skip to main content
10.1145/3603781.3603862acmotherconferencesArticle/Chapter ViewAbstractPublication PagescniotConference Proceedingsconference-collections
research-article

YOLO-WS: A Novel Method for Webpage Segmentation

Published:27 July 2023Publication History

ABSTRACT

To address the limitations of traditional heuristic and machine learning-based webpage segmentation algorithms in feature extraction performance and efficiency, we propose a webpage segmentation method based on deep learning object detection. Specifically, we propose a webpage segmentation method named YOLO-WS based on the YOLOv5 model. We optimized and improved the YOLOv5 model’s network structure, loss function, and post-processing for webpage segmentation tasks, and then use transfer learning to train YOLO-WS on the improved model. Experimental results show that YOLO-WS achieves good performance in web page segmentation tasks.

References

  1. Deng Cai, Shipeng Yu, Ji-Rong Wen, and Wei-Ying Ma. 2003. Vips: a vision-based page segmentation algorithm. (2003).Google ScholarGoogle Scholar
  2. Michael Cormer, Richard Mann, Karyn Moffatt, and Robin Cohen. [n. d.]. Towards an Improved Vision-Based Web Page Segmentation Algorithm. In 2017 14th Conference on Computer and Robot Vision (CRV) (2017-05). 345–352. https://doi.org/10.1109/CRV.2017.38Google ScholarGoogle ScholarCross RefCross Ref
  3. Qibin Hou, Daquan Zhou, and Jiashi Feng. [n. d.]. Coordinate Attention for Efficient Mobile Network Design. arxiv:2103.02907 [cs]http://arxiv.org/abs/2103.02907Google ScholarGoogle Scholar
  4. Glenn Jocher, Ayush Chaurasia, Alex Stoken, Jirka Borovec, NanoCode012, Yonghye Kwon, Kalen Michael, TaoXie, Jiacong Fang, imyhxy, Lorna, 曾逸夫(Zeng Yifu), Colin Wong, Abhiram V, Diego Montes, Zhiqiang Wang, Cristi Fati, Jebastin Nadar, Laughing, UnglvKitDe, Victor Sonck, tkianai, yxNONG, Piotr Skalski, Adam Hogan, Dhruv Nair, Max Strobel, and Mrinal Jain. [n. d.]. ultralytics/yolov5: v7.0 - YOLOv5 SOTA Realtime Instance Segmentation. https://doi.org/10.5281/zenodo.7347926Google ScholarGoogle ScholarCross RefCross Ref
  5. Johannes Kiesel, Florian Kneist, Lars Meyer, Kristof Komlossy, Benno Stein, and Martin Potthast. [n. d.]. Web Page Segmentation Revisited: Evaluation Framework and Dataset. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management (New York, NY, USA, 2020-10-19) (CIKM ’20). Association for Computing Machinery, 3047–3054. https://doi.org/10.1145/3340531.3412782Google ScholarGoogle ScholarDigital LibraryDigital Library
  6. Ningning Ma, Xiangyu Zhang, and Jian Sun. [n. d.]. Funnel Activation for Visual Recognition. https://doi.org/10.48550/arXiv.2007.11824 arxiv:2007.11824 [cs]Google ScholarGoogle ScholarCross RefCross Ref
  7. Tomohiro Manabe and Keishi Tajima. [n. d.]. Extracting logical hierarchical structure of HTML documents based on headings. 8, 12 ([n. d.]), 1606–1617. https://doi.org/10.14778/2824032.2824058Google ScholarGoogle ScholarDigital LibraryDigital Library
  8. Birgit Pfitzmann, Christoph Auer, Michele Dolfi, Ahmed S. Nassar, and Peter W. J. Staar. [n. d.]. DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (2022-08-14). 3743–3751. https://doi.org/10.1145/3534678.3539043 arxiv:2206.01062 [cs]Google ScholarGoogle ScholarDigital LibraryDigital Library
  9. Roman Solovyev, Weimin Wang, and Tatiana Gabruseva. [n. d.]. Weighted boxes fusion: Ensembling boxes from different object detection models. 107 ([n. d.]), 104117. https://doi.org/10.1016/j.imavis.2021.104117Google ScholarGoogle ScholarCross RefCross Ref
  10. Dongxian Wu, Yisen Wang, Shu-Tao Xia, James Bailey, and Xingjun Ma. [n. d.]. Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets. arxiv:2002.05990 [cs, stat]http://arxiv.org/abs/2002.05990Google ScholarGoogle Scholar
  11. Yi-Fan Zhang, Weiqiang Ren, Zhang Zhang, Zhen Jia, Liang Wang, and Tieniu Tan. [n. d.]. Focal and Efficient IOU Loss for Accurate Bounding Box Regression. arxiv:2101.08158 [cs]http://arxiv.org/abs/2101.08158Google ScholarGoogle Scholar

Index Terms

  1. YOLO-WS: A Novel Method for Webpage Segmentation

      Recommendations

      Comments

      Login options

      Check if you have access through your login credentials or your institution to get full access on this article.

      Sign in
      • Published in

        cover image ACM Other conferences
        CNIOT '23: Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things
        May 2023
        1025 pages
        ISBN:9798400700705
        DOI:10.1145/3603781

        Copyright © 2023 ACM

        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        • Published: 27 July 2023

        Permissions

        Request permissions about this article.

        Request Permissions

        Check for updates

        Qualifiers

        • research-article
        • Research
        • Refereed limited

        Acceptance Rates

        Overall Acceptance Rate39of82submissions,48%
      • Article Metrics

        • Downloads (Last 12 months)42
        • Downloads (Last 6 weeks)7

        Other Metrics

      PDF Format

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      HTML Format

      View this article in HTML Format .

      View HTML Format