for human-object interaction detection, but remains below the FGAHOI baseline in accuracy despite fewer parameters.