CVPR 2017 accepted papers on Graph learning
15 of the 783 papers accepted at CVPR 2017 (1.9%) are on Graph learning, compared with 1.6% at CVPR 2016. They fall into 4 topics.
See CVPR 2017 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
Graph algorithms and clustering · 8 papers
- Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications (107 citations)
- Provable Self-Representation Based Outlier Detection in a Union of Subspaces (99 citations)
- Alternating Direction Graph Matching (57 citations)
- A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching (46 citations)
- Binary Constraint Preserving Graph Matching (26 citations)
- A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problems (24 citations)
- Non-Uniform Subset Selection for Active Learning in Structured Data (23 citations)
- Online Graph Completion: Multivariate Signal Recovery in Computer Vision (5 citations)
Graph self-supervised learning · 4 papers
- Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs (1,334 citations)
- Interpretable Structure-Evolving LSTM (94 citations)
- Zero Shot Learning via Multi-Scale Manifold Regularization (44 citations)
- A Graph Regularized Deep Neural Network for Unsupervised Image Representation Learning (33 citations)
Knowledge and temporal graphs · 2 papers
- Scene Graph Generation by Iterative Message Passing (1,254 citations)
- The More You Know: Using Knowledge Graphs for Image Classification (338 citations)
GNN architectures · 1 paper
- DeepNav: Learning to Navigate Large Cities (56 citations)
