Filters








22,636 Hits in 3.1 sec

Ranking robustness

Yun Zhou, W. Bruce Croft
2006 Proceedings of the 15th ACM international conference on Information and knowledge management - CIKM '06  
In this paper, we introduce the notion of ranking robustness, which refers to a property of a ranked list of documents that indicates how stable the ranking is in the presence of uncertainty in the ranked  ...  We demonstrate that the robustness score significantly and consistently correlates with query performance in a variety of TREC test collections including the GOV2 collection.  ...  Ranking robustness in noisy data retrieval refers to a property of a ranked list of documents that indicates how stable the ranking is in the presence of noise brought by the recognition process.  ... 
doi:10.1145/1183614.1183696 dblp:conf/cikm/ZhouC06 fatcat:feavtrzshjbbxjttxuwbkqld5q

Measuring ranked list robustness for query performance prediction

Yun Zhou, W. Bruce Croft
2007 Knowledge and Information Systems  
We introduce the notion of ranking robustness, which refers to a property of a ranked list of documents that indicates how stable the ranking is in the presence of uncertainty in the ranked documents.  ...  Our initial motivation for measuring ranking robustness is to predict topic difficulty for content-based queries in the ad-hoc retrieval task.  ...  Ranking robustness in noisy data retrieval refers to a property of a ranked list of documents that indicates how stable the ranking is in the presence of noise brought by the recognition process.  ... 
doi:10.1007/s10115-007-0100-8 fatcat:a3wpp4hv7fbkzozkkksq5cnjxy

Learning to Rank Microblog Posts for Real-Time Ad-Hoc Search [chapter]

Jing Li, Zhongyu Wei, Hao Wei, Kangfei Zhao, Junwen Chen, Kam-Fai Wong
2015 Lecture Notes in Computer Science  
However, it is not trivial to do microblog search due to the following reasons: 1) microblog posts are noisy and time-sensitive rendering general information retrieval models ineffective. 2) Conventional  ...  In this paper, we propose to utilize learning to rank model for microblog search.  ...  Another line of research in improving retrieval performance in microblog messages focused on using microblog-specific features to improve the performance of microblog retrieval [2, 5, 9, 11] .  ... 
doi:10.1007/978-3-319-25207-0_40 fatcat:nigfqigdjveztot4bujvpzhgqa

Improved Differential Evolution Algorithm for Parameter Estimation to Improve the Production of Biochemical Pathway

Chuii Khim Chong, Mohd Saberi Mohamad, Safaai Deris, Mohd Shahir Shamsir, Yee Wen Choon, Lian En Chai
2012 International Journal of Interactive Multimedia and Artificial Intelligence  
This paper introduces an improved Differential Evolution algorithm (IDE) which aims at improving its performance in estimating the relevant parameters for metabolic pathway data to simulate glycolysis  ...  Many computation algorithms face obstacles due to the noisy data and difficulty of the system in estimating myriad of parameters, and require longer computational time to estimate the relevant parameters  ...  The ability to handle noisy data has contributed to an improved accuracy of the estimated results.  ... 
doi:10.9781/ijimai.2012.153 fatcat:nxcdi7d44bfnxcgov4r3fokigm

Relabeling algorithm for retrieval of noisy instances and improving prediction quality

Shital Shah, Andrew Kusiak
2010 Computers in Biology and Medicine  
A relabeling algorithm for retrieval of noisy instances with binary outcomes is presented.  ...  The relabeling algorithm iteratively retrieves, selects, and re-labels data instances (i.e., transforms a decision space) to improve prediction quality.  ...  The approaches for retrieval of mislabeled instances presented in the literature generally use majority/consensus (allowing presence of impurity) filters to isolate stable and noisy instances.  ... 
doi:10.1016/j.compbiomed.2009.12.005 pmid:20097331 fatcat:vx27ubxhcneibdnrevb3yw6etq

Visual Phrases for Exemplar Face Detection

Vijay Kumar, Anoop Namboodiri, C. V. Jawahar
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
In this paradigm, each exemplar casts a vote using retrieval framework and generalized Hough voting, to locate the faces in the target image.  ...  We perform extensive experiments on standard FDDB, AFW and G-album datasets and show significant improvement over previous exemplar approaches.  ...  As we show in experiments, this approach results in a significant performance improvement over [13, 22] . Some of the works in the area of content-based retrieval have used similar insights.  ... 
doi:10.1109/iccv.2015.231 dblp:conf/iccv/KumarNJ15 fatcat:g4mifm442veetaengcb2vndprm

Term Proximity Constraints for Pseudo-Relevance Feedback

Ali Montazeralghaem, Hamed Zamani, Azadeh Shakery
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
Pseudo-relevance feedback (PRF) refers to a query expansion strategy based on top-retrieved documents, which has been shown to be highly e ective in many retrieval models.  ...  Experiments on four TREC collections demonstrate the e ectiveness of the proposed constraints. Our modi cation to the log-logistic model leads to signi cant and substantial (up to 15%) improvements.  ...  Acknowledgements. is work was supported in part by the Center for Intelligent Information Retrieval and in part by a grant from the Institute for Research in Fundamental Sciences (No. CS1396-4-51).  ... 
doi:10.1145/3077136.3080728 dblp:conf/sigir/Montazeralghaem17 fatcat:z2e2q3pexvbmbfwalhidfgtswm

Distributed Evaluations: Ending Neural Point Metrics [article]

Daniel Cohen, Scott M. Jordan, W. Bruce Croft
2018 arXiv   pre-print
As neural methods are starting to be incorporated into low resource and noisy collections that further exacerbate this issue, we propose evaluating neural models both over multiple random seeds and a set  ...  However, these networks often sample data in random order, are initialized randomly, and their success is determined by a single evaluation score.  ...  ACKNOWLEDGEMENTS This work was supported in part by the Center for Intelligent Information Retrieval.  ... 
arXiv:1806.03790v1 fatcat:yqgzdxerznhvjpelv6tptpmikm

Word Embedding based Generalized Language Model for Information Retrieval

Debasis Ganguly, Dwaipayan Roy, Mandar Mitra, Gareth J.F. Jones
2015 Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '15  
In this paper, we focus on the use of word embeddings for enhancing retrieval effectiveness.  ...  aims to address the vocabulary mismatch problem by taking into account other related terms in the collection.  ...  This research is supported by SFI through the CNGL Programme (Grant No: 12/CE/I2267) in the ADAPT Centre (www.adaptcentre.ie) at Dublin City University, and by a grant under the SFI ISCA India consortium  ... 
doi:10.1145/2766462.2767780 dblp:conf/sigir/GangulyRMJ15 fatcat:t62hzswpc5cmtdkybmrzigvgme

Unsupervised Data Uncertainty Learning in Visual Retrieval Systems [article]

Ahmed Taha, Yi-Ting Chen, Teruhisa Misu, Abhinav Shrivastava, Larry Davis
2019 arXiv   pre-print
This helps identify noisy observations in query and search databases. Evaluation on both image and video retrieval applications highlight the utility of our approach.  ...  Besides improving performance, our formulation models local noise in the embedding space. It quantifies input uncertainty and thus enhances interpretability of the system.  ...  This helps identify noisy and confusing objects in a retrieval system, either in queries or in the search gallery.  ... 
arXiv:1902.02586v1 fatcat:g4dtocduffcdxg2672d44qizam

Identifying personal health experience tweets with deep neural networks

Keyuan Jiang, Ravish Gupta, Matrika Gupta, Ricardo A. Calix, Gordon R. Bernard
2017 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)  
Our results demonstrated a significant amount of improvement in predicting personal health experience tweets by deep neural networks over that by conventional classifiers: 37.5% in accuracy, 31.1% in precision  ...  Twitter data are known for their irregular usages of languages and informal short texts due to the 140 character limit, and for their noisiness such that majority of the posts are irrelevant to any particular  ...  Acknowledgments Authors wish to thank Yongbing Tang for collecting the Twitter data, and Cecelia Lai for annotating the tweets.  ... 
doi:10.1109/embc.2017.8037039 pmid:29060084 pmcid:PMC5702551 dblp:conf/embc/JiangGGCB17 fatcat:vukcztehtjhjjlrlroefcbzsca

Accurate localization by fusing images and GPS signals

Kumar Vishal, C. V. Jawahar, Visesh Chari
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Specifically, we show how noisy GPS signals can be rectified by vision based localization of images captured in the vicinity.  ...  GPS sensors are a commercially viable option for localization, and are ubiquitous in their use, especially in portable devices.  ...  We define unstable objects / interest points as those non-stationary objects / interest points that hinder stable retrieval of a given object / location.  ... 
doi:10.1109/cvprw.2015.7301390 dblp:conf/cvpr/VishalJC15 fatcat:cmtk6qw2qvddhazlxd32h2ehli

Axiomatic Analysis for Improving the Log-Logistic Feedback Model

Ali Montazeralghaem, Hamed Zamani, Azadeh Shakery
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
Pseudo-relevance feedback (PRF) has been proven to be an effective query expansion strategy to improve retrieval performance. Several PRF methods have so far been proposed for many retrieval models.  ...  Experiments on three TREC newswire and web collections demonstrate that the proposed modification significantly outperforms the original log-logistic model, in all collections.  ...  This observation demonstrates that the log-logistic model is less effective and robust in improving the retrieval performance in the web collection, compared to the newswire collections.  ... 
doi:10.1145/2911451.2914768 dblp:conf/sigir/Montazeralghaem16 fatcat:xv7wnbba6nexrpnsdfbsca6ct4

Learning actions from the Web

Nazli Ikizler-Cinbis, R Gokberk Cinbis, Stan Sclaroff
2009 2009 IEEE 12th International Conference on Computer Vision  
Its benefits are two-fold: 1) we can improve retrieval of action images, and 2) we can collect a large generic database of action poses, which can then be used in tagging videos.  ...  The idea is to use images collected from the Web to learn representations of actions and use this knowledge to automatically annotate actions in videos.  ...  This work was supported in part through NSF grants IIS-0713168 and CNS-0202067.  ... 
doi:10.1109/iccv.2009.5459368 dblp:conf/iccv/Ikizler-CinbisCS09 fatcat:4vful757bzguld2alhjwmvuabi

Optimization of an Integrated Model for Automatic Reduction and Expansion of Long Queries [chapter]

Dawei Song, Yanjie Shi, Peng Zhang, Yuexian Hou, Bin Hu, Yuan Jia, Qiang Huang, Udo Kruschwitz, Anne De Roeck, Peter Bruza
2013 Lecture Notes in Computer Science  
In order to smooth such adverse effect, it is important to reduce noisy terms, introduce and boost additional relevant terms.  ...  Empirical evaluation on three large-scale TREC collections demonstrates that our approach, which is automatic, achieves salient improvements over various strong baselines, and also reaches a comparable  ...  This work is funded in part by the Chinese National Program on Key Basic Research Project (973 Program, grant no. 2013CB329304 and 2014CB744604), the Natural Science Foundation of China (grant no. 61272265  ... 
doi:10.1007/978-3-642-45068-6_12 fatcat:dpfaba4z2be5ngrh3zlm24qluq
« Previous Showing results 1 — 15 out of 22,636 results