# Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video (AAAI2020)
This repository contains the pytorch codes and trained models described in the paper "Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video" By Jie Wu, Guanbin Li, Si Liu, Liang Lin. [Paper](https://arxiv.org/pdf/2001.06680.pdf)
## Motivation
![Motivation](https://github.com/WuJie1010/TSP-PRL/blob/master/images/introduction.png)
## Framework
![Framework](https://github.com/WuJie1010/TSP-PRL/blob/master/images/model.png)
## Requirements
- Python 2.7
- Pytorch 0.4.1
- matplotlib
- The code is for [Charades-STA](https://arxiv.org/pdf/1705.02101.pdf) dataset.
## Visual Features
Please download the features in [Features1](https://drive.google.com/drive/folders/1U1GEti3JjLfOAN0AhCb0VXqfGoKV9qMo?usp=sharing), and put it in the "Dataset/Charades" folder.
## Training and Testing Data
Please download the TrainingData in [TrainingData](https://drive.google.com/file/d/14aAJf1Wgn6wHFGdMHDgZBphKG1FbZt_y/view?usp=sharing), and put it in the "Dataset/Charades/ref_info" folder.
Please download the TestingData in [TestingData](https://drive.google.com/file/d/1mg2ru344tzL20iQNRCT2WAzfiHEjppLB/view?usp=sharing), and put it in the "Dataset/Charades/ref_info" folder.
## Pre-trained models
We provide the pre-trained model for Charades-STA dataset, which can get 24.73 on R@1, IoU0.7 and 45.30 on R@1, IoU0.5: [Models](https://drive.google.com/open?id=1lyOlcKR5PY7cN_yjZfGUypfNRTokw_He)
## Train ###
```
python train.py
```
## Validate ###
```
python val.py
```
## Test from Pre-trained Model ###
```
python test.py
```
没有合适的资源?快使用搜索试试~ 我知道了~
基于树结构策略的渐进式强化学习,用于视频中的时间语言基础 _python_代码_下载
共9个文件
py:6个
png:2个
md:1个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 99 浏览量
2022-06-22
16:50:51
上传
评论
收藏 635KB ZIP 举报
温馨提示
基于树结构策略的渐进式强化学习用于视频中的时间语言基础 效果展示:https://github.com/WuJie1010/TSP-PRL/blob/master/images/introduction.png 更多详情、使用方法,请下载后阅读README.md文件
资源推荐
资源详情
资源评论
收起资源包目录
TSP-PRL-master.zip (9个子文件)
TSP-PRL-master
images
introduction.png 464KB
model.png 160KB
utils.py 5KB
dataloader_charades.py 15KB
test.py 19KB
train.py 40KB
val.py 30KB
model.py 7KB
README.md 2KB
共 9 条
- 1
资源评论
快撑死的鱼
- 粉丝: 1w+
- 资源: 9154
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功