This repository provides the WebForest dataset proposed in the paper "Modeling Visual Containment for Web Page Layout Optimization" (Pacific Graphics 2021).
Layout tree | Composite image |
---|---|
-
Clone this repository
git clone https://github.com/ktrk115/web_layout.git cd web_layout
-
Create a new conda environment (Python 3.8)
conda create -n web_layout python=3.8 graphviz conda activate web_layout
-
Install dependent libraries
pip install -r requirements.txt
-
Download the WebForest dataset
bash download.sh
-
Run and see
demo.py
for how to use the datasetpython demo.py # ---------- Root ---------- # {'accessed': '2020-04-12 11:42:53.546634', # 'box': [0, 0, 1366, 768], # 'categories': ['Top/Computers/Software/Business_Drawing'], # 'height': 768, # 'nbox': [0.0, 0.0, 1.0, 0.5622254758418741], # 'url': 'https://www.tomsplanner.com/', # 'width': 1366} # # ---------- First element ---------- # {'area_importance': 3, # 'box': [0, 0, 1366, 111], # 'css_selector': 'html > body > div > header', # 'html_tag': 'header', # 'label': 'image', # 'nbox': [0.0, 0.0, 1.0, 0.08125915080527087], # 'order': 0, # 'parent': 'root'} # # Save layout tree to "tree.png" # Save composite image to "composite.png"
GNU AGPLv3
If this repository helps your research, please consider citing our paper.
@article{Kikuchi2021,
title = {Modeling Visual Containment for Web Page Layout Optimization},
author = {Kotaro Kikuchi and Mayu Otani and Kota Yamaguchi and Edgar Simo-Serra},
journal = {Computer Graphics Forum},
volume = {40},
number = {7},
pages = {},
year = {2021},
doi = {}
}