Generation Tasks
Improved GAN
related tasks
Improved GAN-Image Generation
GAN
Problems of GAN
Improved GAN
New paper from DeepMind
Semi-parametric Strategy
Image Generation
Message-Passing Strategy
Message Passing Strategy for Feature Sharing.
Domain Adaptation Strategy
Video generation
Text Effects Transfer
Scene graph Generation
Robot Control
Cross-Modal Zero-Shot Hashing retrieval
Reference
Acknowledgment


Reference[原文]: Joselynzhao.top & 夏木青 | Generation Tasks 

Improved GAN
如何从语言描述的场景来生成图像


related tasks

image synthesis





可以通过 RNN+GAN 生成实现
Improved GAN-Image Generation
GAN
Improved GAN-Image Generation

Image Generation from Scene Graphs (CVPR2018)
Stackgan: Text to photo-realistic image synthesis with

stacked generative adversarial networks. (ICCV 2017)

使用堆积的生成对抗网络实现从文本到真实图像的合成

Problems of GAN
carefully balance the capabilities between the generator and the discriminator

仔细平衡发生器和鉴别器之间的能力
unsuitable parameter settings can degrade the performance

不合适的参数设置会降低性能
Improved GAN
Evolutionary Generative Adversarial Networks (TEVC 2019)
New paper from DeepMind
Vector Quantized Variational AutoEncoder model（VQ-VAE2 wins bigGAN）

矢量量化变分自动编码器模型


Semi-parametric Strategy
半参数策略
Image Generation
Parametric models

end-to-end training of highly expressive models. （高度表达模型）
Nonparametric models （非参数模型）

extract materials from large real image datasets during testing

在测试的时候提取信息
Semi-parametric Strategy

Semi-parametric Image Synthesis (CVPR2018)
The problem of existing image generation methods （现有方法的问题）

give stunning results on limited domains such as

descriptions of birds, flowers or people.

Low-quality image of other domains.

作用领域有限
Using semi-parametric strategy to improve  Image generation method
Message-Passing Strategy
Message Passing Strategy for Feature Sharing.
用于特征共享的消息传递策略

Scene Graph Generation from Objects, Phrases and Region Captions(ICCV2017)

Domain Adaptation Strategy
区域适应策略

give stunning results on limited domains such as descriptions of birds, flowers or people.
Using Domain Adaptation to improve Image generation method  in more domains.
Video generation


输入 深度图像

输出 对手关节、姿势的估计


3D Hand Shape and Pose Estimation from a Single RGB Image（CVPR19 Oral）
Text Effects Transfer




创新的分布感知数据增强策略

TET-GAN: Text Effects Transfer via Stylization and Destylization

（AAAI2019）
Scene graph Generation


modeling these statistical correlations between object pairs and relationships can effectively regularize the semantic prediction space （structured knowledge graph ）

对这些对象和关系之间的统计相关性建模可以有效地规范语义预测空间（结构化知识图）
Knowledge-Embedded Routing Network for   Scene Graph Generation （CVPR2019）


Robot Control


Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection(2017)


Towards Accurate Task Accomplishment with Low-Cost Robotic Arms（CVPR2019）

Cross-Modal Zero-Shot Hashing retrieval
跨模态 zero-shot 哈希检索


Attribute-Guided Network for Cross-Modal Zero-Shot Hashing(T-NNLS19)
Reference

Image Generation from Scene Graphs (CVPR2018)
Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. (ICCV 2017)
Evolutionary Generative Adversarial Networks  (TEVC 2019)
Semi-parametric Image Synthesis (CVPR2018)
Scene Graph Generation from Objects, Phrases and Region Captions(ICCV2017)
3D Hand Shape and Pose Estimation from a Single RGB Image（CVPR19 Oral）
TET-GAN: Text Effects Transfer via Stylization and Destylization

（AAAI2019）
Knowledge-Embedded Routing Network for   Scene Graph Generation （CVPR2019）
Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection(2017)
Towards Accurate Task Accomplishment with Low-Cost Robotic Arms（CVPR2019）
Attribute-Guided Network for Cross-Modal Zero-Shot Hashing(T-NNLS19)

Acknowledgment
感谢本篇博文的内容提供者：崔亚文（Cui Yawen）· HPCL

A family hierarchy is usually presented by a pedigree tree where all the nodes on the same level belong to the same generation. Your task is to find the generation with the largest population.

Input Specification:

Each input file contains one test case. Each case starts with two positive integers N (<100) which is the total number of family members in the tree (and hence assume that all the members are numbered from 01 to N), and M (<N) which is the number of family members who have children. Then M lines follow, each contains the information of a family member in the following format:

ID K ID[1] ID[2] ... ID[K]


where ID is a two-digit number representing a family member, K (>0) is the number of his/her children, followed by a sequence of two-digit ID's of his/her children. For the sake of simplicity, let us fix the root ID to be 01. All the numbers in a line are separated by a space.

Output Specification:

For each test case, print in one line the largest population number and the level of the corresponding generation. It is assumed that such a generation is unique, and the root level is defined to be 1.

Sample Input:

23 13
21 1 23
01 4 03 02 04 05
03 3 06 07 08
06 2 12 13
13 1 21
08 2 15 16
02 2 09 10
11 2 19 20
17 1 22
05 1 11
07 1 14
09 1 17
10 1 18


Sample Output:

9 4

vector或者数组存储树

有点类似层序遍历，层序遍历是使用queue进行输出，但是我想了半天没有想出一个很好地办法计算每层的节点数量。

最后参考了别人的代码，使用vector来模拟，好处就在于可以使用erase直接删除上一代节点

 

#include <iostream>
#include <vector>
#include <queue>
using namespace std;
int main(){
	vector<int> nodes[100];           //保存树
	int n,m;
	scanf("%d %d",&n,&m);
	for(int i=0;i<m;i++){
		int pId,nCh;
		scanf("%d %d",&pId,&nCh);
		for(int j=0;j<nCh;j++){
			int temp;
			scanf("%d",&temp);
			nodes[pId].push_back(temp);      //谁的孩子谁装
		}
	}
	int max=0,level=1,t;
    vector<int> data;
	data.push_back(1);                      //把根节点装进去
	while(!data.empty()){
		int size=data.size();               //当代节点数量
		if(size>max){
			t=level;
			max=size;
		}
		for(int k=0;k<size;k++){
			for(int l=0;l<nodes[data[k]].size();l++){  //添加下一代节点
				data.push_back(nodes[data[k]][l]);
			}
		}
		data.erase(data.begin(),data.begin()+size);
		level++;

	}
	printf("%d %d",max,t);
return 0;
}