Deep Learning

Pytorch implementation of the preprint paper "Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos"

Code base for WaveTransformer: A novel architecture for automated audio captioning

Multilingual T5 (mT5) is a massively multilingual pretrained text-to-text transformer model, trained following a similar recipe as T5. This repo can be used to reproduce the experiments in the mT5 paper.

In this repository we release models from the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale that were pre-trained on the ImageNet-21k (imagenet21k) dataset. We provide the code for fine-tuning th

Code for BebopNet: Deep Neural Models for Personalized Jazz Improvisations

Hierarchical Fashion Graph Network for Personalized Outfit Recommendation, SIGIR 2020

AR-Net: Adaptive Resolution Network for Efficient Video Understanding

Aim — a super-easy way to record, search and compare AI experiments

MyVision is a free online image annotation tool used for generating computer vision based ML training data. It is designed with the user in mind, offering features to speed up the labelling process and help maintain workflows with

NeurIPS 2020 Spotlight, trains fast as Adam, generalizes well as SGD, and is stable to train GANs.

This repo contains a list of summarization papers including various topics.

The 2nd place solution to the 2020 edition of the Google Landmark Recognition competition

​ This project aims to help engineers, researchers and students to easily find and learn the good thoughts and designs in AI-related fields, such as AI/ML/DL accelerators, chips, and systems, proposed in the top-tier architecture

crnn实现水平和垂直方向中文文字识别, 提供在3w多个中文字符训练的水平识别和垂直识别的预训练模型

The Cross-lingual Choice of Plausible Alternatives dataset is a benchmark to evaluate the ability of machine learning models to transfer commonsense reasoning across languages.

A demo code of KDD2020 paper "M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems"

pystiche (pronounced /ˈpaɪˈstiʃ/ ) is a framework for Neural Style Transfer (NST) built upon PyTorch

RobustBench: a standardized adversarial robustness benchmark [arXiv, Oct 2020]

Joint Learning of Vessel Segmentation and Artery/Vein Classification

RRPN++: Guidance Towards More Accurate Scene Text Detection

Unsupervised image-to-image translation method via pre-trained StyleGAN2 network

A flow-based network is considered to be inefficient in parameter complexity because of reduced expressiveness of bijective mapping, which renders the models prohibitively expensive in terms of parameters. We present an alternativ

[CVPR2020] TextureFusion: High-Quality Texture Acquisition for Real-Time RGB-D Scanning

Repository for "End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds"

Official implementation of paper "TP-LSD: Tri-points based line segment detector" .

Improving One-stage Visual Grounding by Recursive Sub-query Construction, ECCV 2020

[NeurIPS 2020] "SMYRF: Efficient Attention using Asymmetric Clustering".

[EMNLP 2020] What is More Likely to Happen Next? Video-and-Language Future Event Prediction

BigGAN-AM improves the sample diversity of BigGAN and synthesizes Places365 images.

Code for TPAMI 2020 paper "A Generalized Earley Parser for Human Activity Parsing and Prediction"

An implementation of the algorithm and experiments defined in "Ab-Initio Solution of the Many-Electron Schroedinger Equation with Deep Neural Networks", David Pfau, James S. Spencer, Alex G de G Matthews and W.M.C. Foulkes, Phys.

A code implementation for our arXiv paper "Multi-agent Adhoc Team Play using Decompositional Q function"

State-of-the-art Automatic Speech Recognition in Tensorflow 2