DG-STA builds dynamic graphs from hand skeletons, applies spatial-temporal self-attention to learn features, and uses a mask to cut cost by 99%, outperforming prior methods on DHG-14/28 and SHREC'17.
Dropout: a simple way to prevent neural networks from overfitting
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2019 4verdicts
UNVERDICTED 4representative citing papers
A semi-supervised feature-level attribute manipulation method for fashion images that matches manipulated feature distributions to real features to support both instance retrieval and attribute editing.
Hierarchical multigraph GCNs applied to superpixels achieve competitive or superior accuracy to CNNs on standard image classification benchmarks.
A CNN model trained with pseudo-label semi-supervised learning reports higher AUC than a supervised baseline on the PCam histopathology dataset.
citing papers explorer
-
Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention
DG-STA builds dynamic graphs from hand skeletons, applies spatial-temporal self-attention to learn features, and uses a mask to cut cost by 99%, outperforming prior methods on DHG-14/28 and SHREC'17.
-
Semi-supervised Feature-Level Attribute Manipulation for Fashion Image Retrieval
A semi-supervised feature-level attribute manipulation method for fashion images that matches manipulated feature distributions to real features to support both instance retrieval and attribute editing.
-
Image Classification with Hierarchical Multigraph Networks
Hierarchical multigraph GCNs applied to superpixels achieve competitive or superior accuracy to CNNs on standard image classification benchmarks.
-
Semi-Supervised Learning for Cancer Detection of Lymph Node Metastases
A CNN model trained with pseudo-label semi-supervised learning reports higher AUC than a supervised baseline on the PCam histopathology dataset.