HiResNets use foveated log-polar warps directly inside a residual stream, giving convolution cost that grows logarithmically with resolution and better accuracy on egocentric video benchmarks.
Salisa: Saliency-based input sampling for efficient video object detection, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
HiResNets: Native Full-HD Video Recognition with Foveal Residual Streams
HiResNets use foveated log-polar warps directly inside a residual stream, giving convolution cost that grows logarithmically with resolution and better accuracy on egocentric video benchmarks.