ICCV 2021 accepted papers on Probabilistic and scientific modeling
20 of the 1,612 papers accepted at ICCV 2021 (1.2%) are on Probabilistic and scientific modeling, compared with 1.8% at ICCV 2019. They fall into 5 topics.
See ICCV 2021 in the interactive map
Submitting to ICCV? 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 · 9 papers
- Bifold and Semantic Reasoning for Pedestrian Behavior Prediction (99 citations)
- Human Trajectory Prediction via Counterfactual Analysis (98 citations)
- Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis (91 citations)
- Where Are You Heading? Dynamic Trajectory Prediction With Expert Goal Examples (84 citations)
- Personalized Trajectory Prediction via Distribution Discrimination (69 citations)
- On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors (57 citations)
- Safety-Aware Motion Prediction With Unseen Vehicles for Autonomous Driving (30 citations)
- Prediction by Anticipation: An Action-Conditional Prediction Method Based on Interaction Learning (6 citations)
- Sensor-Guided Optical Flow (6 citations)
Uncertainty and Gaussian processes · 5 papers
- Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation (114 citations)
- Energy-Based Open-World Uncertainty Modeling for Confidence Calibration (59 citations)
- Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval (48 citations)
- Bayesian Deep Basis Fitting for Depth Completion With Uncertainty (30 citations)
- Fast and Efficient DNN Deployment via Deep Gaussian Transfer Learning (7 citations)
Variational and generative sampling · 4 papers
- Likelihood-Based Diverse Sampling for Trajectory Forecasting (29 citations)
- JEM++: Improved Techniques for Training JEM (16 citations)
- Manifold Matching via Deep Metric Learning for Generative Modeling (12 citations)
- Semantic Perturbations With Normalizing Flows for Improved Generalization (7 citations)
Causal discovery · 1 paper
- Causal Attention for Unbiased Visual Recognition (136 citations)
