Presents MMIO benchmark and RTVP method achieving state-of-the-art 42.2% AP in zero-shot industrial defect detection.
Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions , publisher =
4 Pith papers cite this work, alongside 416 external citations. Polarity classification is still indexing.
4
Pith papers citing it
416
external citations · external index
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
MixTGFormer reports state-of-the-art 3D pose estimation errors of 37.6 mm on Human3.6M and 15.7 mm on MPI-INF-3DHP by using parallel GCN-Transformer streams with SE layers for local-global feature fusion.
HSANet uses Efficient Global Attention and hybrid upsampling in a Swin-based architecture to achieve better simultaneous denoising of low-dose PET/CT images than prior methods with a compact model.
YOLO-AMC integrates GAM, Res-CBAM, and SA attention into YOLOv11's neck after removing C2PSA, yielding mAP@0.5 of 0.9917 and real-time FPS on RTX 4090 and Raspberry Pi 5 for crack detection.
citing papers explorer
-
Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline
Presents MMIO benchmark and RTVP method achieving state-of-the-art 42.2% AP in zero-shot industrial defect detection.
-
Dual-stream Spatio-Temporal GCN-Transformer Network for 3D Human Pose Estimation
MixTGFormer reports state-of-the-art 3D pose estimation errors of 37.6 mm on Human3.6M and 15.7 mm on MPI-INF-3DHP by using parallel GCN-Transformer streams with SE layers for local-global feature fusion.
-
Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoising
HSANet uses Efficient Global Attention and hybrid upsampling in a Swin-based architecture to achieve better simultaneous denoising of low-dose PET/CT images than prior methods with a compact model.
-
YOLO-AMC: An Improved YOLO Architecture with Attention Mechanisms for Building Crack Detection
YOLO-AMC integrates GAM, Res-CBAM, and SA attention into YOLOv11's neck after removing C2PSA, yielding mAP@0.5 of 0.9917 and real-time FPS on RTX 4090 and Raspberry Pi 5 for crack detection.