Trending Research

Semantic Image Synthesis with Spatially-Adaptive Normalization

18 Mar 2019NVlabs/SPADE

We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout.

IMAGE GENERATION

1,762
12.77 stars / hour

Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly

15 Mar 2019dragonfly/dragonfly

We compare Dragonfly to a suite of other packages and algorithms for global optimisation and demonstrate that when the above methods are integrated, they enable significant improvements in the performance of BO.

BAYESIAN OPTIMISATION

261
2.53 stars / hour

Multi-Task Deep Neural Networks for Natural Language Understanding

31 Jan 2019namisan/mt-dnn

In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks.

DOMAIN ADAPTATION LANGUAGE MODELLING NATURAL LANGUAGE INFERENCE PARAPHRASE IDENTIFICATION SENTIMENT ANALYSIS

164
1.30 stars / hour

Selective Kernel Networks

15 Mar 2019implus/SKNet

A building block called Selective Kernel (SK) unit is designed, in which multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches.

58
0.91 stars / hour

PifPaf: Composite Fields for Human Pose Estimation

15 Mar 2019vita-epfl/openpifpaf

We propose a new bottom-up method for multi-person 2D human pose estimation that is particularly well suited for urban mobility such as self-driving cars and delivery robots.

POSE ESTIMATION SELF-DRIVING CARS

110
0.85 stars / hour

Bags of Tricks and A Strong Baseline for Deep Person Re-identification

17 Mar 2019michuanhaohao/reid-strong-baseline

In the literature, some effective training tricks are briefly appeared in several papers or source codes.

PERSON RE-IDENTIFICATION

66
0.74 stars / hour

Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose

29 Nov 2018Daniil-Osokin/lightweight-human-pose-estimation.pytorch

In this work we adapt multi-person pose estimation architecture to use it on edge devices.

MULTI-PERSON POSE ESTIMATION

52
0.59 stars / hour

Attention Is All You Need

NeurIPS 2017 audier/DeepSpeechRecognition

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.

CONSTITUENCY PARSING MACHINE TRANSLATION

293
0.55 stars / hour

Splitter: Learning Node Representations that Capture Multiple Social Contexts

WWW 2019 benedekrozemberczki/Splitter

Recent interest in graph embedding methods has focused on learning a single representation for each node in the graph.

GRAPH EMBEDDING LINK PREDICTION NETWORK EMBEDDING

38
0.49 stars / hour

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

11 Oct 2018google-research/bert

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.

COMMON SENSE REASONING CROSS-LINGUAL NATURAL LANGUAGE INFERENCE NAMED ENTITY RECOGNITION QUESTION ANSWERING

13,243
0.47 stars / hour