{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T03:09:32Z","timestamp":1777432172930,"version":"3.51.4"},"publisher-location":"New York, New York, USA","reference-count":36,"publisher":"ACM Press","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1145\/3178876.3186167","type":"proceedings-article","created":{"date-parts":[[2018,4,13]],"date-time":"2018-04-13T15:53:48Z","timestamp":1523634828000},"page":"1865-1874","source":"Crossref","is-referenced-by-count":6,"title":["Hidden in Plain Sight"],"prefix":"10.1145","author":[{"given":"Navneet","family":"Potti","sequence":"first","affiliation":[{"name":"University of Wisconsin - Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James B.","family":"Wendt","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sandeep","family":"Tata","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Najork","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","reference":[{"key":"key-10.1145\/3178876.3186167-1","unstructured":"Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A System for Large-scale Machine Learning. In Proc. of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI). 265--283."},{"key":"key-10.1145\/3178876.3186167-2","unstructured":"Douglas Aberdeen, Ondrej Pacovsky, and Andrew Slater. 2010. The Learning Behind Gmail Priority Inbox. In LCCC: NIPS 2010 Workshop on Learning on Cores, Clusters and Clouds."},{"key":"key-10.1145\/3178876.3186167-3","doi-asserted-by":"crossref","unstructured":"Nir Ailon, Zohar S Karnin, Edo Liberty, and Yoelle Maarek. 2013. Threading Machine Generated Email. In Proc. of the 6th ACM International Conference on Web Search and Data Mining (WSDM). 405--414.","DOI":"10.1145\/2433396.2433447"},{"key":"key-10.1145\/3178876.3186167-4","doi-asserted-by":"crossref","unstructured":"Noa Avigdor-Elgrabli, Mark Cwalinski, Dotan Di Castro, Iftah Gamzu, Irena Grabovitch-Zuyev, Liane Lewin-Eytan, and Yoelle Maarek. 2016. Structural Clustering of Machine-Generated Mail. In Proc. of the 25th ACM International on Conference on Information and Knowledge Management (CIKM). 217--226.","DOI":"10.1145\/2983323.2983350"},{"key":"key-10.1145\/3178876.3186167-5","doi-asserted-by":"crossref","unstructured":"Michael Bendersky, Xuanhui Wang, Donald Metzler, and Marc Najork. 2017. Learning from User Interactions in Personal Search via Attribute Parameterization. In Proc. of the 10th ACM International Conference on Web Search and Data Mining (WSDM). 791--799.","DOI":"10.1145\/3018661.3018712"},{"key":"key-10.1145\/3178876.3186167-6","doi-asserted-by":"crossref","unstructured":"Alessandro Bissacco, Mark Cummins, Yuval Netzer, and Hartmut Neven. 2013. PhotoOCR: Reading Text in Uncontrolled Conditions. In Proc. of the 2013 IEEE International Conference on Computer Vision (ICCV). 785--792.","DOI":"10.1109\/ICCV.2013.102"},{"key":"key-10.1145\/3178876.3186167-7","doi-asserted-by":"crossref","unstructured":"Enrico Blanzieri and Anton Bryl. 2008. A Survey of Learning-based Techniques of Email Spam Filtering. Artificial Intelligence Review 29, 1 (2008), 63--92.","DOI":"10.1007\/s10462-009-9109-6"},{"key":"key-10.1145\/3178876.3186167-8","unstructured":"Chia-Hui Chang, Mohammed Kayed, Moheb R Girgis, and Khaled F Shaalan. 2006. A Survey of Web Information Extraction Systems. IEEE Transactions on Knowledge and Data Engineering 18, 10 (2006), 1411--1428."},{"key":"key-10.1145\/3178876.3186167-9","unstructured":"Michael Chui, James Manyika, Jacques Bughin, Richard Dobbs, Charles Roxburgh, Hugo Sarrazin, Geoffrey Sands, and Magdalena Westergren. 2012. The Social Economy: Unlocking Value and Productivity through Social Technologies. McKinsey Global Institute."},{"key":"key-10.1145\/3178876.3186167-10","doi-asserted-by":"crossref","unstructured":"Dotan Di Castro, Zohar Karnin, Liane Lewin-Eytan, and Yoelle Maarek. 2016. You've Got Mail, and Here is What You Could Do With It!: Analyzing and Predicting Actions on Email Messages. In Proc. of the 9th ACM International Conference on Web Search and Data Mining (WSDM). 307--316.","DOI":"10.1145\/2835776.2835811"},{"key":"key-10.1145\/3178876.3186167-11","doi-asserted-by":"crossref","unstructured":"Dotan Di Castro, Liane Lewin-Eytan, Yoelle Maarek, Ran Wolff, and Eyal Zohar. 2016. Enforcing K-anonymity in Web Mail Auditing. In Proc. of the 9th ACM International Conference on Web Search and Data Mining (WSDM). 327--336.","DOI":"10.1145\/2835776.2835803"},{"key":"key-10.1145\/3178876.3186167-12","doi-asserted-by":"crossref","unstructured":"Y. Fujii, D. Genzel, A. C. Popat, and R. Teunen. 2015. Label Transition and Selection Pruning and Automatic Decoding Parameter Optimization for Timesynchronous Viterbi Decoding. In Proc. of the 13th International Conference on Document Analysis and Recognition (ICDAR). 756--760.","DOI":"10.1109\/ICDAR.2015.7333863"},{"key":"key-10.1145\/3178876.3186167-13","doi-asserted-by":"crossref","unstructured":"Iftah Gamzu, Zohar Karnin, Yoelle Maarek, and David Wajc. 2015. You Will Get Mail! Predicting the Arrival of Future Email. In Proc. of the 24th International Conference on World Wide Web (WWW). 1327--1332.","DOI":"10.1145\/2740908.2741694"},{"key":"key-10.1145\/3178876.3186167-14","doi-asserted-by":"crossref","unstructured":"Daniel Golovin, Benjamin Solnik, Subhodeep Moitra, Greg Kochanski, John Karro, and D. Sculley. 2017. Google Vizier: A Service for Black-Box Optimization. In Proc. of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 1487--1495.","DOI":"10.1145\/3097983.3098043"},{"key":"key-10.1145\/3178876.3186167-15","unstructured":"Google. 2015. Cloud Vision API. https:\/\/cloud.google.com\/vision\/. (2015)."},{"key":"key-10.1145\/3178876.3186167-16","doi-asserted-by":"crossref","unstructured":"Mihajlo Grbovic, Guy Halawi, Zohar Karnin, and Yoelle Maarek. 2014. How Many Folders Do You Really Need?: Classifying Email nto a Handful of Categories. In Proc. of the 23rd ACM International Conference on Conference on Information and Knowledge Management (KDD). 869--878.","DOI":"10.1145\/2661829.2662018"},{"key":"key-10.1145\/3178876.3186167-17","doi-asserted-by":"crossref","unstructured":"Mihajlo Grbovic, Vladan Radosavljevic, Nemanja Djuric, Narayan Bhamidipati, Jaikit Savla, Varun Bhagwan, and Doug Sharp. 2015. E-commerce in Your Inbox: Product Recommendations at Scale. In Proc. of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 1809--1818.","DOI":"10.1145\/2783258.2788627"},{"key":"key-10.1145\/3178876.3186167-18","unstructured":"The Radicati Group. 2017. Email Statistics Report, 2017--2021. http:\/\/www.radicati. com\/?p=8801. (2017)."},{"key":"key-10.1145\/3178876.3186167-19","doi-asserted-by":"crossref","unstructured":"Anjuli Kannan, Karol Kurach, Sujith Ravi, Tobias Kaufmann, Andrew Tomkins, Balint Miklos, Greg Corrado, Laszlo Lukacs, Marina Ganea, Peter Young, and Vivek Ramavajjala. 2016. Smart Reply: Automated Response Suggestion for Email. In Proc. of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 955--964.","DOI":"10.1145\/2939672.2939801"},{"key":"key-10.1145\/3178876.3186167-20","unstructured":"Nicholas Kushmerick, Daniel S. Weld, and Robert Doorenbos. 1997. Wrapper Induction for Information Extraction. In Proc. of the 15th International Joint Conference on Artificial Intelligence (IJCAI). 729--737."},{"key":"key-10.1145\/3178876.3186167-21","doi-asserted-by":"crossref","unstructured":"Himabindu Lakkaraju, Jon Kleinberg, Jure Leskovec, Jens Ludwig, and Sendhil Mullainathan. 2017. The Selective Labels Problem: Evaluating Algorithmic Predictions in the Presence of Unobservables. In Proc. of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 275-- 284.","DOI":"10.1145\/3097983.3098066"},{"key":"key-10.1145\/3178876.3186167-22","unstructured":"Philippe Le Hégaret, Ray Whitmer, and Lauren Wood. 2005. Document Object Model (DOM). http:\/\/www.w3.org\/DOM. (2005)."},{"key":"key-10.1145\/3178876.3186167-23","doi-asserted-by":"crossref","unstructured":"Yoelle Maarek. 2017. Web Mail is not Dead!: It's Just Not Human Anymore. In Proc. of the 26th International Conference on World Wide Web (WWW). 5--5.","DOI":"10.1145\/3038912.3050916"},{"key":"key-10.1145\/3178876.3186167-24","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. In Proc. of the 1st International Conference on Learning Representations: Workshop Track (ICLR). arXiv:1301.3781"},{"key":"key-10.1145\/3178876.3186167-25","doi-asserted-by":"crossref","unstructured":"Marc Najork. 2016. Using Machine Learning to Improve the Email Experience. In Proc. of the 25th ACM International on Conference on Information and Knowledge Management (CIKM). 891--891.","DOI":"10.1145\/2983323.2983371"},{"key":"key-10.1145\/3178876.3186167-26","doi-asserted-by":"crossref","unstructured":"Christopher Olston and Marc Najork. 2010. Web Crawling. Foundations and Trends in Information Retrieval 4, 3 (2010), 175--246.","DOI":"10.1561\/1500000017"},{"key":"key-10.1145\/3178876.3186167-27","doi-asserted-by":"crossref","unstructured":"Julia Proskurnia, Marc-Allen Cartright, Lluís Garcia-Pueyo, Ivo Krka, James B Wendt, Tobias Kaufmann, and Balint Miklos. 2017. Template Induction over Unstructured Email Corpora. In Proc. of the 26th International Conference on World Wide Web (WWW). 1521--1530.","DOI":"10.1145\/3038912.3052631"},{"key":"key-10.1145\/3178876.3186167-28","doi-asserted-by":"crossref","unstructured":"Sunita Sarawagi. 2008. Information Extraction. Foundations and Trends in Databases 1, 3 (2008), 261--377.","DOI":"10.1561\/1900000003"},{"key":"key-10.1145\/3178876.3186167-29","doi-asserted-by":"crossref","unstructured":"Ray Smith. 2007. An Overview of the Tesseract OCR Engine. In Proc. of the 9th International Conference on Document Analysis and Recognition (ICDAR). 629--633.","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"key-10.1145\/3178876.3186167-30","doi-asserted-by":"crossref","unstructured":"Sandeep Tata, Alexandrin Popescul, Marc Najork, Mike Colagrosso, Julian Gibbons, Alan Green, Alexandre Mah, Michael Smith, Divanshu Garg, Cayden Meyer, et al. 2017. Quick Access: Building a Smart Experience for Google Drive. In Proc. of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 1643--1651.","DOI":"10.1145\/3097983.3098048"},{"key":"key-10.1145\/3178876.3186167-31","unstructured":"W3C. 1999. Objects, Images, and Applets. https:\/\/www.w3.org\/TR\/html4\/struct\/ objects.html. (1999)."},{"key":"key-10.1145\/3178876.3186167-32","unstructured":"W3C. 2009. HTML Microdata. https:\/\/dev.w3.org\/html5\/md-LC\/. (2009)."},{"key":"key-10.1145\/3178876.3186167-33","doi-asserted-by":"crossref","unstructured":"Kai Wang, Boris Babenko, and Serge Belongie. 2011. End-to-End Scene Text Recognition. In Proc. of the 2011 International Conference on Computer Vision (ICCV). 1457--1464.","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"key-10.1145\/3178876.3186167-34","doi-asserted-by":"crossref","unstructured":"James B. Wendt, Michael Bendersky, Lluis Garcia-Pueyo, Vanja Josifovski, Balint Miklos, Ivo Krka, Amitabh Saikia, Jie Yang, Marc-Allen Cartright, and Sujith Ravi. 2016. Hierarchical Label Propagation and Discovery for Machine Generated Email. In Proc. of the 9th ACM International Conference on Web Search and Data Mining (WSDM). 317--326.","DOI":"10.1145\/2835776.2835780"},{"key":"key-10.1145\/3178876.3186167-35","doi-asserted-by":"crossref","unstructured":"Aston Zhang, Lluis Garcia-Pueyo, James B Wendt, Marc Najork, and Andrei Broder. 2017. Email Category Prediction. In Proc. of the 26th International Conference on World Wide Web Companion (WWW). 495--503.","DOI":"10.1145\/3041021.3055166"},{"key":"key-10.1145\/3178876.3186167-36","doi-asserted-by":"crossref","unstructured":"Weinan Zhang, Amr Ahmed, Jie Yang, Vanja Josifovski, and Alex J. Smola. 2015. Annotating Needles in the Haystack Without Looking: Product Information Extraction from Emails. In Proc. of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 2257--2266.","DOI":"10.1145\/2783258.2788580"}],"event":{"name":"the 2018 World Wide Web Conference","location":"Lyon, France","acronym":"WWW '18","number":"2018","sponsor":["SIGWEB, ACM Special Interest Group on Hypertext, Hypermedia, and Web","IW3C2, International World Wide Web Conference Committee"],"start":{"date-parts":[[2018,4,23]]},"end":{"date-parts":[[2018,4,27]]}},"container-title":["Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3178876.3186167","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/dl.acm.org\/ft_gateway.cfm?id=3186167&ftid=1957439&dwn=1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:08:17Z","timestamp":1750208897000},"score":1,"resource":{"primary":{"URL":"http:\/\/dl.acm.org\/citation.cfm?doid=3178876.3186167"}},"subtitle":["Classifying Emails Using Embedded Image Contents"],"proceedings-subject":"World Wide Web","short-title":[],"issued":{"date-parts":[[2018]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1145\/3178876.3186167","relation":{},"subject":[],"published":{"date-parts":[[2018]]}}}