hzhang57

AdaFocusV2

AS-MLP

This is an official implementation for "AS-MLP: An Axial Shifted MLP Architecture for Vision".

awesome-attention-mechanism-in-cv

:punch: CV中常用注意力模块;即插即用模块;ViT模型. PyTorch Implementation Collection of Attention Module and Plug&Play Module

awesome-hand-pose-estimation

Awesome work on hand pose estimation/tracking

CAA

CAA: Channelized Axial Attention for Semantic Segmentation

CMT_CNN-meet-Vision-Transformer

A PyTorch implementation of CMT based on paper CMT: Convolutional Neural Networks Meet Vision Transformers.

Compact-Transformers

[Preprint] Escaping the Big Data Paradigm with Compact Transformers, 2021

ConvNeXt

Code release for ConvNeXt model

Convolutional-MLPs

[Preprint] ConvMLP: Hierarchical Convolutional MLPs for Vision, 2021

deepvecfont

[SIGGRAPH Asia 2021] DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning

DynamicViT

[NeurIPS 2021] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

ffcv

FFCV: Fast Forward Computer Vision (and other ML workloads!)

GFNet

[NeurIPS 2021] Global Filter Networks for Image Classification

GrabNet

GrabNet: A Generative model to generate realistic 3D hands grasping unseen objects (ECCV2020)

Hand3DResearch

how-do-vits-work

(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"

img2dataset

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

LLVIP

LLVIP: A Visible-infrared Paired Dataset for Low-light Vision

MotionSqueeze

Official PyTorch Implementation of MotionSqueeze, ECCV 2020

MoViNet-pytorch

MoViNets PyTorch implementation: Mobile Video Networks for Efficient Video Recognition;

MOW

MSG-Transformer

MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens

MultiBench

[NeurIPS 2021] Multiscale Benchmarks for Multimodal Representation Learning

PASS

The PASS dataset: pretrained models and how to get the data

poster_template

some academic posters as references. May we have in-person poster session soon!

SlowFast

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

SPACH

temporal-adaptive-module

TAM: Temporal Adaptive Module for Video Recognition

vidaug

Effective Video Augmentation Techniques for Training Convolutional Neural Networks

Visformer