CASWiT reaches 66.37% mIoU on FLAIR-HUB and 49.2% on URUR by injecting low-resolution context via stage-wise cross-attention in a dual-branch Swin architecture with SimMIM-style pretraining.
Deep residual learning for image recognition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
GraphFusion3D reports improved 3D object detection accuracy on SUN RGB-D and ScanNetV2 by combining adaptive image-to-point fusion with multi-scale graph reasoning on proposals.
citing papers explorer
-
Context-Aware Semantic Segmentation via Stage-Wise Attention
CASWiT reaches 66.37% mIoU on FLAIR-HUB and 49.2% on URUR by injecting low-resolution context via stage-wise cross-attention in a dual-branch Swin architecture with SimMIM-style pretraining.
-
GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection
GraphFusion3D reports improved 3D object detection accuracy on SUN RGB-D and ScanNetV2 by combining adaptive image-to-point fusion with multi-scale graph reasoning on proposals.