Generative Models

Applying the Information Bottleneck Principle to Prosodic Representation Learning Interspeech 2021 ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators ICCV 2021 Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions NeurIPS 2021 ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables ICML 2021 ArtCoder: An End-to-End Method for Generating Scanning-Robust Stylized QR Codes CVPR 2021 ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows CVPR 2021 Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data ICCV 2021 Artistic Style Transfer with Internal-external Learning and Contrastive Learning NeurIPS 2021 ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring CVPR 2021 A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis NeurIPS 2021 A Sliced Wasserstein Loss for Neural Texture Synthesis CVPR 2021 Aspect Sentiment Quad Prediction as Paraphrase Generation EMNLP 2021 A statistical theory of cold posteriors in deep neural networks ICLR 2021 A Structured Observation Distribution for Generative Biological Sequence Prediction and Forecasting ICML 2021 A Survey of Machine Learning-Based Physics Event Generation IJCAI 2021 Asymmetric Bilateral Motion Estimation for Video Frame Interpolation ICCV 2021 Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation CVPR 2021 A Theory of Independent Mechanisms for Extrapolation in Generative Models AAAI 2021 Attack As the Best Defense: Nullifying Image-to-Image Translation GANs via Limit-Aware Adversarial Attack ICCV 2021 Attention-Based Spatial Guidance for Image-to-Image Translation WACV 2021 AttnMove: History Enhanced Trajectory Recovery via Attentional Network AAAI 2021 Attribute Alignment: Controlling Text Generation from Pre-trained Language Models EMNLP 2021 Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion IJCAI 2021 Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting ICLR 2021 A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder ICCV 2021