CVPR 2022 accepted papers on Probabilistic and scientific modeling
34 of the 2,077 papers accepted at CVPR 2022 (1.6%) are on Probabilistic and scientific modeling, compared with 1.2% at CVPR 2021. They fall into 5 topics.
See CVPR 2022 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
Molecules and proteins · 12 papers
- Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion (302 citations)
- GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction With Relational Reasoning (194 citations)
- Global Matching With Overlapping Attention for Optical Flow Estimation (95 citations)
- LTP: Lane-Based Trajectory Prediction for Autonomous Driving (84 citations)
- Non-Probability Sampling Network for Stochastic Human Trajectory Prediction (77 citations)
- HLRTF: Hierarchical Low-Rank Tensor Factorization for Inverse Problems in Multi-Dimensional Imaging (61 citations)
- Uncertainty-Guided Probabilistic Transformer for Complex Action Recognition (46 citations)
- Motron: Multimodal Probabilistic Human Motion Forecasting (38 citations)
- MotionAug: Augmentation With Physical Correction for Human Motion Prediction (26 citations)
- A Probabilistic Graphical Model Based on Neural-Symbolic Reasoning for Visual Relationship Detection (19 citations)
- Contrastive Conditional Neural Processes (12 citations)
- AIM: An Auto-Augmenter for Images and Meshes (1 citation)
Variational and generative sampling · 11 papers
- RecDis-SNN: Rectifying Membrane Potential Distribution for Directly Training Spiking Neural Networks (85 citations)
- Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression (56 citations)
- CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Data (22 citations)
- Split Hierarchical Variational Compression (16 citations)
- Rethinking Controllable Variational Autoencoders (15 citations)
- Super-Fibonacci Spirals: Fast, Low-Discrepancy Sampling of SO(3) (14 citations)
- Glass: Geometric Latent Augmentation for Shape Spaces (12 citations)
- Robust Outlier Detection by De-Biasing VAE Likelihoods (11 citations)
- Generative Flows With Invertible Attentions (9 citations)
- Efficient Maximal Coding Rate Reduction by Variational Forms (5 citations)
- Bi-Level Doubly Variational Learning for Energy-Based Latent Variable Models (4 citations)
Uncertainty and Gaussian processes · 6 papers
- Bayesian Invariant Risk Minimization (52 citations)
- Deep Depth From Focus With Differential Focus Volume (43 citations)
- A Variational Bayesian Method for Similarity Learning in Non-Rigid Image Registration (17 citations)
- Learning Structured Gaussians To Approximate Deep Ensembles (7 citations)
- Understanding Uncertainty Maps in Vision With Statistical Testing (4 citations)
- Gaussian Process Modeling of Approximate Inference Errors for Variational Autoencoders (2 citations)
Differential equations and PDEs · 3 papers
- NODEO: A Neural Ordinary Differential Equation Based Optimization Framework for Deformable Image Registration (36 citations)
- Learning Optimal K-Space Acquisition and Reconstruction Using Physics-Informed Neural Networks (22 citations)
- TO-FLOW: Efficient Continuous Normalizing Flows With Temporal Optimization Adjoint With Moving Speed (3 citations)
Causal discovery · 2 papers
- Do Learned Representations Respect Causal Relationships? (5 citations)
- Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets (1 citation)
