Efstratios Gavves

Latest

• SIGMA: Sinkhorn-Guided Masked Video Modeling
• Amortized Equation Discovery in Hybrid Dynamical Systems
• How to Train Neural Field Representations: A Comprehensive Study and Benchmark
• Graph Neural Networks for Learning Equivariant Representations of Neural Networks
• Latent Field Discovery in Interacting Dynamical Systems with Neural Fields
• Modulated Neural ODEs
• Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations
• Towards Open-Vocabulary Video Instance Segmentation
• Graph Switching Dynamical Systems
• BISCUIT: Causal Representation Learning from Binary Interactions
• PC-Reg: A pyramidal prediction–correction approach for large deformation image registration
• PerfU-Net: Baseline infarct estimation from CT perfusion source data for acute ischemic stroke
• Spatio-temporal physics-informed learning: A novel approach to CT perfusion analysis in acute ischemic stroke
• Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems
• Differentiable Mathematical Programming for Object-Centric Representation Learning
• Fake It Till You Make It: Towards Accurate Near-Distribution Novelty Detection
• Modelling Long Range Dependencies in N-D: From Task-Specific to a General Purpose CNN
• Scalable Subset Sampling with Neural Conditional Poisson Networks
• DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer
• Dynamic Transformer for Few-shot Instance Segmentation
• WeakSTIL: weak whole-slide image level stromal tumor infiltrating lymphocyte scores are all you need
• Batch Bayesian Optimization on Permutations using the Acquisition Weighted Kernel
• 3D Equivariant Graph Implicit Functions
• Delta Distillation for Efficient Video Processing
• Continual Learning of Dynamical Systems With Competitive Federated Reservoir Computing
• Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network
• CITRIS - Causal Identifiability from Temporal Intervened Sequences
• Dynamic Prototype Convolution Network for Few-shot Semantic Segmentation
• NFormer: Robust Person Re-identification with Neighbor Transformer
• Efficient Neural Causal Discovery without Acyclicity Constraints
• Stability Regularization for Discrete Representation Learning
• WeakSTIL: Weak whole-slide image level stromal tumor infiltrating lymphocyte scores are all you need
• Roto-translated Local Coordinate Frames For Interacting Dynamical Systems
• Sparse-Shot Learning With Exclusive Cross-Entropy for Extremely Many Localisations
• Neural Feature Matching in Implicit 3D Representations
• Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders
• Unsharp Mask Guided Filtering
• Rotation Equivariant Siamese Networks for Tracking
• Categorical Normalizing Flows via Continuous Transformations
• Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning
• Domain- and task-specific transfer learning for medical segmentation tasks
• Model Decay in Long-Term Tracking
• Quasibinary Classifier for Images with Zero and Multiple Labels
• Self-Selective Context for Interaction Recognition
• Automatic Triage of 12‐Lead ECGs Using Deep Convolutional Neural Networks
• PointMixup: Augmentation for Point Clouds
• Low Bias Low Variance Gradient Estimates for Boolean Stochastic Networks
• Siamese Tracking of Cell Behaviour Patterns