Meeting #3879
Updated by Evgeniy Pavlovskiy about 4 years ago
Record of seminar: https://youtu.be/xMWuuKEl2SI
1 VoiceFilter from Google https://google.github.io/speaker-id/publications/VoiceFilter/
2 Wavesplit - Июль 2020. SDR 21.0 на WSJ0-mix2 https://arxiv.org/pdf/2002.08933v2.pdf
3 Neural Supersampling for Real-time Rendering (Facebok) https://research.fb.com/wp-content/uploads/2020/06/Neural-Supersampling-for-Real-time-Rendering.pdf (https://neurohive.io/ru/novosti/nejroset-ot-fair-povyshaet-razreshenie-izobrazheniya-v-16-raz/)
4 DeepFaceDrawing: Deep Generation of Face Images from Sketches http://geometrylearning.com/paper/DeepFaceDrawing.pdf (https://neurohive.io/ru/novosti/deepfacedrawing-nejroset-generiruet-izobrazheniya-ljudej-po-sketcham/)
5 Tacotron 2 (without wavenet) https://github.com/NVIDIA/tacotron2 (paper: https://arxiv.org/pdf/1712.05884.pdf)
6 DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation. https://arxiv.org/pdf/2006.04868.pdf
7 LoCo: Local Contrastive Representation Learning, https://arxiv.org/abs/2008.01342 (https://arxiv.org/abs/2008.01342)
8 3D Self-Supervised Methods for Medical Imaging https://arxiv.org/abs/2006.03829 (https://arxiv.org/abs/2006.03829)
9 Brain Tumor Survival Prediction using Radiomics Features, https://arxiv.org/abs/2009.02903
10 Multilingual Speech Recognition with Corpus Relatedness Sampling. https://isca-speech.org/archive/Interspeech_2019/pdfs/3052.pdf
11 Does BERT Make Any Sense? https://arxiv.org/pdf/1909.10430.pdf
12 Unsupervised Cross-lingual Representation Learning at Scale https://arxiv.org/pdf/1911.02116.pdf
13 Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness https://arxiv.org/pdf/1905.13472.pdf
14 The Bottom-up Evolution of Representations in the Transformer:A Study with Machine Translation and Language Modeling Objectives https://arxiv.org/pdf/1909.01380.pdf
15 Zero-Shot Learning - A ComprehensiveEvaluation of the Good, the Bad and the Ugly https://arxiv.org/pdf/1707.00600.pdf
16 Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders https://arxiv.org/pdf/1812.01784.pdf
17 Rethinking Generative Zero-Shot Learning: An EnsembleLearning Perspective for Recognising Visual Patches https://arxiv.org/pdf/2007.13314.pdf
18 Plug and Play Language Models: A Simple Approach to Controlled Text Generation https://arxiv.org/pdf/1912.02164.pdf
1 VoiceFilter from Google https://google.github.io/speaker-id/publications/VoiceFilter/
2 Wavesplit - Июль 2020. SDR 21.0 на WSJ0-mix2 https://arxiv.org/pdf/2002.08933v2.pdf
3 Neural Supersampling for Real-time Rendering (Facebok) https://research.fb.com/wp-content/uploads/2020/06/Neural-Supersampling-for-Real-time-Rendering.pdf (https://neurohive.io/ru/novosti/nejroset-ot-fair-povyshaet-razreshenie-izobrazheniya-v-16-raz/)
4 DeepFaceDrawing: Deep Generation of Face Images from Sketches http://geometrylearning.com/paper/DeepFaceDrawing.pdf (https://neurohive.io/ru/novosti/deepfacedrawing-nejroset-generiruet-izobrazheniya-ljudej-po-sketcham/)
5 Tacotron 2 (without wavenet) https://github.com/NVIDIA/tacotron2 (paper: https://arxiv.org/pdf/1712.05884.pdf)
6 DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation. https://arxiv.org/pdf/2006.04868.pdf
7 LoCo: Local Contrastive Representation Learning, https://arxiv.org/abs/2008.01342 (https://arxiv.org/abs/2008.01342)
8 3D Self-Supervised Methods for Medical Imaging https://arxiv.org/abs/2006.03829 (https://arxiv.org/abs/2006.03829)
9 Brain Tumor Survival Prediction using Radiomics Features, https://arxiv.org/abs/2009.02903
10 Multilingual Speech Recognition with Corpus Relatedness Sampling. https://isca-speech.org/archive/Interspeech_2019/pdfs/3052.pdf
11 Does BERT Make Any Sense? https://arxiv.org/pdf/1909.10430.pdf
12 Unsupervised Cross-lingual Representation Learning at Scale https://arxiv.org/pdf/1911.02116.pdf
13 Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness https://arxiv.org/pdf/1905.13472.pdf
14 The Bottom-up Evolution of Representations in the Transformer:A Study with Machine Translation and Language Modeling Objectives https://arxiv.org/pdf/1909.01380.pdf
15 Zero-Shot Learning - A ComprehensiveEvaluation of the Good, the Bad and the Ugly https://arxiv.org/pdf/1707.00600.pdf
16 Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders https://arxiv.org/pdf/1812.01784.pdf
17 Rethinking Generative Zero-Shot Learning: An EnsembleLearning Perspective for Recognising Visual Patches https://arxiv.org/pdf/2007.13314.pdf
18 Plug and Play Language Models: A Simple Approach to Controlled Text Generation https://arxiv.org/pdf/1912.02164.pdf