Trending Research
Is Space-Time Attention All You Need for Video Understanding?
• facebookresearch/TimeSformer
• 
We present a convolution-free approach to video classification built exclusively on self-attention over space and time.
Ranked #1 on
Action Recognition
on Diving-48
ACTION CLASSIFICATION ACTION RECOGNITION VIDEO QUESTION ANSWERING VIDEO UNDERSTANDING
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision.
Ranked #1 on
Semantic Segmentation
on ADE20K
IMAGE CLASSIFICATION INSTANCE SEGMENTATION REAL-TIME OBJECT DETECTION SEMANTIC SEGMENTATION
Tacotron: Towards End-to-End Speech Synthesis
• mozilla/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.
Ranked #4 on
Speech Synthesis
on North American English
Lite-HRNet: A Lightweight High-Resolution Network
• HRNet/Lite-HRNet
•
We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1x1) convolutions in shuffle blocks.
Ranked #11 on
Pose Estimation
on COCO test-dev
MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis
• bes-dev/MobileStyleGAN.pytorch
•
In recent years, the use of Generative Adversarial Networks (GANs) has become very popular in generative image modeling.
LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis
• Layout-Parser/layout-parser
•
Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks.
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.
Ranked #11 on
Conditional Image Generation
on ImageNet 128x128
Handling Background Noise in Neural Speech Generation
Recent advances in neural-network based generative modeling of speech has shown great potential for speech coding.
Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
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).
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
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.
Ranked #1 on
Common Sense Reasoning
on CommonsenseQA
COMMON SENSE REASONING GRAPH REPRESENTATION LEARNING KNOWLEDGE GRAPHS LANGUAGE MODELLING MULTI-HOP QUESTION ANSWERING QUESTION ANSWERING