Online 3D skeleton-based action recognition with a single RGB camera

Awesome List of Attention Modules and Plug&Play Modules in Computer Vision

Dual Attention Network for Scene Segmentation (CVPR2019)

Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"

try to implement the CVPR 2019 paper "Selective Kernel Networks" by PyTorch

Code for our CVPR2021 paper coordinate attention

code and trained models for "Attention as Activation"

Skeleton-based Action Recognition

PyTorch implementation of SENet

Attention over nodes in Graph Neural Networks using PyTorch (NeurIPS 2019)

FcaNet: Frequency Channel Attention Networks

Official PyTorch Implementation for "Rotate to Attend: Convolutional Triplet Attention Module." [WACV 2021]

ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks

Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition (https://arxiv.org/pdf/2006.11538.pdf)

Depthwise Over-parameterized Convolutional Layer

PyTorch implementation of Octave Convolution with pre-trained Oct-ResNet and Oct-MobileNet models

Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

Datasets, Transforms and Models specific to Computer Vision

code and trained models for "Attentional Feature Fusion"

[ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer

Spatial Temporal Transformer Network for Skeleton-Based Activity Recognition

Collection of the latest, greatest, deep learning optimizers (for Pytorch) - CNN, NLP suitable

Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition

PyTorch implementation for the paper GanHand: Predicting Human Grasp Affordances in Multi-Object Scenes (CVPR 2020 Oral)

Info and sample codes for "NTU RGB+D Action Recognition Dataset"