Variational Inference

Vector-quantized Variational Autoencoder for Phase-aware Speech Enhancement Interspeech 2022 VICE: Variational Interpretable Concept Embeddings NeurIPS 2022 VIM: Variational Independent Modules for Video Prediction CLeaR 2022 Wasserstein Iterative Networks for Barycenter Estimation NeurIPS 2022 Weakly-Supervised Action Transition Learning for Stochastic Human Motion Prediction CVPR 2022 Weakly supervised causal representation learning NeurIPS 2022 Weakly-Supervised Generation and Grounding of Visual Descriptions With Conditional Generative Models CVPR 2022 3D Video Stabilization With Depth Estimation by CNN-Based Optimization CVPR 2021 A Benchmark of Dynamical Variational Autoencoders Applied to Speech Spectrogram Modeling Interspeech 2021 Accelerating Continuous Normalizing Flow with Trajectory Polynomial Regularization AAAI 2021 A Contrastive Learning Approach for Training Variational Autoencoder Priors NeurIPS 2021 A Deep Decomposable Model for Disentangling Syntax and Semantics in Sentence Representation EMNLP 2021 A Differentiable Point Process with Its Application to Spiking Neural Networks ICML 2021 A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing EMNLP 2021 A Generalised Linear Model Framework for β-Variational Autoencoders based on Exponential Dispersion Families JMLR 2021 A Hierarchical VAE for Calibrating Attributes while Generating Text using Normalizing Flow ACL 2021 A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction ICCV 2021 A Learned Conditional Prior for the VAE Acoustic Space of a TTS System Interspeech 2021 A Mean-Field Variational Inference Approach to Deep Image Prior for Inverse Problems in Medical Imaging MIDL 2021 Amortized Variational Inference for Simple Hierarchical Models NeurIPS 2021 APo-VAE: Text Generation in Hyperbolic Space NAACL 2021 ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables ICML 2021 A Scalable Gradient Free Method for Bayesian Experimental Design with Implicit Models AISTATS 2021 Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation CVPR 2021 Audio2Gestures: Generating Diverse Gestures From Speech Audio With Conditional Variational Autoencoders ICCV 2021