https://github.com/kacky24/stylenet

A pytorch implemention of "StyleNet: Generating Attractive Visual Captions with Styles"
https://github.com/kacky24/stylenet

caption cnn dlhacks image-captioning lstm microsoft pytorch pytorch-implemention stylenet

Last synced: 3 months ago
JSON representation

A pytorch implemention of "StyleNet: Generating Attractive Visual Captions with Styles"

• Host: GitHub
• URL: https://github.com/kacky24/stylenet
• Owner: kacky24
• Created: 2017-11-08T02:51:58.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2020-12-13T13:13:23.000Z (about 4 years ago)
• Last Synced: 2024-08-02T20:44:31.593Z (6 months ago)
• Topics: caption, cnn, dlhacks, image-captioning, lstm, microsoft, pytorch, pytorch-implemention, stylenet
• Language: Python
• Homepage:
• Size: 13.2 MB
• Stars: 62
• Watchers: 3
• Forks: 10
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-Video-Captioning - [pytorch-code

README

        
# StyleNet: Generating Attractive Visual Captions with Styles

### * under development

- Powered by [DLHacks](http://deeplearning.jp/hacks/)

StyleNet is a novel framework to address the task of generating attractive captions for images and videos with different styles. A novel model component, named factored LSTM is used in StyleNet, which automatically distills the style factors in the monolingual text corpus.

framework

![Imgur](https://i.imgur.com/G5ZTvwB.png)

examples of generated captions

![Imgur](https://i.imgur.com/aUJXKEo.png)

## Description

- A pytorch implemention of StyleNet

- Author: Chuang Gan, Zhe Gan, Xiaodong He, Jianfeng Gao, Li Deng

- Published in: Computer Vision and Pattern Recognition (CVPR), 2017

- URL:  https://www.microsoft.com/en-us/research/wp-content/uploads/2017/06/Generating-Attractive-Visual-Captions-with-Styles.pdf

- Dataset: https://zhegan27.github.io/Paper.html

- Slideshare: https://www.slideshare.net/DeepLearningJP2016/dl-hacks-stylenet-generating-attractive-visual-captions-with-styles

- written by [Kota Kakiuchi](https://github.com/kacky24)

## Requirement

- python 3.5.3

- pytorch 0.2.0

- torchvision 0.1.9

- numpy 1.13.3

- scikit-image 0.13.1

- nltk 3.2.5