8,850 Hits in 5.9 sec

Boosting cross-media retrieval via visual-auditory feature analysis and relevance feedback

Hong Zhang, Junsong Yuan, Xingyu Gao, Zhenyu Chen
2014 Proceedings of the ACM International Conference on Multimedia - MM '14  
In this paper, we propose a new cross-media retrieval method based on short-term and long-term relevance feedback. Our method mainly focuses on two typical types of media data, i.e. image and audio.  ...  There are abundant correlations among heterogeneous low-level media content, which makes it challenging to query cross-media data effectively.  ...  Therefore, in this section, we propose both short-term and long-term strategies to further explore prior knowledge over the course of many query sessions so as to improve cross-media retrieval performance  ... 
doi:10.1145/2647868.2654975 dblp:conf/mm/ZhangYGC14 fatcat:adpf47i5lbgdxkpespkzgbzhnq

Merging Results from Different Media: Lic2m Experiments at ImageCLEF 2005

Romaric Besançon, Christophe Millet
2005 Conference and Labs of the Evaluation Forum  
For both ad hoc and medical task, we perform experiments on merging the results of two independent search systems: a crosslanguage information retrieval system exploiting the text part of the query and  ...  a content-based image retrieval system exploiting the example images given with the query.  ...  The LIC2M participated in ImageCLEF 2005 to perform experiments on merging strategies to integrate the results obtained from the cross-language text retrieval system and the content-based image retrieval  ... 
dblp:conf/clef/BesanconM05a fatcat:unscu4r63fgwfe5g4jzmegwanm

XRCE's Participation to ImageCLEFphoto 2007

Stéphane Clinchant, Jean-Michel Renders, Gabriela Csurka
2007 Conference and Labs of the Evaluation Forum  
This year, with a "lightly" annotated corpus of images, it appears that mono-media retrieval performance is more or less equivalent for pure image and pure text content (around 20% MAP).  ...  One issue that arises when adopting such a strategy is to determine how to compute the mono-media similarity between an aggregate of objects coming from a first (pseudo-)feedback step and one single multimodal  ...  The authors also want to thank Florent Perronin for his greatly appreciated help in applying some of the Generic Visual Categorizer (GVC) components in ImageCLEF07 experiments.  ... 
dblp:conf/clef/ClinchantRC07a fatcat:r3lgegw3jvazngmcragtpb3nwq

Search for Multi-modality Data in Digital Libraries [chapter]

Jun Yang, Yueting Zhuang, Qing Li
2001 Lecture Notes in Computer Science  
As its specific approaches, a learningfrom-elements strategy is devised for propagation of semantic descriptions, and a cross media search mechanism with relevance feedback is proposed for evaluation and  ...  Unlike most previously proposed retrieval approaches that focus on a specific media type, this paper presents 2M2Net as a seamless integration framework for retrieval of multi-modality data in digital  ...  User feedback is accepted and handled by the Feedback & Learning Subsystem. It conducts a parallel session of relevance feedback on each media type to improve the retrieval results immediately.  ... 
doi:10.1007/3-540-45453-5_62 fatcat:4oz3qzdxpzdc5o2uchpsszuda4

Using Text and Image Retrieval Systems. Lic2m experiments at ImageCLEF 2006

Romaric Besançon, Christophe Millet
2006 Conference and Labs of the Evaluation Forum  
We perform experiments on merging the results of two independent search systems: a cross-language information retrieval system exploiting the text part of the query and a content-based image retrieval  ...  A first analysis give some hints on possible improvements: example images are often chosen to be visually different to show several aspects of possible relevant images for the chosen topic, therefore the  ...  Search and Merging Strategy Both systems are used independently to retrieve documents from textual and visual information.  ... 
dblp:conf/clef/BesanconM06 fatcat:qqlxxuqcwjaujdiuph7rozhosq

Leveraging Image, Text and Cross–media Similarities for Diversity–focused Multimedia Retrieval [chapter]

Julien Ah-Pine, Stephane Clinchant, Gabriela Csurka, Florent Perronnin, Jean-Michel Renders
2010 ImageCLEF  
Acknowledgements This work was partially supported by the European Projects PinView FP7-216529 and Sync3 FP7-231854, and the French projects Omnia ANR-06-CIS6-01 and Fragrances ANR-08-CORD-008.  ...  new information from the image to improve the text based retrieval.  ...  We can see that the cross-media image-text is really beneficial in our strategy allowing to better bridge the gap between image and text.  ... 
doi:10.1007/978-3-642-15181-1_17 fatcat:je7zmhdtlvd6vcbbefuipmcz2q

MIRACLE's Combination of Visual and Textual Queries for Medical Image Retrieval

Julio Villena-Román, José Carlos González Cristóbal, José Miguel Goñi-Menoyo, Juan José Fernández
2005 Conference and Labs of the Evaluation Forum  
of information retrieval, no matter if it is text or content based.  ...  This task certainly requires the use of image retrieval techniques and therefore it is mainly aimed at image analysis research groups.  ...  Acknowledgements This work has been partially supported by the Spanish R+D National Plan, by means of the project RIMMEL (Multilingual and Multimedia Information Retrieval, and its Evaluation), TIN2004  ... 
dblp:conf/clef/Villena-RomanCGF05 fatcat:xffbljj2bfelbbvgtoil776d3q

Late fusion of heterogeneous methods for multimedia image retrieval

Hugo Jair Escalante, Carlos A. Hérnadez, Luis Enrique Sucar, Manuel Montes
2008 Proceeding of the 1st ACM international conference on Multimedia information retrieval - MIR '08  
Late fusion of independent retrieval methods is the simpler approach and a widely used one for combining visual and textual information for the search process.  ...  An interesting result is that even methods that perform poor (individually) resulted very useful to the fusion strategy.  ...  The IRMs we consider include retrieval methods based on text, image-content, visualconcept detection, region-level image annotation, Web-based query expansion and inter-media relevance feedback.  ... 
doi:10.1145/1460096.1460125 dblp:conf/mir/EscalanteHSM08 fatcat:4pkhxdvmsjbjljyyhfq7sk4tae

Unsupervised Visual and Textual Information Fusion in Multimedia Retrieval - A Graph-based Point of View [article]

Gabriela Csurka and Julien Ah-Pine and Stéphane Clinchant
2014 arXiv   pre-print
We are interested in repositories of image/text multimedia objects and we study multimodal information fusion techniques in the context of content based multimedia information retrieval.  ...  We compare cross-media and random walk based results using three different real-world datasets.  ...  In a second time, we use the visual information of the (text based) retrieved objects in order to improve the search results.  ... 
arXiv:1401.6891v1 fatcat:dbo4xnptebejdktgyc5h6qbiee

Overview of the ImageCLEF 2006 Photographic Retrieval and Object Annotation Tasks [chapter]

Paul Clough, Michael Grubinger, Thomas Deselaers, Allan Hanbury, Henning Müller
2007 Lecture Notes in Computer Science  
However, 31% of runs involved a visual retrieval technique, typically combined with text through the merging of image and text retrieval results.  ...  Similar to previous years, the use of relevance feedback to enable query expansion was seen to improve the text-based submissions by an average of 39%.  ...  Special thanks to viventura, the IAPR and LTUtech for providing their image databases for this years' tasks, and to Tobias Weyand for creating the web interface for submissions.  ... 
doi:10.1007/978-3-540-74999-8_71 fatcat:nwavr7byzbbflp3b7wvxd4lem4

Unsupervised Visual and Textual Information Fusion in CBMIR Using Graph-Based Methods

Julien Ah-Pine, Gabriela Csurka, Stéphane Clinchant
2015 ACM Transactions on Information Systems  
We are interested in repositories of image/text multimedia objects and we study multimodal information fusion techniques in the context of content based multimedia information retrieval.  ...  We compare cross-media and random walk based results using three different real-world datasets.  ...  They draw inspiration from cross-media relevance models ] and intermedia feedback methods [Maillot et al. 2006 ] by generalizing the pseudo-feedback idea present in the cross-media relevance model.  ... 
doi:10.1145/2699668 fatcat:p3bqd767sjcbbdn2hn3fpxmp2i

XRCE's Participation in Wikipedia Retrieval, Medical Image Modality Classification and Ad-hoc Retrieval Tasks of ImageCLEF 2010

Stéphane Clinchant, Gabriela Csurka, Julien Ah-Pine, Guillaume Jacquet, Florent Perronnin, Jorge Sánchez, Keyvan Minoukadeh
2010 Conference and Labs of the Evaluation Forum  
: text, image or mixed.  ...  For representing images, we used Fisher Vectors improved by power and L2 normalizations and a spatial pyramid representation.  ...  We would like also to acknowledge Craig Saunders for his proofreading and useful comments on the paper.  ... 
dblp:conf/clef/ClinchantCAJPSM10 fatcat:7ak2xjpgkfdkfgvy5pxwk4hlvm

Comparative Evaluation of Cross-language Information Retrieval Systems [chapter]

Carol Peters
2005 Lecture Notes in Computer Science  
With the increasing importance of the "Global Information Society" and as the world's depositories of online collections proliferate, there is a growing need for systems that enable access to information  ...  In recognition of this, five years ago, the DELOS Network for Digital Libraries launched the Cross-Language Evaluation Forum (CLEF), with the objective of promoting multilingual information access by providing  ...  It was also shown that, like cross-language retrieval on text collections, query expansion and relevance feedback improved performance.  ... 
doi:10.1007/978-3-540-31842-2_16 fatcat:4ad3pwr6pnhr5n6v3gwzsqd4cu

Multimodal indexing based on semantic cohesion for image retrieval

Hugo Jair Escalante, Manuel Montes, Enrique Sucar
2011 Information retrieval (Boston)  
This paper introduces two novel strategies for representing multimodal images with application to multimedia image retrieval.  ...  Accordingly, the main assumption of this work is that by combining information from text and labels we can develop very effective retrieval methods.  ...  Acknowledgments The authors are grateful with the reviewers for their comments that have helped to improve the content of the article.  ... 
doi:10.1007/s10791-011-9170-z fatcat:hetabkkhefh6rnzy7g3u2mykp4

Applying semantic web technologies to knowledge sharing in aerospace engineering

A.-S. Dadzie, R. Bhagdev, A. Chakravarthy, S. Chapman, J. Iria, V. Lanfranchi, J. Magalhães, D. Petrelli, F. Ciravegna
2008 Journal of Intelligent Manufacturing  
This paper details an integrated methodology to optimise Knowledge reuse and sharing, illustrated with a use case in the aeronautics domain.  ...  This approach has been applied and evaluated successfully within the aerospace domain, and is currently being extended for use in other domains on an increasingly large scale.  ...  information storage and retrieval across text, images and cross-media documents. 2.  ... 
doi:10.1007/s10845-008-0141-1 fatcat:v2qeknjo5fgulnevw33tgcjhdm
« Previous Showing results 1 — 15 out of 8,850 results