Capture, Learning, and Synthesis of 3D Speaking Styles

CVPR 2019 TimoBolkart/voca

We then train a neural network on our dataset that factors identity from facial motion.

15 Jun 2019

Reweighted Expectation Maximization

13 Jun 2019adjidieng/REM

The typical workaround is to use variational inference (VI) and maximize a lower bound to the log marginal likelihood of the data.

13 Jun 2019

Training Neural Networks for and by Interpolation

13 Jun 2019oval-group/ali-g

We empirically show that ALI-G outperforms adaptive gradient methods such as Adam, and provides comparable performance with SGD, although SGD benefits from manual learning rate schedules.

13 Jun 2019

Grid R-CNN Plus: Faster and Better

13 Jun 2019STVIR/Grid-R-CNN

Grid R-CNN is a well-performed objection detection framework.

13 Jun 2019

Cognitive Knowledge Graph Reasoning for One-shot Relational Learning

13 Jun 2019THUDM/CogKR

Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently.

13 Jun 2019

The Replica Dataset: A Digital Replica of Indoor Spaces

13 Jun 2019facebookresearch/Replica-Dataset

We introduce Replica, a dataset of 18 highly photo-realistic 3D indoor scene reconstructions at room and building scale.


13 Jun 2019

Learning Spatio-Temporal Representation with Local and Global Diffusion

CVPR 2019 ZhaofanQiu/local-and-global-diffusion-networks

Diffusions effectively interact two aspects of information, i. e., localized and holistic, for more powerful way of representation learning.

13 Jun 2019

Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking

13 Jun 2019misonuma/strsum

This paper focuses on the end-to-end abstractive summarization of a single product review without supervision.

13 Jun 2019

Contrastive Multiview Coding

13 Jun 2019HobbitLong/CMC

Humans view the world through many sensory channels, e. g., the long-wavelength light channel, viewed by the left eye, or the high-frequency vibrations channel, viewed by the right ear.

13 Jun 2019

A JIT Compiler for Neural Network Inference

13 Jun 2019bhuman/CompiledNN

This paper describes a C++ library that compiles neural network models at runtime into machine code that performs inference.

13 Jun 2019