roadrunner01

Pop Music Transformer: Generating Music with Rhythm and Harmony pdf: https://arxiv.org/pdf/2002.00212.pdf … abs: https://arxiv.org/abs/2002.00212  github: https://github.com/YatingMusic/remi …pic.twitter.com/nwdyGG6kvZ

Reconstructing Natural Scenes from fMRI Patterns using BigBiGAN pdf: https://arxiv.org/pdf/2001.11761.pdf … abs: https://arxiv.org/abs/2001.11761 pic.twitter.com/Cmepes0dzm

Self-Adversarial Learning with Comparative Discrimination for Text Generation pdf: https://arxiv.org/pdf/2001.11691.pdf … abs: https://arxiv.org/abs/2001.11691 pic.twitter.com/vxMAAyMyC6

ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation pdf: https://arxiv.org/pdf/2001.11314.pdf … abs: https://arxiv.org/abs/2001.11314 pic.twitter.com/O7LooF9zDh

Multimodal Story Generation on Plural Images pdf: https://arxiv.org/pdf/2001.10980.pdf … abs: https://arxiv.org/abs/2001.10980 pic.twitter.com/HuOYaIAjsV

Controlling generative models with continuous factors of variations pdf: https://arxiv.org/pdf/2001.10238.pdf … abs: https://arxiv.org/abs/2001.10238 pic.twitter.com/XW0pgixYh3

Bringing Stories Alive: Generating Interactive Fiction Worlds pdf: https://arxiv.org/pdf/2001.10161.pdf … abs: https://arxiv.org/abs/2001.10161 pic.twitter.com/epeMMuKw3p

Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos pdf: https://arxiv.org/pdf/2001.09518.pdf … abs: https://arxiv.org/abs/2001.09518 pic.twitter.com/Bb4FA2Q9Bx

FakeLocator: Robust Localization of GAN-Based Face Manipulations via Semantic Segmentation Networks with Bells and Whistles pdf: https://arxiv.org/pdf/2001.09598.pdf … abs: https://arxiv.org/abs/2001.09598 pic.twitter.com/WewtXQfbjG

On the Role of Receptive Field in Unsupervised Sim-to-Real Image Translation pdf: https://arxiv.org/pdf/2001.09257.pdf … abs: https://arxiv.org/abs/2001.09257 pic.twitter.com/zFlr6FGcY6

PCGRL: Procedural Content Generation via Reinforcement Learning pdf: https://arxiv.org/pdf/2001.09212.pdf … abs: https://arxiv.org/abs/2001.09212 pic.twitter.com/xXGA1AHofQ

Fine-Tuning a Transformer-Based Language Model to Avoid Generating Non-Normative Text pdf: https://arxiv.org/pdf/2001.08764.pdf … abs: https://arxiv.org/abs/2001.08764 pic.twitter.com/uvXxDmff0E

ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data pdf: https://arxiv.org/pdf/2001.07966.pdf … abs: https://arxiv.org/abs/2001.07966 pic.twitter.com/KClsXgvVNy

ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network pdf: https://arxiv.org/pdf/2001.08073.pdf … abs: https://arxiv.org/abs/2001.08073 pic.twitter.com/RvrpGsZb8s

Human-Aware Motion Deblurring pdf: https://arxiv.org/pdf/2001.06816.pdf … abs: https://arxiv.org/abs/2001.06816 pic.twitter.com/BLUNhb4RwF

P2-GAN: Efficient Style Transfer Using Single Style Image pdf: https://arxiv.org/pdf/2001.07466.pdf … abs: https://arxiv.org/abs/2001.07466 pic.twitter.com/GxplAOvIyE

JVS-MuSiC: Japanese multispeaker singing-voice corpus pdf: https://arxiv.org/pdf/2001.07044.pdf … abs: https://arxiv.org/abs/2001.07044  project page: https://sites.google.com/site/shinnosuketakamichi/research-topics/jvs_music …pic.twitter.com/WTNSbiBNLG

Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement pdf: https://arxiv.org/pdf/2001.06826.pdf … abs: https://arxiv.org/abs/2001.06826 pic.twitter.com/0LHdFHWmzs

RobBERT: a Dutch RoBERTa-based Language Model pdf: https://arxiv.org/pdf/2001.06286.pdf … abs: https://arxiv.org/abs/2001.06286  github: https://github.com/iPieter/RobBERT pic.twitter.com/GvV0lPqaWv

SieveNet: A Unified Framework for Robust Image-Based Virtual Try-On pdf: https://arxiv.org/pdf/2001.06265.pdf … abs: https://arxiv.org/abs/2001.06265 pic.twitter.com/mUjEzMO19T