{"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":1774399995855,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819972531","type":"print"},{"value":"9789819972548","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-99-7254-8_25","type":"book-chapter","created":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T05:01:47Z","timestamp":1697864507000},"page":"319-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Web Page Segmentation: A DOM-Structural Cohesion Analysis Approach"],"prefix":"10.1007","author":[{"given":"Minh-Hieu","family":"Huynh","sequence":"first","affiliation":[]},{"given":"Quoc-Tri","family":"Le","sequence":"additional","affiliation":[]},{"given":"Vu","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Tien","family":"Nguyen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,21]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Alcic, S., Conrad, S.: Page segmentation by web content clustering. In: Proceedings of the WIMS, pp. 1\u20139 (2011)","DOI":"10.1145\/1988688.1988717"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Bar-Yossef, Z., Rajagopalan, S.: Template detection via data mining and its applications. In: Proceedings of the 11th WWW, pp. 580\u2013591 (2002)","DOI":"10.1145\/511446.511522"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Cai, D., He, X., Li, Z., Ma, W.Y., Wen, J.R.: Hierarchical clustering of www image search results using visual (2004)","DOI":"10.1145\/1027527.1027747"},{"key":"25_CR4","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":"25_CR5","unstructured":"Cai, D., Yu, S., Wen, J.R., Ma, W.Y.: VIPS: a vision-based page segmentation algorithm (2003)"},{"key":"25_CR6","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"6","author":"J Canny","year":"1986","unstructured":"Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 6, 679\u2013698 (1986)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Chakrabarti, D., Kumar, R., Punera, K.: A graph-theoretic approach to webpage segmentation. In: Proceedings of the 17th WWW, pp. 377\u2013386 (2008)","DOI":"10.1145\/1367497.1367549"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Chen, K., et al.: Hybrid task cascade for instance segmentation. In: CVPR, pp. 4974\u20134983 (2019)","DOI":"10.1109\/CVPR.2019.00511"},{"key":"25_CR9","unstructured":"Chen, K., et al.: MMDetection: Open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Cormer, M., Mann, R., Moffatt, K., Cohen, R.: Towards an improved vision-based web page segmentation algorithm. In: 2017 14th CRV, pp. 345\u2013352. IEEE (2017)","DOI":"10.1109\/CRV.2017.38"},{"key":"25_CR11","doi-asserted-by":"publisher","unstructured":"Jayashree, S.R., Dias, G., Andrew, J.J., Saha, S., Maurel, F., Ferrari, S.: Multimodal web page segmentation using self-organized multi-objective clustering. ACM Trans. Inf. Syst. 40(3) (2022). https:\/\/doi.org\/10.1145\/3480966","DOI":"10.1145\/3480966"},{"issue":"3","key":"25_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326457","volume":"19","author":"Z Jiang","year":"2019","unstructured":"Jiang, Z., Yin, H., Wu, Y., Lyu, Y., Min, G., Zhang, X.: Constructing novel block layouts for webpage analysis. TOIT 19(3), 1\u201318 (2019)","journal-title":"TOIT"},{"key":"25_CR13","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: Proceedings of the 29th ACM CIKM, CIKM 2020, pp. 3047\u20133054. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3340531.3412782","DOI":"10.1145\/3340531.3412782"},{"key":"25_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/978-3-030-72240-1_5","volume-title":"Advances in Information Retrieval","author":"J Kiesel","year":"2021","unstructured":"Kiesel, J., Meyer, L., Kneist, F., Stein, B., Potthast, M.: An empirical comparison of web page segmentation algorithms. In: Hiemstra, D., Moens, M.-F., Mothe, J., Perego, R., Potthast, M., Sebastiani, F. (eds.) ECIR 2021. LNCS, vol. 12657, pp. 62\u201374. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-72240-1_5"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Kohlsch\u00fctter, C., Nejdl, W.: A densitometric approach to web page segmentation. In: Proceedings of the 17th ACM CIKM, pp. 1173\u20131182 (2008)","DOI":"10.1145\/1458082.1458237"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Lu, C., Bing, L., Lam, W.: Structured positional entity language model for enterprise entity retrieval. In: 22nd ACM CIKM, pp. 129\u2013138 (2013)","DOI":"10.1145\/2505515.2505702"},{"issue":"12","key":"25_CR17","doi-asserted-by":"publisher","first-page":"1606","DOI":"10.14778\/2824032.2824058","volume":"8","author":"T Manabe","year":"2015","unstructured":"Manabe, T., Tajima, K.: Extracting logical hierarchical structure of html documents based on headings. Proc. VLDB Endow. 8(12), 1606\u20131617 (2015). https:\/\/doi.org\/10.14778\/2824032.2824058","journal-title":"Proc. VLDB Endow."},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Manku, G.S., Jain, A., Das Sarma, A.: Detecting near-duplicates for web crawling. In: Proceedings of the 16th WWW, pp. 141\u2013150 (2007)","DOI":"10.1145\/1242572.1242592"},{"key":"25_CR19","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 ICDAR, vol. 1, pp. 414\u2013419. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.75"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Narayana, V., Premchand, P., Govardhan, A.: A novel and efficient approach for near duplicate page detection in web crawling. In: 2009 IACC, pp. 1492\u20131496. IEEE (2009)","DOI":"10.1109\/IADCC.2009.4809238"},{"key":"25_CR21","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/j.is.2015.08.004","volume":"56","author":"M Pawlik","year":"2016","unstructured":"Pawlik, M., Augsten, N.: Tree edit distance: Robust and memory-efficient. Inf. Syst. 56, 157\u2013173 (2016). https:\/\/doi.org\/10.1016\/j.is.2015.08.004","journal-title":"Inf. Syst."},{"key":"25_CR22","doi-asserted-by":"publisher","unstructured":"Sanoja, A., Gan\u00e7arski, S.: Block-o-matic: a web page segmentation framework. In: 2014 ICMCS, pp. 595\u2013600 (2014). https:\/\/doi.org\/10.1109\/ICMCS.2014.6911249","DOI":"10.1109\/ICMCS.2014.6911249"},{"issue":"3","key":"25_CR23","first-page":"173","volume":"4","author":"RP Velloso","year":"2013","unstructured":"Velloso, R.P., Dorneles, C.F.: Automatic web page segmentation and noise removal for structured extraction using tag path sequences. JIDM 4(3), 173 (2013)","journal-title":"JIDM"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Vieira, K., Da Silva, A.S., Pinto, N., De Moura, E.S., Cavalcanti, J.M., Freire, J.: A fast and robust method for web page template detection and removal. In: 15th ACM CIKM, pp. 258\u2013267 (2006)","DOI":"10.1145\/1183614.1183654"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Xiang, P., Yang, X., Shi, Y.: Web page segmentation based on gestalt theory. In: 2007 IEEE ICME, pp. 2253\u20132256. IEEE (2007)","DOI":"10.1109\/ICME.2007.4285135"},{"key":"25_CR26","unstructured":"Xie, X., Miao, G., Song, R., Wen, J.R., Ma, W.Y.: Efficient browsing of web search results on mobile devices based on block importance model. In: 3rd IEEE PerCom, pp. 17\u201326. IEEE (2005)"},{"issue":"3","key":"25_CR27","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TSE.2022.3171295","volume":"49","author":"RK Yandrapally","year":"2023","unstructured":"Yandrapally, R.K., Mesbah, A.: Fragment-based test generation for web apps. IEEE Trans. Softw. Eng. 49(3), 1086\u20131101 (2023). https:\/\/doi.org\/10.1109\/TSE.2022.3171295","journal-title":"IEEE Trans. Softw. Eng."},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Yi, L., Liu, B., Li, X.: Eliminating noisy information in web pages for data mining. In: 9th KDD, pp. 296\u2013305 (2003)","DOI":"10.1145\/956750.956785"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Yin, X., Lee, W.S.: Understanding the function of web elements for mobile content delivery using random walk models. In: Special interest tracks and posters of the 14th WWW, pp. 1150\u20131151 (2005)","DOI":"10.1145\/1062745.1062913"}],"container-title":["Lecture Notes in Computer Science","Web Information Systems Engineering \u2013 WISE 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-7254-8_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T05:07:09Z","timestamp":1697864829000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-7254-8_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819972531","9789819972548"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-7254-8_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"21 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WISE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Web Information Systems Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Melbourne, VIC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wise2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.wise-conferences.org\/2023\/","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":"137","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":"33","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":"40","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":"24% - 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":"4","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)"}}]}}