SeamCam quantifies camouflage by computing one minus the highest IoU recoverable from category-conditioned detection proposals against a ground-truth mask, achieving 78.82% agreement with human judgments.
Machine Intelligence Research 20(1), 92–108 (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SeamCam: Quantifying Seamless Camouflage via Multi-Cue Visual Detectability
SeamCam quantifies camouflage by computing one minus the highest IoU recoverable from category-conditioned detection proposals against a ground-truth mask, achieving 78.82% agreement with human judgments.