LeetCode 刷题攻略:200道经典题目刷题顺序,共60w字的详细图解,视频难点剖析,50余张思维导图,支持C++,Java,Python,Go,JavaScript等多语言版本,从此算法学习不再迷茫!🔥🔥 来看看,你会发现相见恨晚!🚀
CVPR 2022 Oral | IA-SSD:用于3D LiDAR点云的高效基于点的检测器 我们研究了 3D LiDAR 点云的有效目标检测问题。为了降低内存和计算成本,现有的基于点的pipeline通常采用与任务无关的随机采样或最远点采样来逐步下采样输入点云,尽管并非所有点对目标检测任务都同等重要。特别是,对于目标检测器,前景点本质上比背景点更重要。
FUKinect-Fall dataset was created using Kinect V1. The dataset includes walking, bending, sitting, squatting, lying and falling actions performed by 21 subjects between 19-72 years of age
Source code of paper "Convolutional Sequence to Sequence Model for Human Dynamics"
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.
Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark, CVPR 2019, Oral
MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.
Repository containing the material required to reproduce the results of the paper "Vision-Based Fall Detection with Convolutional Neural Networks 论文:https://www.hindawi.com/journals/wcmc/2017/9474806/
This is a implementation of integrating a simple but efficient attention block in CNN + bidirectional LSTM for video classification.