ECCV 2022 accepted papers on Probabilistic and scientific modeling
18 of the 1,645 papers accepted at ECCV 2022 (1.1%) are on Probabilistic and scientific modeling, compared with 1.5% at ECCV 2020. They fall into 5 topics.
See ECCV 2022 in the interactive map
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
Uncertainty and Gaussian processes · 6 papers
- BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks (22 citations)
- Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval (21 citations)
- Latent Discriminant Deterministic Uncertainty (14 citations)
- Uncertainty Quantification in Depth Estimation via Constrained Ordinal Regression (12 citations)
- Improving the Reliability for Confidence Estimation (10 citations)
- Vibration-Based Uncertainty Estimation for Learning from Limited Supervision (2 citations)
Molecules and proteins · 6 papers
- SocialVAE: Human Trajectory Prediction Using Timewise Latents (171 citations)
- Human Trajectory Prediction via Neural Social Physics (144 citations)
- View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums (87 citations)
- Action-Based Contrastive Learning for Trajectory Prediction (60 citations)
- StretchBEV: Stretching Future Instance Prediction Spatially and Temporally (52 citations)
- S2Net: Stochastic Sequential Pointcloud Forecasting (25 citations)
Variational and generative sampling · 3 papers
Causal discovery · 2 papers
- Structural Causal 3D Reconstruction (12 citations)
- GCISG: Guided Causal Invariant Learning for Improved Syn-to-Real Generalization (4 citations)
