lichengunc

powerlevel10k

A Zsh theme

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

nlpaug

Data augmentation for NLP

PyContrast

PyTorch implementation of Contrastive Learning methods

daxigua

最简单的魔改发布『 合成大西瓜 』，配套改图工具，不用改代码，修改配置即可！

awesome-fashion-ai

A repository to curate and summarise research papers related to fashion and e-commerce

awesome-vision-language-pretraining-papers

Recent Advances in Vision and Language PreTrained Models (VL-PTMs)

lxmert

PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".

UNITER

Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"

StyleMapGAN

Official pytorch implementation of StyleMapGAN (CVPR 2021)

HERO

Research code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"

TVRetrieval

[ECCV 2020] PyTorch code for XML on TVRetrieval dataset - TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval

PoPPy

A Point Process Toolbox Based on PyTorch

TVCaption

[ECCV 2020] PyTorch code of MMT (a multimodal transformer captioning model) on TVCaption dataset

StarterCode

Starter Code for VALUE benchmark

connect-caption-and-trace

A unified framework to jointly model images, text, and human attention traces.

LightningDOT

source code and pre-trained/fine-tuned checkpoint for NAACL 2021 paper LightningDOT

VisualRelationships

Data of ACL 2019 Paper "Expressing Visual Relationships via Language".

BachGAN

worldsheet

Code release for the paper “Worldsheet Wrapping the World in a 3D Sheet for View Synthesis from a Single Image”, ICCV 2021.

mmf

[ECCV 2022] FashionViL: Fashion-Focused V+L Representation Learning

Crisscrossed-Captions

Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO

VideoLanguageFuturePred

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

GD-VCR

Code and data for "Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning" (EMNLP 2021).

How2R-and-How2QA

A video retrieval dataset How2R and a video QA dataset How2QA

UVLP

CVPR 2022 (Oral) Pytorch Code for Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment

detectron2

Detectron2 is FAIR's next-generation research platform for object detection and segmentation.

werewolf_assistant