DRRNet is a four-stage camouflaged object detection network that fuses global and local features and then applies two rounds of reverse refinement to sharpen object boundaries.
Extremality of graph entropy based on Laplacian degrees of k-uniform hypergraphs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The graph entropy describes the structural information of graph. Motivated by the definition of graph entropy in general graphs, the graph entropy of hypergraphs based on Laplacian degree are defined. Some results on graph entropy of simple graphs are extended to k-uniform hypergraphs. Using an edge-moving operation, the maximum and minimum graph entropy based on Laplacian degrees are determined in k-uniform hypertrees, unicyclic k-uniform hypergraphs, bicyclic k-uniform hypergraphs and k-uniform chemical hypertrees, respectively, and the corresponding extremal graphs are determined.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DRRNet: Macro-Micro Feature Fusion and Dual Reverse Refinement for Camouflaged Object Detection
DRRNet is a four-stage camouflaged object detection network that fuses global and local features and then applies two rounds of reverse refinement to sharpen object boundaries.