CVPR 2019 accepted papers on Graph learning
36 of the 1,294 papers accepted at CVPR 2019 (2.8%) are on Graph learning, compared with 1.3% at CVPR 2018. They fall into 4 topics.
See CVPR 2019 in the interactive map
Submitting to CVPR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Knowledge and temporal graphs · 23 papers
- Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition (2,091 citations)
- Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition (1,272 citations)
- Multi-Label Image Recognition With Graph Convolutional Networks (1,264 citations)
- Skeleton-Based Action Recognition With Directed Graph Neural Networks (966 citations)
- Auto-Encoding Scene Graphs for Image Captioning (860 citations)
- Learning to Compose Dynamic Tree Structures for Visual Contexts (559 citations)
- Graph-Based Global Reasoning Networks (550 citations)
- Semantic Graph Convolutional Networks for 3D Human Pose Regression (521 citations)
- Knowledge-Embedded Routing Network for Scene Graph Generation (434 citations)
- Rethinking Knowledge Graph Propagation for Zero-Shot Learning (380 citations)
- Scene Graph Generation With External Knowledge and Image Reconstruction (330 citations)
- Learning Actor Relation Graphs for Group Activity Recognition (313 citations)
and 11 more in the interactive map.
Graph algorithms and clustering · 5 papers
- Linkage Based Face Clustering via Graph Convolution Network (201 citations)
- Learning to Cluster Faces on an Affinity Graph (149 citations)
- Biologically-Constrained Graphs for Global Connectomics Reconstruction (31 citations)
- Explore-Exploit Graph Traversal for Image Retrieval (31 citations)
- A Convex Relaxation for Multi-Graph Matching
Graph self-supervised learning · 4 papers
- Graphonomy: Universal Human Parsing via Graph Transfer Learning (198 citations)
- Label Efficient Semi-Supervised Learning via Graph Filtering (173 citations)
- Adaptively Connected Neural Networks (69 citations)
- Data Representation and Learning With Graph Diffusion-Embedding Networks (31 citations)
GNN architectures · 4 papers
- Explainability Methods for Graph Convolutional Neural Networks (531 citations)
- Edge-Labeling Graph Neural Network for Few-Shot Learning (528 citations)
- Semi-Supervised Learning With Graph Learning-Convolutional Networks (484 citations)
- Exploiting Edge Features for Graph Neural Networks (293 citations)
