feymanpriv

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

paper-reading

深度学习经典、新论文逐段精读

ConvNeXt

Code release for ConvNeXt model

img2dataset

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

vector-quantize-pytorch

Vector (and Scalar) Quantization, in Pytorch

GLIP

Grounded Language-Image Pre-training

RecommenderSystem

detrex

detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.

fastdup

fastdup is a powerful free tool designed to rapidly extract valuable insights from your image & video datasets. Assisting you to increase your dataset images & labels quality and reduce your data operations costs at an unparalleled scale.

Video-Pre-Training

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

VideoX

VideoX: a collection of video cross-modal models

SimMIM

This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".

cv-arxiv-daily

🎓Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)

FastestDet

:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler

CVPR-2022-Papers

self_supervised

A Pytorch-Lightning implementation of self-supervised algorithms

XPretrain

Multi-modality pre-training

QuadTreeAttention

QuadTree Attention for Vision Transformers (ICLR2022)

ovr-cnn

A new framework for open-vocabulary object detection, based on maskrcnn-benchmark

knowhere

Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.

Text4Vis

【AAAI'2023 & IJCV】Transferring Vision-Language Models for Visual Recognition: A Classifier Perspective

learning_minimal

Learning to Solve Hard Minimal Problems

MCQ

Official code for "Bridging Video-text Retrieval with Multiple Choice Questions", CVPR 2022 (Oral).

MUST

PyTorch code for MUST

BootMAE

ECCV2022,Bootstrapped Masked Autoencoders for Vision BERT Pretraining

everything_at_once

This is the official implementation of "Everything at Once - Multi-modal Fusion Transformer for Video Retrieval". CVPR 2022

CLIP4CirDemo

[CVPR 2022 - Demo Track] - Effective conditioned and composed image retrieval combining CLIP-based features

LAVENDER

A Unified Framework for Video-Language Understanding

met

A large-scale dataset for instance-level recognition for artworks is introduced.

Universal-Transformer

Training Google Universal Image Embedding