Search Results for author:
Found 2 papers, 2 papers with code
Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment
The first LA-GCN module constructs an aesthetics-related graph in the coordinate space and performs reasoning over spatial nodes.
Weakly Supervised Coupled Networks for Visual Sentiment Analysis
The second branch utilizes both the holistic and localized information by coupling the sentiment map with deep features for robust classification.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
