Filters








8,316 Hits in 8.0 sec

Performance on Image Segmentation Resulting In Canny and MoG

Mr. S Ravikumar
2012 IOSR Journal of Computer Engineering  
The MoG algorithm is enhanced with combined feature weight model. The combined feature weight is used I segmentation the class assignment process.  ...  Images are analyzed with edge and color values. Pixel information is used in the color property extraction. Texture and contrast are pixel based features.  ...  Currently he is working as Assistant Professor in Bannari Amman Institute of Technology, Sathyamangalam. His area of interest includes Image Processing, Texture segmentation, Clustering.  ... 
doi:10.9790/0661-0620108 fatcat:vq7mo32nybdm5m5a5ef7aqhbky

Improving searcher models using mouse cursor activity

Jeff Huang, Ryen W. White, Georg Buscher, Kuansan Wang
2012 Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '12  
We start by exploring recorded user interactions with the search results, both qualitatively and quantitatively.  ...  While this data is easy to collect and provides information about user behavior, it omits user interactions with the search engine that do not hit the server; these logs omit search data such as users'  ...  Scrolling: Window scrolling is a client-side interaction that is rarely captured in the context of Web search.  ... 
doi:10.1145/2348283.2348313 dblp:conf/sigir/HuangWBW12 fatcat:qvzmpnr7irfkfeov2osbxuu6xi

Shopping in the Multiverse: A Counterfactual Approach to In-Session Attribution [article]

Jacopo Tagliabue, Bingqing Yu
2020 arXiv   pre-print
We tackle the challenge of in-session attribution for on-site search engines in eCommerce.  ...  We phrase the problem as a causal counterfactual inference, and contrast the approach with rule-based systems from industry settings and prediction models from the multi-touch attribution literature.  ...  Figure 7 : 7 Single-intent (left) and multi-intent (right) sessions in which the search interaction is causally relevant for the final purchase.  ... 
arXiv:2007.10087v1 fatcat:nzptlux2anh55cwuw7jkj7hzfu

Characterizing and Predicting Email Deferral Behavior

Bahareh Sarrafzadeh, Ahmed Hassan Awadallah, Christopher H. Lin, Chia-Jung Lee, Milad Shokouhi, Susan T. Dumais
2019 Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining - WSDM '19  
During a triage session, users commonly defer handling emails that they cannot immediately deal with to later.  ...  Inspired by the characteristics of deferred emails and contextual factors involved in deciding if an email should be deferred, we train a classifier for predicting whether a recently triaged email is actually  ...  Following the work on session segmentation in Web search, We segmented our logs into session based on a threshold on the time of inactivity between actions. Following Narang et al.  ... 
doi:10.1145/3289600.3291028 dblp:conf/wsdm/SarrafzadehALLS19 fatcat:eub4jult3fbm7fdsvrzbg3rxxq

A Model-Free Time Series Segmentation Approach for Land Cover Change Detection

Ashish Garg, Lydia Manikonda, Shashank Kumar, Vikrant Krishna, Shyam Boriah, Michael S. Steinbach, Durga Toshnival, Vipin Kumar, Christopher Potter, Steven A. Klooster
2011 Conference on Intelligent Data Understanding  
The conference originated in 2004 as a small workshop in Cleveland Ohio with about 25 participants. This is the second year that CIDU is publishing full-length papers.  ...  The conference features invited speakers, poster sessions, oral paper presentations, panel, and networking opportunities for interested researchers and students.  ...  Julie Winkler for valuable discussion on statistical downscaling for climate change projection.  ... 
dblp:conf/cidu/GargMKKBSTKPK11 fatcat:yur5kmzxovbuxczf6lrix43viy

Mining search and browse logs for web search

Daxin Jiang, Jian Pei, Hang Li
2013 ACM Transactions on Intelligent Systems and Technology  
Jian Pei's research in this work was supported in part by an NSERC Discovery Grant project and a BCFRST NRAS Endowment Research Team Program project.  ...  All opinions, findings, conclusions and recommendations in this paper are those of the authors and do not necessarily reflect the views of the funding agencies.  ...  The major difference between the search state and the browse state lies in the type of server which the user interacts with: if a user is interacting with a search engine, she is in the search state; otherwise  ... 
doi:10.1145/2508037.2508038 fatcat:rfysu5bx7vaabgd4jyms2wyyta

Modeling actions of PubMed users with n-gram language models

Jimmy Lin, W. John Wilbur
2008 Information retrieval (Boston)  
We encode user actions as string sequences and model these sequences using n-gram language models. The models are evaluated in terms of perplexity and in a sequence prediction task.  ...  Unlike most previous studies on general Web search, our work examines user activities with a highly-specialized search engine.  ...  Open Access This article is distributed under the terms of the Creative Commons Attribution Noncommercial License which permits any noncommercial use, distribution, and reproduction in any medium, provided  ... 
doi:10.1007/s10791-008-9067-7 pmid:19684883 pmcid:PMC2727615 fatcat:57ratsdp5ngbhlarqyxiuhviee

Segment Routing: a Comprehensive Survey of Research Activities, Standardization Efforts and Implementation Results [article]

Pier Luigi Ventre, Stefano Salsano, Marco Polverini, Antonio Cianfrani, Ahmed Abdelsalam, Clarence Filsfils, Pablo Camarillo, Francois Clad
2020 arXiv   pre-print
Then, we provide a tutorial on Segment Routing technology, with a focus on the novel SRv6 solution.  ...  We start with an introduction on the motivations for Segment Routing and an overview of its evolution and standardization.  ...  In particular, the authors focus on static fast failover solutions for Segment Routing, not requiring any interaction with the control plane.  ... 
arXiv:1904.03471v5 fatcat:2qofywgo7rcwrblltqog4fyzm4

Probabilistic models for personalizing web search

David Sontag, Kevyn Collins-Thompson, Paul N. Bennett, Ryen W. White, Susan Dumais, Bodo Billerbeck
2012 Proceedings of the fifth ACM international conference on Web search and data mining - WSDM '12  
Our findings demonstrate gains in retrieval performance for queries with high ambiguity, with particularly large improvements for acronym queries.  ...  We present a new approach for personalizing Web search results to a specific user.  ...  Acknowledgements Thanks to Dan Liebling and Josh Feng for assistance with data collection and classification.  ... 
doi:10.1145/2124295.2124348 dblp:conf/wsdm/SontagCBWDB12 fatcat:lufhjzg7ajgazpi4hmev4dpfkm

QoE Management of Multimedia Streaming Services in Future Networks: A Tutorial and Survey

Alcardo Alex Barakabitze, Nabajeet Barman, Arslan Ahmad, Saman Zadtootaghaj, Lingfen Sun, Maria G. Martini, Luigi Atzori
2019 IEEE Communications Surveys and Tutorials  
We then summarize the key elements in SDN/NFV along with an overview of ongoing research projects, standardization activities and use cases related to SDN, NFV, and other emerging applications.  ...  Finally, we provide a discussion on future research directions with a focus on emerging research areas in QoE management, such as QoE-oriented business models, QoE-based big data strategies, and scalability  ...  The monitoring tool runs at the client side to provide a quantification of status for the running applications and enables to predict the end-users QoE.  ... 
doi:10.1109/comst.2019.2958784 fatcat:7bgzl5rpmfgedo5e5psz7i3t4a

A Survey of Query Auto Completion in Information Retrieval

Fei Cai, Maarten de Rijke
2016 Foundations and Trends in Information Retrieval  
search intents.  ...  : given a prefix consisting of a number of characters entered into a search box, the user interface proposes alternative ways of extending the prefix to a full query.  ...  In their study, the participants' interactions are recorded using eye-tracking and client-side logging when they complete the assigned web search tasks.  ... 
doi:10.1561/1500000055 fatcat:cwnopwelhnbdbn4s3joiarmymq

Search Result Prefetching Using Cursor Movement

Fernando Diaz, Qi Guo, Ryen W. White
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
Balancing the costs in prefetching particular results against the benefits in reduced latency to searchers represents the search result prefetching challenge.  ...  We present methods that leverage searchers' cursor movements on search result pages in real time to dynamically estimate the result that searchers will request next.  ...  In the current implementation, we optimize our client-side code to ensure no significant delay on PLT for SERPs with the logging enabled.  ... 
doi:10.1145/2911451.2911516 dblp:conf/sigir/DiazGW16 fatcat:styflimtq5aexcvwmovsfscibm

Modeling dwell time to predict click-level satisfaction

Youngho Kim, Ahmed Hassan, Ryen W. White, Imed Zitouni
2014 Proceedings of the 7th ACM international conference on Web search and data mining - WSDM '14  
Clicks on search results are the most widely used behavioral signals for predicting search satisfaction. Even though clicks are correlated with satisfaction, they can also be noisy.  ...  We show that the topic of the page, its length and its readability level are critical in determining the amount of dwell time needed to predict whether any click is associated with satisfaction.  ...  ., client side monitoring rather than server side as reported here), study other factors that may affect click dwell time (e.g., pages revisited by the same user may lead to lower dwell times given increased  ... 
doi:10.1145/2556195.2556220 dblp:conf/wsdm/KimHWZ14 fatcat:zvskvygasngmxdglt4vklfmr4q

Enhancing web search by promoting multiple search engine use

Ryen W. White, Matthew Richardson, Mikhail Bilenko, Allison P. Heath
2008 Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '08  
Any given Web search engine may provide higher quality results than others for certain queries. Therefore, it is in users' best interest to utilize multiple search engines.  ...  In contrast to prior work on meta-search, we do not advocate for replacement of multiple engines with an aggregate one, but rather facilitate simultaneous use of individual engines.  ...  The logs gave us access to user interactions with all search engines. From these logs, we extracted search sessions that began with a query to Google, Yahoo!  ... 
doi:10.1145/1390334.1390344 dblp:conf/sigir/WhiteRBH08 fatcat:4tavswoklrdxxjybiybq7j5oia

Investigating behavioral variability in web search

Ryen W. White, Steven M. Drucker
2007 Proceedings of the 16th international conference on World Wide Web - WWW '07  
We analyze the search interactions of more than two thousand volunteer users over a five-month period, with the aim of characterizing differences in their interaction styles.  ...  Understanding the extent to which people's search behaviors differ in terms of the interaction flow and information targeted is important in designing interfaces to help World Wide Web users search more  ...  Through client-side logging of 2,527 users over a five-month period, we gathered sufficient interaction log data to perform a detailed analysis of variability in search behavior within and between users  ... 
doi:10.1145/1242572.1242576 dblp:conf/www/WhiteD07 fatcat:xzcpqphsh5d4pfy5yxpajkcvom
« Previous Showing results 1 — 15 out of 8,316 results