ICCV 2021 accepted papers on Learning theory and algorithms
22 of the 1,612 papers accepted at ICCV 2021 (1.4%) are on Learning theory and algorithms, compared with 1.9% at ICCV 2019. They fall into 7 topics.
See ICCV 2021 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
Matrix and tensor methods · 6 papers
- GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognition (34 citations)
- Transforms Based Tensor Robust PCA: Corrupted Low-Rank Tensors Recovery via Convex Optimization (33 citations)
- Square Root Marginalization for Sliding-Window Bundle Adjustment (25 citations)
- Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling? (21 citations)
- Low-Rank Tensor Completion by Approximating the Tensor Average Rank (12 citations)
- Generalized Shuffled Linear Regression (8 citations)
Prediction and decision losses · 5 papers
- Large-Scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification (155 citations)
- Uniformity in Heterogeneity: Diving Deep Into Count Interval Partition for Crowd Counting (50 citations)
- Learning Multiple Pixelwise Tasks Based on Loss Scale Balancing (23 citations)
- Self-Born Wiring for Neural Trees (7 citations)
- Statistically Consistent Saliency Estimation (4 citations)
Clustering · 4 papers
- Multi-VAE: Learning Disentangled View-Common and View-Peculiar Visual Representations for Multi-View Clustering (160 citations)
- One-Pass Multi-View Clustering for Large-Scale Data (145 citations)
- Localized Simple Multiple Kernel K-Means (53 citations)
- Graph Constrained Data Representation Learning for Human Motion Segmentation (7 citations)
Optimal transport · 4 papers
Sample complexity · 1 paper
- VSAC: Efficient and Accurate Estimator for H and F (34 citations)
Kernels and regression theory · 1 paper
- Kernel Methods in Hyperbolic Spaces (41 citations)
