ECCV 2020 accepted papers on Probabilistic and scientific modeling
21 of the 1,358 papers accepted at ECCV 2020 (1.5%) are on Probabilistic and scientific modeling, compared with 0.8% at ECCV 2018. They fall into 5 topics.
See ECCV 2020 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
Variational and generative sampling · 11 papers
- The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement (106 citations)
- Learning latent representations across multiple data domains using Lifelong VAEGAN (76 citations)
- SG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenes (49 citations)
- Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders (31 citations)
- Learning Disentangled Representations with Latent Variation Predictability (30 citations)
- Learning Multi-layer Latent Variable Model via Variational Optimization of Short Run MCMC for Approximate Inference (20 citations)
- A Closest Point Proposal for MCMC-based Probabilistic Surface Registration (19 citations)
- MPCC: Matching Priors and Conditionals for Clustering (4 citations)
- Truncated Inference for Latent Variable Optimization Problems: Application to Robust Estimation and Learning (2 citations)
- LIMP: Learning Latent Shape Representations with Metric Preservation Priors
- Regularization with Latent Space Virtual Adversarial Training
Molecules and proteins · 7 papers
- Implicit Latent Variable Model for Scene-Consistent Motion Forecasting (158 citations)
- LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation (110 citations)
- DSDNet: Deep Structured self-Driving Network (100 citations)
- Improving Optical Flow on a Pyramid Level (45 citations)
- Testing the Safety of Self-driving Vehicles by Simulating Perception and Prediction (21 citations)
- It is not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
- V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction
Uncertainty and Gaussian processes · 1 paper
- TRADI: Tracking Deep Neural network Weight Distributions (43 citations)
Bayesian optimization · 1 paper
- AutoSimulate: (Quickly) Learning Synthetic Data Generation (23 citations)
