UniV2D is a dual-branch network that lets high-level saliency masks guide low-level image restoration and lets restored features improve saliency detection, outperforming prior separate-stage methods on underwater benchmarks.
Enhanced-alignment measure for binary foreground map evaluation
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 6years
2026 6roles
baseline 1polarities
baseline 1representative citing papers
Camo-M3FD is a curated visible-thermal benchmark dataset for cross-spectral camouflaged pedestrian detection, with annotations and baseline evaluations showing the value of fusion.
MHENet enhances RGB texture and depth geometry features hierarchically with dedicated modules before adaptive fusion, outperforming prior RGB-D COD methods on four benchmarks.
BASFNet fuses boundary-aware frequency-domain edge exploration with spatial core segmentation and interaction modules to outperform prior methods on camouflaged object detection benchmarks.
EviRCOD integrates reference-guided deformable encoding, uncertainty-aware evidential decoding, and boundary refinement to achieve state-of-the-art performance on referring camouflaged object detection benchmarks with calibrated uncertainty.
CATP prunes low-confidence tokens in COD Transformers and uses dual-path compensation to cut computation while preserving segmentation accuracy on boundary regions.
citing papers explorer
-
UniV2D: Bridging Visual Restoration and Semantic Perception for Underwater Salient Object Detection
UniV2D is a dual-branch network that lets high-level saliency masks guide low-level image restoration and lets restored features improve saliency detection, outperforming prior separate-stage methods on underwater benchmarks.
-
Camo-M3FD: A New Benchmark Dataset for Cross-Spectral Camouflaged Pedestrian Detection
Camo-M3FD is a curated visible-thermal benchmark dataset for cross-spectral camouflaged pedestrian detection, with annotations and baseline evaluations showing the value of fusion.
-
Modality-Specific Hierarchical Enhancement for RGB-D Camouflaged Object Detection
MHENet enhances RGB texture and depth geometry features hierarchically with dedicated modules before adaptive fusion, outperforming prior RGB-D COD methods on four benchmarks.
-
Exploring Boundary-Aware Spatial-Frequency Fusion for Camouflaged Object Detection
BASFNet fuses boundary-aware frequency-domain edge exploration with spatial core segmentation and interaction modules to outperform prior methods on camouflaged object detection benchmarks.
-
EviRCOD: Evidence-Guided Probabilistic Decoding for Referring Camouflaged Object Detection
EviRCOD integrates reference-guided deformable encoding, uncertainty-aware evidential decoding, and boundary refinement to achieve state-of-the-art performance on referring camouflaged object detection benchmarks with calibrated uncertainty.
-
CATP: Confidence-Aware Token Pruning for Camouflaged Object Detection
CATP prunes low-confidence tokens in COD Transformers and uses dual-path compensation to cut computation while preserving segmentation accuracy on boundary regions.