Trending Research

Is Space-Time Attention All You Need for Video Understanding?

9 Feb 2021facebookresearch/TimeSformer

We present a convolution-free approach to video classification built exclusively on self-attention over space and time.

ACTION CLASSIFICATION ACTION RECOGNITION VIDEO QUESTION ANSWERING VIDEO UNDERSTANDING

131
4.69 stars / hour

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

25 Mar 2021microsoft/Swin-Transformer

This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision.

IMAGE CLASSIFICATION INSTANCE SEGMENTATION REAL-TIME OBJECT DETECTION SEMANTIC SEGMENTATION

2,305
3.37 stars / hour

Tacotron: Towards End-to-End Speech Synthesis

29 Mar 2017mozilla/TTS

A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module.

SPEECH SYNTHESIS TEXT-TO-SPEECH SYNTHESIS

4,435
2.99 stars / hour

Lite-HRNet: A Lightweight High-Resolution Network

13 Apr 2021HRNet/Lite-HRNet

We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1x1) convolutions in shuffle blocks.

POSE ESTIMATION SEMANTIC SEGMENTATION

171
2.19 stars / hour

MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis

10 Apr 2021bes-dev/MobileStyleGAN.pytorch

In recent years, the use of Generative Adversarial Networks (GANs) has become very popular in generative image modeling.

IMAGE GENERATION

285
2.13 stars / hour

LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis

29 Mar 2021Layout-Parser/layout-parser

Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks.

1,841
1.98 stars / hour

Self-Attention Generative Adversarial Networks

arXiv 2018 vijishmadhavan/SkinDeep

In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks.

CONDITIONAL IMAGE GENERATION

438
1.78 stars / hour

Handling Background Noise in Neural Speech Generation

23 Feb 2021google/lyra

Recent advances in neural-network based generative modeling of speech has shown great potential for speech coding.

DENOISING SPEECH SYNTHESIS

2,100
1.67 stars / hour

Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer

12 Apr 2021PaddlePaddle/PaddleGAN

Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle).

STYLE TRANSFER

2,706
1.12 stars / hour

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering

13 Apr 2021michiyasunaga/qagnn

The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge from large KGs, and (ii) perform joint reasoning over the QA context and KG.

COMMON SENSE REASONING GRAPH REPRESENTATION LEARNING KNOWLEDGE GRAPHS LANGUAGE MODELLING MULTI-HOP QUESTION ANSWERING QUESTION ANSWERING

51
0.77 stars / hour