CVPR 2017 accepted papers on Probabilistic and scientific modeling
18 of the 783 papers accepted at CVPR 2017 (2.3%) are on Probabilistic and scientific modeling, compared with 1.7% at CVPR 2016. They fall into 4 topics.
See CVPR 2017 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
- FlowNet 2.0: Evolution of Optical Flow Estimation With Deep Networks (3,371 citations)
- Optical Flow Estimation Using a Spatial Pyramid Network (1,433 citations)
- Accurate Optical Flow via Direct Cost Volume Processing (226 citations)
- Deep Structured Learning for Facial Action Unit Intensity Estimation (134 citations)
- Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation (80 citations)
- Robust Interpolation of Correspondences for Large Displacement Optical Flow (71 citations)
- S2F: Slow-To-Fast Interpolator Flow (25 citations)
- Additive Component Analysis (5 citations)
Variational and generative sampling · 6 papers
- Infinite Variational Autoencoder for Semi-Supervised Learning (74 citations)
- Factorized Variational Autoencoders for Modeling Audience Reactions to Movies (63 citations)
- A Non-Convex Variational Approach to Photometric Stereo Under Inaccurate Lighting (56 citations)
- Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold (36 citations)
- ShapeOdds: Variational Bayesian Learning of Generative Shape Models (5 citations)
- Multi-Modal Mean-Fields via Cardinality-Based Clamping (2 citations)
Uncertainty and Gaussian processes · 3 papers
- Soft-Margin Mixture of Regressions (25 citations)
- Personalizing Gesture Recognition Using Hierarchical Bayesian Neural Networks (22 citations)
- Bayesian Supervised Hashing (15 citations)
Causal discovery · 1 paper
- Discovering Causal Signals in Images (206 citations)
