Python
Java
PHP
IOS
Android
Nodejs
JavaScript
Html5
Windows
Ubuntu
Linux
Convolutional Pose Machines
本论文将 深度学习 应用于人体姿态分析 xff0c 同时用卷积图层表达纹理信息和空间信息 目前在2016年的 MPII竞赛中名列前茅 作者在github提供了 训练和测试源码 convolutional pose machines CVPR
convolutional
pose
Machines
Visualizing and Understanding Convolutional Networks
Matthew D Zeiler xff0c Rob Fergus Visualizing and Understanding Convolutional Networks CVPR2014 论文下载 推荐一篇比较好的blog xff1a
Visualizing
and
Understanding
convolutional
networks
SECOND: Sparsely Embedded Convolutional Detection
contributions 应用sparse convolution 提升了训练以及inference的速度 提出一个novel 的angle loss 来回归yaw角 介绍了gt sampling的augmentation的方式 spar
Second
Sparsely
Embedded
convolutional
Detection
ICCV 2019: FCOS: Fully Convolutional One-Stage Object Detection论文阅读笔记
ICCV
2019
FCOS
Fully
convolutional
【论文笔记】Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition...
Spatial Temporal Graph Convolutional Networks for Skeleton Based Action Recognition 2018 01 28 15 45 13 研究背景和动机 xff1a 行人
Spatial
Temporal
Graph
convolutional
networks
【论文复现】ECO_Efficient Convolutional Network for Online Video Understandin
论文链接 xff1a https arxiv org abs 1804 09066 代码链接 xff1a https github com mzolfaghari ECO pytorch 该篇论文是百度paddlepaddle线上训练营推荐
ECO
Efficient
convolutional
network
for
Attentional Graph Convolutional Networks for Knowledge Concept Recommendation in MOOCs in a Heter---
Attentional Graph Convolutional Networks for Knowledge Concept Recommendation in MOOCs in a Heterogeneous View 目录 Attent
Attentional
Graph
convolutional
networks
for
论文阅读之Convolutional Knowledge Tracing: Modeling Individualization in Student Learning Process
Convolutional Knowledge Tracing Modeling Individualization in Student Learning Process SIGIR 2020 提出背景 xff1a 得益于Coursera
convolutional
Knowledge
Tracing
Modeling
Individualization
DDGCN: A Dynamic Directed Graph Convolutional Network for Action Recognition
Introduction 作者认为解决如下两个问题能有效增强GCN在动作识别中的能力 xff1a 1 在人类骨骼的不同部位中有着时空关联性 xff0c 但这些关联性是动态的 xff0c 而且在时空域中不同的动作关联性也是不同的 标椎卷积操作
DDGCN
Dynamic
Directed
Graph
convolutional
Multi-view graph convolutional networks with attention mechanism
摘要 传统的图卷积网络关注于如何高效的探索不同阶跳数 hops 的邻居节点的信息 但是目前的基于GCN的图网络模型都是构建在固定邻接矩阵上的即实际图的一个拓扑视角 当数据包含噪声或者图不完备时 xff0c 这种方式会限制模型的表达能力 由于
Multi
View
Graph
convolutional
networks