CVPR 2021 accepted papers on Probabilistic and scientific modeling
20 of the 1,661 papers accepted at CVPR 2021 (1.2%) are on Probabilistic and scientific modeling, compared with 1.8% at CVPR 2020. They fall into 5 topics.
See CVPR 2021 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 · 8 papers
- Trajectory Prediction With Latent Belief Energy-Based Model (90 citations)
- Fast End-to-End Learning on Protein Surfaces (86 citations)
- Interpretable Social Anchors for Human Trajectory Forecasting in Crowds (54 citations)
- Deep Multi-Task Learning for Joint Localization, Perception, and Prediction (48 citations)
- Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers (36 citations)
- Mol2Image: Improved Conditional Flow Models for Molecule to Image Synthesis (22 citations)
- Geo-FARM: Geodesic Factor Regression Model for Misaligned Pre-Shape Responses in Statistical Shape Analysis (6 citations)
- Cluster-Wise Hierarchical Generative Model for Deep Amortized Clustering (5 citations)
Uncertainty and Gaussian processes · 4 papers
- Masksembles for Uncertainty Estimation (87 citations)
- Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression (55 citations)
- Learning an Explicit Weighting Scheme for Adapting Complex HSI Noise (14 citations)
- Bayesian Nested Neural Networks for Uncertainty Calibration and Adaptive Compression (5 citations)
Causal discovery · 3 papers
- CausalVAE: Disentangled Representation Learning via Neural Structural Causal Models (248 citations)
- Generative Interventions for Causal Learning (49 citations)
- Causal Hidden Markov Model for Time Series Disease Forecasting (36 citations)
Dynamical systems · 3 papers
- Physics-Based Iterative Projection Complex Neural Network for Phase Retrieval in Lensless Microscopy Imaging (23 citations)
- Discovering Hidden Physics Behind Transport Dynamics (6 citations)
- NewtonianVAE: Proportional Control and Goal Identification From Pixels via Physical Latent Spaces
Variational and generative sampling · 2 papers
- iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression (40 citations)
- Learning Deep Latent Variable Models by Short-Run MCMC Inference With Optimal Transport Correction (6 citations)
