ICCV 2019 accepted papers on Learning theory and algorithms
20 of the 1,075 papers accepted at ICCV 2019 (1.9%) are on Learning theory and algorithms, compared with 3.5% at ICCV 2017. They fall into 7 topics.
See ICCV 2019 in the interactive map
Submitting to ICCV? 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
Combinatorial and search optimization · 7 papers
- A Quaternion-Based Certifiably Optimal Solution to the Wahba Problem With Outliers (81 citations)
- Closed-Form Optimal Two-View Triangulation Based on Angular Errors (25 citations)
- Consensus Maximization Tree Search Revisited (24 citations)
- New Convex Relaxations for MRF Inference With Unknown Graphs (7 citations)
- Pareto Meets Huber: Efficiently Avoiding Poor Minima in Robust Estimation (3 citations)
- Bottleneck Potentials in Markov Random Fields (2 citations)
- Parametric Majorization for Data-Driven Energy Minimization Methods (2 citations)
Clustering · 4 papers
- Reciprocal Multi-Layer Subspace Learning for Multi-View Clustering (155 citations)
- Video Face Clustering With Unknown Number of Clusters (67 citations)
- Is an Affine Constraint Needed for Affine Subspace Clustering? (22 citations)
- Subspace Structure-Aware Spectral Clustering for Robust Subspace Clustering (4 citations)
Matrix and tensor methods · 3 papers
Prediction and decision losses · 3 papers
- Bayesian Loss for Crowd Count Estimation With Point Supervision (685 citations)
- Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression (332 citations)
- AM-LFS: AutoML for Loss Function Search (67 citations)
Sample complexity · 1 paper
Kernels and regression theory · 1 paper
- Fast-deepKCF Without Boundary Effect (17 citations)
