liqier

-

2s-AGCN

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19

AS-GCN

The model architecture of AS-GCN (for human action recognition)

Channel-Transformer

CTR-GCN

[ICCV2021] Official code for "Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition"

darts

Differentiable architecture search for convolutional and recurrent networks

DARTS-

Code for "DARTS-: Robustly Stepping out of Performance Collapse Without Indicators"

GCN-NAS

Source code for "Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching", AAAI2020

NAS-Bench-Macro

NAS Benchmark in "Prioritized Architecture Sampling with Monto-Carlo Tree Search", CVPR2021

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

liqier/GCN-NAS

Source code for "Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching", AAAI2020

liqier/NAS-Bench-Macro

NAS Benchmark in "Prioritized Architecture Sampling with Monto-Carlo Tree Search", CVPR2021

liqier/openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

liqier/2s-AGCN

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19

liqier/AS-GCN

The model architecture of AS-GCN (for human action recognition)

liqier/Channel-Transformer

liqier/CTR-GCN

[ICCV2021] Official code for "Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition"

liqier/darts

Differentiable architecture search for convolutional and recurrent networks

liqier/DARTS-

Code for "DARTS-: Robustly Stepping out of Performance Collapse Without Indicators"

liqier/deep_learning_for_camera_trap_images

This repo contains code+pre-trained models for extracting information from camera-trap images. The pre-trained models have been trained on the Snapshot Serengeti dataset.

liqier/DOTS

The official implementation of "DOTS: Decoupling Operation and Topology in Differentiable Architecture Search

liqier/evolution-strategies-starter

Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"

liqier/ezc3d

Easy to use C3D reader/writer for C++, Python and Matlab

liqier/gluon-cv

Gluon CV Toolkit

liqier/Graph-Bert

Source code of Graph-Bert

liqier/hourglasstensorlfow

Tensorflow implementation of Stacked Hourglass Networks for Human Pose Estimation

liqier/HW-NAS-Bench

[ICLR 2021] HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark

liqier/LeetCodeAnimation

Demonstrate all the questions on LeetCode in the form of animation.（用动画的形式呈现解LeetCode题目的思路）

liqier/Long-Short-Graph-Memory-Network

Long-Short Graph Memory Network for Skeleton-based Action Recognition（WACV2020）

liqier/mmaction

An open-source toolbox for action understanding based on PyTorch

liqier/mmskeleton

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

liqier/moments_models

The pretrained models trained on Moments in Time Dataset

liqier/MS-G3D

[CVPR 2020 Oral] PyTorch implementation of "Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition"

liqier/NLP_Coding

NLP

liqier/RA-GCNv1

RA-GCN v1 for incomplete skeleton-based action recognition, accepted by ICIP2019

liqier/ResGCNv1

ResGCN: an efficient baseline for skeleton-based human action recognition.

liqier/SGN

This is the implementation of CVPR2020 paper “Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition”.

liqier/Shift-GCN

The implementation for "Skeleton-Based Action Recognition with Shift Graph Convolutional Network" (CVPR2020 oral).

liqier/ST-TR

Spatial Temporal Transformer Network for Skeleton-Based Activity Recognition

liqier/TENAS

[ICLR 2021] "Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective" by Wuyang Chen, Xinyu Gong, Zhangyang Wang