CSSSketch2Code: An Automatic Method to Generate Web Pages with CSS Style

With the constantly increasing scale of the Internet and the users, the Internet applications have higher demands on the front-end web pages. Some web pages have single lattice structure and a relatively fixed HTML code template, which can be automatically generated. There have been research abroad using the deep learning on the task of automatically generating the web pages. However due to the basic encoder-decoder model adopted, the generalization ability of the model is not very robust. In this paper, we propose a novel method based on object detection and attention mechanism to automatically generate a web page with CSS style information. We use object detection to extend the original problem, which makes the model possible to detect the CSS style contents in the web page. Meanwhile we use attention mechanism to strengthen the model. Finally we propose our own dataset, based on which the experiment results show that method we proposed outperforms other existing methods.

[1]  Alon Lavie,et al.  METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments , 2005, IEEvaluation@ACL.

[2]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[3]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[5]  J. Suykens,et al.  Chaos control using least squares support vector machines , 1999 .

[6]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[7]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[8]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[9]  Chenliang Xu,et al.  Image Caption Generation with Text-Conditional Semantic Attention , 2016, ArXiv.

[10]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[11]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Xu Jia,et al.  Guiding Long-Short Term Memory for Image Caption Generation , 2015, ArXiv.

[13]  Samy Bengio,et al.  Show and tell: A neural image caption generator , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Alex Graves,et al.  Long Short-Term Memory , 2020, Computer Vision.

[15]  Geoffrey Zweig,et al.  From captions to visual concepts and back , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[17]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[18]  Tony Beltramelli,et al.  pix2code: Generating Code from a Graphical User Interface Screenshot , 2017, EICS.

[19]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[20]  Eric Nichols,et al.  Named Entity Recognition with Bidirectional LSTM-CNNs , 2015, TACL.

[21]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Xu Jia,et al.  Guiding the Long-Short Term Memory Model for Image Caption Generation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[23]  Martin Fowler,et al.  Domain-Specific Languages , 2010, The Addison-Wesley signature series.