ECCV 2024 accepted papers on Probabilistic and scientific modeling
22 of the 2,387 papers accepted at ECCV 2024 (0.9%) are on Probabilistic and scientific modeling, compared with 1.1% at ECCV 2022. They fall into 6 topics.
See ECCV 2024 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
Molecules and proteins · 8 papers
- "SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow" (135 citations)
- UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction (62 citations)
- Progressive Pretext Task Learning for Human Trajectory Prediction (38 citations)
- Bidirectional Progressive Transformer for Interaction Intention Anticipation (8 citations)
- Adaptive Human Trajectory Prediction via Latent Corridors (6 citations)
- This Probably Looks Exactly Like That: An Invertible Prototypical Network (6 citations)
- Risk-Aware Self-Consistent Imitation Learning for Trajectory Planning in Autonomous Driving (3 citations)
- Beyond the Data Imbalance: Employing the Heterogeneous Datasets for Vehicle Maneuver Prediction (1 citation)
Uncertainty and Gaussian processes · 4 papers
- "A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimation" (7 citations)
- Bayesian Evidential Deep Learning for Online Action Detection (4 citations)
- Optimization-based Uncertainty Attribution Via Learning Informative Perturbations (3 citations)
- Imaging with Confidence: Uncertainty Quantification for High-dimensional Undersampled MR Images (1 citation)
