{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:53:15Z","timestamp":1774399995440,"version":"3.50.1"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030722395","type":"print"},{"value":"9783030722401","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-72240-1_5","type":"book-chapter","created":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T14:49:01Z","timestamp":1617288541000},"page":"62-74","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["An Empirical Comparison of Web Page Segmentation Algorithms"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1617-6508","authenticated-orcid":false,"given":"Johannes","family":"Kiesel","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7280-808X","authenticated-orcid":false,"given":"Lars","family":"Meyer","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4111-662X","authenticated-orcid":false,"given":"Florian","family":"Kneist","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9033-2217","authenticated-orcid":false,"given":"Benno","family":"Stein","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2451-0665","authenticated-orcid":false,"given":"Martin","family":"Potthast","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,3,30]]},"reference":[{"issue":"4","key":"5_CR1","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1007\/s10791-008-9066-8","volume":"12","author":"E Amig\u00f3","year":"2009","unstructured":"Amig\u00f3, E., Gonzalo, J., Artiles, J., Verdejo, F.: A comparison of extrinsic clustering evaluation metrics based on formal constraints. Inf. Retr. 12(4), 461\u2013486 (2009). https:\/\/doi.org\/10.1007\/s10791-008-9066-8","journal-title":"Inf. Retr."},{"key":"5_CR2","unstructured":"Arias, J., Deschacht, K., Moens, M.F.: Language independent content extraction from web pages. In: Proceedings of the 9th Dutch-Belgian Information Retrieval Workshop, pp. 50\u201355. University of Twente, Enschede (2009)"},{"key":"5_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1007\/3-540-36901-5_42","volume-title":"Web Technologies and Applications","author":"D Cai","year":"2003","unstructured":"Cai, D., Yu, S., Wen, J.-R., Ma, W.-Y.: Extracting content structure for web pages based on visual representation. In: Zhou, X., Orlowska, M.E., Zhang, Y. (eds.) APWeb 2003. LNCS, vol. 2642, pp. 406\u2013417. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-36901-5_42"},{"key":"5_CR4","unstructured":"Chen, K., et al.: MMDetection: open MMLab detection toolbox and benchmark. CoRR abs\/1906.07155 (2019). http:\/\/arxiv.org\/abs\/1906.07155"},{"key":"5_CR5","unstructured":"Chen, K., et al.: Hybrid task cascade for instance segmentation. CoRR abs\/1901.07518 (2019). http:\/\/arxiv.org\/abs\/1901.07518"},{"key":"5_CR6","doi-asserted-by":"publisher","unstructured":"Cormier, M., Mann, R., Moffatt, K., Cohen, R.: Towards an improved vision-based web page segmentation algorithm. In: 14th Conference on Computer and Robot Vision, CRV 2017, pp. 345\u2013352 (2017). https:\/\/doi.org\/10.1109\/CRV.2017.38","DOI":"10.1109\/CRV.2017.38"},{"key":"5_CR7","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.cviu.2016.02.007","volume":"148","author":"M Cormier","year":"2016","unstructured":"Cormier, M., Moffatt, K., Cohen, R., Mann, R.: Purely vision-based segmentation of web pages for assistive technology. Comput. Vis. Image Underst. 148, 46\u201366 (2016). https:\/\/doi.org\/10.1016\/j.cviu.2016.02.007","journal-title":"Comput. Vis. Image Underst."},{"key":"5_CR8","unstructured":"Goldstein, E.B.: Sensation and Perception. Cengage Learning, 8th edn. (2009). ISBN 9780495601494"},{"issue":"4","key":"5_CR9","doi-asserted-by":"publisher","first-page":"17:1","DOI":"10.1145\/3239574","volume":"10","author":"J Kiesel","year":"2018","unstructured":"Kiesel, J., Kneist, F., Alshomary, M., Stein, B., Hagen, M., Potthast, M.: Reproducible web corpora: interactive archiving with automatic quality assessment. J. Data Inf. Qual. (JDIQ) 10(4), 17:1\u201317:25 (2018). https:\/\/doi.org\/10.1145\/3239574. https:\/\/dl.acm.org\/authorize?N676358","journal-title":"J. Data Inf. Qual. (JDIQ)"},{"key":"5_CR10","doi-asserted-by":"publisher","unstructured":"Kiesel, J., Kneist, F., Meyer, L., Komlossy, K., Stein, B., Potthast, M.: Web page segmentation revisited: evaluation framework and dataset. In: d\u2019Aquin, M., Dietze, S., Hauff, C., Curry, E., Cudr\u00e9-Mauroux, P. (eds.) 29th ACM International Conference on Information and Knowledge Management (CIKM 2020), pp. 3047\u20133054. ACM (October 2020). https:\/\/doi.org\/10.1145\/3340531.3412782","DOI":"10.1145\/3340531.3412782"},{"key":"5_CR11","doi-asserted-by":"publisher","unstructured":"Kumar, R., et al.: Webzeitgeist: design mining the web. In: Mackay, W.E., Brewster, S.A., B\u00f8dker, S. (eds.) 2013 ACM SIGCHI Conference on Human Factors in Computing Systems, CHI 2013, pp. 3083\u20133092. ACM (2013). https:\/\/doi.org\/10.1145\/2470654.2466420","DOI":"10.1145\/2470654.2466420"},{"key":"5_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"5_CR13","unstructured":"Ma, L., Goharian, N., Chowdhury, A.: Automatic data extraction from template generated web pages. In: Arabnia, H.R., Mun, Y. (eds.) Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications, PDPTA 2003, pp. 642\u2013648. CSREA Press (2003)"},{"issue":"12","key":"5_CR14","first-page":"1606","volume":"8","author":"T Manabe","year":"2015","unstructured":"Manabe, T., Tajima, K.: Extracting logical hierarchical structure of HTML documents based on headings. PVLDB 8(12), 1606\u20131617 (2015)","journal-title":"PVLDB"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Meier, B., Stadelmann, T., Stampfli, J., Arnold, M., Cieliebak, M.: Fully convolutional neural networks for newspaper article segmentation. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 414\u2013419. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.75"},{"key":"5_CR16","volume-title":"Eyetracking Web Usability","author":"J Nielsen","year":"2010","unstructured":"Nielsen, J., Pernice, K.: Eyetracking Web Usability. Pearson Education, London (2010). ISBN 9780321714077"},{"issue":"3","key":"5_CR17","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1016\/j.ipm.2017.02.002","volume":"53","author":"J Zeleny","year":"2017","unstructured":"Zeleny, J., Burget, R., Zendulka, J.: Box clustering segmentation: a new method for vision-based web page preprocessing. Inf. Process. Manag. 53(3), 735\u2013750 (2017). https:\/\/doi.org\/10.1016\/j.ipm.2017.02.002","journal-title":"Inf. Process. Manag."}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-72240-1_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T15:24:55Z","timestamp":1617290695000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-72240-1_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030722395","9783030722401"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-72240-1_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"30 March 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 March 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 April 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"43","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ecir2021.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"436","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"50","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"39","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"11% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}