4,941 Hits in 5.6 sec

Retrieval activities in a database consisting of heterogeneous collections of structured text

Forbes J. Burkowski
1992 Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '92  
The database is considered to be a hierarchical collection of contiguous extents each extent being a word, word phrase, text element or non-text element.  ...  The first part of this paper briefly describes a mathematical framework (called the containment model) that provides the operations and data structures for a text dominated database with a hierarchical  ...  Similar information is used by a Full-Text Search Window, in particular, it must be informed of all tags used in the semantic layer.  ... 
doi:10.1145/133160.133185 dblp:conf/sigir/Burkowski92 fatcat:ozyov3fp45b5tofwbwqvu5yvsa

Automated Annotation of Landmark Images Using Community Contributed Datasets and Web Resources [chapter]

Gareth J. F. Jones, Daragh Byrne, Mark Hughes, Noel E. O'Connor, Andrew Salway
2011 Lecture Notes in Computer Science  
In the first stage, an input image is matched to a set of community contributed images (with keyword tags) on the basis of its GPS information and image classification techniques.  ...  The system then takes advantage of the information written about landmarks available on the web at large to extract a fact about the landmark in the image.  ...  Acknowledgement The research reported in this paper is part of the project TRIPOD supported by the European commission under contract No. 045335.  ... 
doi:10.1007/978-3-642-23017-2_8 fatcat:6ofsa5dtbfarlj5snlm4pg2lke


Karthikram .
2014 International Journal of Research in Engineering and Technology  
This leads to poor performance in Tag Based Image Retrieval (TBIR). Automatic Image Annotation (AIA) analyzes the missing and noisy tags and over-refines it to increase the performance of TBIR.  ...  In recent days, several social networking sites are more popular with digitized images. It comprises the major portion of the databases which makes the search engines to face difficulty in searching.  ...  This technique uses the local and global features for estimating the presence of the training dataset in the given image.  ... 
doi:10.15623/ijret.2014.0303027 fatcat:wt7x3ycawzafjcycqlywdtwgfu

An Image Retrieving Scheme Using Salient Features and Annotation Watermarking

2014 KSII Transactions on Internet and Information Systems  
In this paper, we propose an annotation watermarking system for users to embed text descriptions, and retrieve more relevant textual information from similar images.  ...  Specifically, we use global features such as color ratios and dominant sub-image colors for preliminary filtering.  ...  With the filtering of color ratios and dominant sub-image colors, the system can retrieve a high percentage (more than 96%) of the relevant images and their annotations for relevant information retrieval  ... 
doi:10.3837/tiis.2014.01.013 fatcat:q5mveu44gnft5pvsozptmd6l3y

HEALTH GeoJunction: place-time-concept browsing of health publications

Alan M MacEachren, Michael S Stryker, Ian J Turton, Scott Pezanowski
2010 International Journal of Health Geographics  
due to the database size.  ...  Conclusions: PubMed is a database of over 19 million biomedical abstracts and citations maintained by the National Center for Biotechnology Information; achieving quick filtering is an important contribution  ...  The views and conclusions contained in this document are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of the U.S.  ... 
doi:10.1186/1476-072x-9-23 pmid:20482806 pmcid:PMC2889882 fatcat:q4iujpdtb5fufkchb2hjjhgfsa

Building recognition in urban environments: A survey of state-of-the-art and future challenges

Jing Li, Wei Huang, Ling Shao, Nigel Allinson
2014 Information Sciences  
To this end, we present a comprehensive review of the dominant building recognition systems by first grouping them into two categories: (i) effectiveness approaches that mainly focus on the improvement  ...  To this end, this paper surveys the state-of-the-art building recognition techniques on city building images from different aspects, covering a variety of knowledge in the computer vision research field  ...  I 1 of each geo-cluster, where I 1 contains photos of one or several adjacent landmarks; (3) extract text tags of each photo in a visual cluster by filtering out stop words and phrases; and (4) compute  ... 
doi:10.1016/j.ins.2014.02.112 fatcat:ip3us37bi5b3lkntde6ovyoqbq

Multimodal ranking for image search on community databases

Fabian Richter, Stefan Romberg, Eva Hörster, Rainer Lienhart
2010 Proceedings of the international conference on Multimedia information retrieval - MIR '10  
The image ranking approach presented in this work represents an image collection as a graph that is built using a multimodal similarity measure based on visual features and user tags.  ...  We perform a random walk on this graph to find the most common images.  ...  Typically one would pre-filter the images in the database to keep only those likely showing the query content.  ... 
doi:10.1145/1743384.1743402 dblp:conf/mir/RichterRHL10 fatcat:ylplqntbq5go7nm25wrcfvi35i

Interactive Tag Maps and Tag Clouds for the Multiscale Exploration of Large Spatio-temporal Datasets

Aidan Slingsby, Jason Dykes, Jo Wood, Keith Clarke
2007 Information Visualisation  
In combination, these aspatial and spatial views are used to explore a large structured spatio-temporal data set by providing overviews and filtering by text and geography.  ...  The interactive tag map and tag cloud techniques and the rapid prototyping method used are informally evaluated through successes and limitations encountered.  ...  Four anonymous reviewers provided informative suggestions that have resulted in significant enhancements to the submitted draft of this paper.  ... 
doi:10.1109/iv.2007.71 dblp:conf/iv/SlingsbyDWC07 fatcat:6f3dfnsqxbcejbtvxcv22bk6zu

Practical elimination of near-duplicates from web video search

Xiao Wu, Alexander G. Hauptmann, Chong-Wah Ngo
2007 Proceedings of the 15th international conference on Multimedia - MULTIMEDIA '07  
The results of 24 queries in a data set of 12,790 videos retrieved from Google, Yahoo!  ...  This paper outlines ways to cluster and filter out the nearduplicate video using a hierarchical approach. Initial triage is performed using fast signatures derived from color histograms.  ...  The tool of near-duplicate detection can be used in several ways: As a filter to remove redundant videos in the listing of retrieval results, as a tool for finding similar videos in different variations  ... 
doi:10.1145/1291233.1291280 dblp:conf/mm/WuHN07a fatcat:vr6iqrapfvdwdjtqhwk3mrxx3a

Semi-automated document image clustering and retrieval

Markus Diem, Florian Kleber, Stefan Fiel, Robert Sablatnig, Bertrand Coüasnon, Eric K. Ringger
2013 Document Recognition and Retrieval XXI  
The methods presented allow for the analysis of heterogeneous documents that contain printed and handwritten text and allow for a hierarchically clustering with different feature subsets in different layers  ...  Ideally the initial bundling of shuffled document images can be reproduced to explore large document databases.  ...  ACKNOWLEDGMENTS The authors would like to thank the Fraunhofer-Institute for Production Systems and Design Technology (IPK), Berlin for supporting the work.  ... 
doi:10.1117/12.2043010 dblp:conf/drr/DiemKFS14 fatcat:hvqkwxiuzjgnllxe3vvvo5i3nu

BioTextQuest + : a knowledge integration platform for literature mining and concept discovery

Nikolas Papanikolaou, Georgios A. Pavlopoulos, Evangelos Pafilis, Theodosios Theodosiou, Reinhard Schneider, Venkata P. Satagopam, Christos A. Ouzounis, Aristides G. Eliopoulos, Vasilis J. Promponas, Ioannis Iliopoulos
2014 Computer applications in the biosciences : CABIOS  
growth of scientific corpora and the plethora of tools designed to mine PubMed V R and related biological databases.  ...  The iterative process of finding relevant information in biomedical literature and performing bioinformatics analyses might result in an endless loop for an inexperienced user, considering the exponential  ...  ACKNOWLEDGEMENTS The authors wish to thank the four anonymous reviewers for invaluable comments. I.I. and V.P.S. would like to thank I. Manolakis for fruitful discussions.  ... 
doi:10.1093/bioinformatics/btu524 pmid:25100685 fatcat:gyf7y7qvxfbb5maq4ofsrrh25a

Learning supervised embeddings for large scale sequence comparisons

Dhananjay Kimothi, Pravesh Biyani, James M. Hogan, Akshay Soni, Wayne Kelly, Vasilis J Promponas
2020 PLoS ONE  
Such filtering of the original database allows slower but more accurate methods to be executed quickly over a far smaller dataset.  ...  Further, the new methods are an order of magnitude faster than BLAST for the database retrieval task, supporting hybrid approaches that rapidly filter the collection so that only potentially relevant records  ...  To apply these approaches to the retrieval task, we consider the protein family tag (retrieved from the PFAM database [18] ) as the class-label for a given sequence.  ... 
doi:10.1371/journal.pone.0216636 pmid:32168338 fatcat:cwrxyfxdmngctln2rdq6kskfgi

Word Sense Discovery for Web Information Retrieval

Tomasz Nykiel, Henryk Rybinski
2008 2008 IEEE International Conference on Data Mining Workshops  
The method attempts to discover not only word senses that are dominating, but also senses that are dominated and underrepresented in the repository.  ...  Word meaning disambiguation has always been an important problem in many computer science tasks, such as information retrieval and extraction.  ...  Information retrieval is the research area devoted to searching for information in documents, searching for text documents themselves, or searching for metadata.  ... 
doi:10.1109/icdmw.2008.10 dblp:conf/icdm/NykielR08 fatcat:6qu3wyybbrhm3ov7faymmvbtoq

Multimodal Image Retrieval

Stefan Romberg, Rainer Lienhart, Eva Hörster
2012 International Journal of Multimedia Information Retrieval  
The proposed approach is evaluated in a query-by-example retrieval task where various variants of our mm-pLSA system are compared to systems relying on a single modality and other ad-hoc combinations of  ...  In this work, we extend the standard single-layer probabilistic Latent Semantic Analysis (pLSA) (Hofmann in Mach Learn 42(1-2):177-196, 2001) to multiple layers.  ...  Moreover, the image database we use for learning and retrieval is a real-world, large-scale, 10 million images' database in contrast to the small and almost noise-free COREL data-base that was used in  ... 
doi:10.1007/s13735-012-0006-4 fatcat:usa7xvlgrzfdxoenf3ovs6hqle

Hierarchical Fuzzy Feature Similarity Combination for Presentation Slide Retrieval

A. Kushki, M. Ajmal, K. N. Plataniotis
2009 EURASIP Journal on Advances in Signal Processing  
In response to a textual user query, each extracted feature is used to compute a fuzzy relevance score for each slide in the database.  ...  The improvements are attributed to both the incorporation of the contextual features and the hierarchical feature combination scheme.  ...  ACKNOWLEDGMENT This work has been partially supported by the National Research Council of Canada under the Network for Effective Collaboration Technologies through Advanced Research (NECTAR) project.  ... 
doi:10.1155/2008/547923 fatcat:isvtxjpwofhmbgcc5qggcoawru
« Previous Showing results 1 — 15 out of 4,941 results