7,397 Hits in 5.3 sec

Multimedia news exploration and retrieval by integrating keywords, relations and visual features

Hangzai Luo, Jianping Fan, Youjie Zhou
2010 Multimedia tools and applications  
Multimedia news may be organized by the keywords and categories for exploration and retrieval applications, but it is very difficult to integrate the relation and visual information into the traditional  ...  Based on this semantic representation framework, the news exploration and retrieval applications can be organized by not only keywords and categories but also relations and visual properties.  ...  As our model preserve keyword, relation, visual properties and user's interestingness in a uniform framework, our model can provide more usefulness than traditional models for multimedia news exploration  ... 
doi:10.1007/s11042-010-0639-3 fatcat:b2voajc3lnhh7drw2lnp4ykyry

Tenth international workshop on multimedia data mining

Valery A. Petrushin, Jia-Yu (Tim) Pan, Cees G.M. Snoek
2011 SIGKDD Explorations  
In this report we provide a summary of the tenth Multimedia Data Mining Workshop that was held in conjunction with the 16th ACM  ...  on the visual keywords representation and Histogram Intersection Kernel.  ...  INTRODUCTION As evidenced by the success of the previous editions of the Workshop, there is an increasing interest in new techniques and tools that can detect and discover patterns in multimedia data,  ... 
doi:10.1145/1964897.1964909 fatcat:pmhjo25aorhslicey2ljgsyo3q

A Foundational Perspective for Visual Information Retrieval

Qi Tian
2006 IEEE Multimedia  
Learning semantic relations Chapter 8 concentrates on unifying keywords and low-level contents in image retrieval.  ...  These techniques are presented gradually, from lowlevel visual feature representation to mid-level learning in relevance feedback, and to semantic retrieval in a hybrid (keyword and visual content) feature  ... 
doi:10.1109/mmul.2006.24 fatcat:t2tcojekuffvhomroyhawccexu

Narrowing the semantic gap - improved text-based web document retrieval using visual features

Rong Zhao, W.I. Grosky
2002 IEEE transactions on multimedia  
Experimental results show that LSI, together with both textual and visual features, is able to extract the underlying semantic structure of web documents, thus helping to improve the retrieval performance  ...  In this paper, we examine the use of this technique for content-based web document retrieval, using both keywords and image features to represent the documents.  ...  Second, we validated that integrating textual features with visual features, together with LSI, can represent the contents of multimedia web document better than using keywords only.  ... 
doi:10.1109/tmm.2002.1017733 fatcat:52qgrls22fho7ogfoct3vt7zye

Facilitating Multimedia Database Exploration through Visual Interfaces and Perpetual Query Reformulations

Wen-Syan Li, K. Selçuk Candan, Kyoji Hirata, Yoshinori Hara
1997 Very Large Data Bases Conference  
The contribution of this work is the integration of database methodology, user interface design, IR concepts, and image matching techniques for facilitating multimedia database exploration.  ...  Since multimedia retrieval is based on similarity calculations of semantics and media-based search, exact matches are not expected.  ...  Acknowledgments We would like to express our sincere appreciation to Peter Scheuermann and Chris Clifton for their invaluable comments and suggestions on this work.  ... 
dblp:conf/vldb/LiCHH97 fatcat:syy5rv5uyrco5krmw36loirjqm

Human-computer interaction for large-scale image retrieval

Yuli Gao, Chunlei Yang, Yi Shen, Jianping Fan
2009 2009 IEEE International Conference on Multimedia and Expo  
In this paper, we have developed a human-centered computing framework for assisting users to access large-scale online image collections: (a) filtering out junk images from Google Images; and (b) exploring  ...  Thus supporting more effective retrieval from large-scale image collections has become a challenging issue for CBIR community.  ...  (b) Context-Driven Image Visualization and Exploration: Kernel PCA and hyperbolic visualization are seamlessly integrated to enable interactive image exploration according to their inherent visual similarity  ... 
doi:10.1109/icme.2009.5202780 dblp:conf/icmcs/GaoYSF09 fatcat:6yb2hzfwsba3zal4uud6dzuxla

Modal Keywords, Ontologies, and Reasoning for Video Understanding [chapter]

Alejandro Jaimes, Belle L. Tseng, John R. Smith
2003 Lecture Notes in Computer Science  
We discuss semi-automatic construction of multimedia ontologies and present experiments in which visual detector outputs are modified by simple rules that use context information available with the video  ...  A method is presented to automatically classify keywords from speech recognition, queries, or related text into these categories using WordNet and TGM I.  ...  Related Work Our concept of modal keywords is new, but some related research includes the following.  ... 
doi:10.1007/3-540-45113-7_25 fatcat:yup2ep6gfbahfadczhhsftcrsm

Capturing Text Semantics for Concept Detection in News Video [chapter]

Gang Wang, Tat-Seng Chua
2008 Signals and Communication Technology  
We perform a multi-resolution analysis at the shot, multimedia discourse and story levels to capture the semantics in news video.  ...  One is text classification and the other is text retrieval. Both methods have their own strengths and weaknesses. In addition, fusion of text and visual analysis is still an open problem.  ...  We will further improve the performance on building linkage between visual features and ASR transcript.  ... 
doi:10.1007/978-0-387-76569-3_5 fatcat:t7xz7pxx5jb4vpcljvdow6vqt4

Mining User Navigation Patterns For Efficient Relevance Feedback For Cbir

2018 Zenodo  
In today's modernized world, content based image retrieval (CBIR) is considered as a bastion in image retrieval system.  ...  For making CBIR most suitable and productive technique, relevance feedback technique is used in conjunction with CBIR for producing more specific results which are obtained by taking feedback from user  ...  Typically, in the development of an image requisition system, semantic image retrieval relies heavily on the related captions, e.g., categories, file-names, and other manual descriptions, annotated keywords  ... 
doi:10.5281/zenodo.1464589 fatcat:ymxavnvoynayfev6vouqzxstni

Multimedia in Cultural Heritage Manuscripts: Integrating Description, Transcription, and Image Content

Catalin Calistru, Cristina Ribeiro, Gabriel David
2009 EURASIP Journal on Image and Video Processing  
To offer a faceted access to the collection it is necessary to explore these diverse materials, integrate them according to a model that accounts for both metadata and the content and provide a comprehensive  ...  retrieval environment.  ...  Search on the contextual metadata is handled by the built-in indexes of the relational database management system. Query by visual features is integrated with the keyword search.  ... 
doi:10.1155/2009/876487 fatcat:5rrenmxkzzbj5kow3hxgogdl5u

End-to-End Adaptive Framework for Multimedia Information Retrieval [chapter]

Maria Sokhn, Elena Mugellini, Omar Abou Khaled, Ahmed Serhrouchni
2011 Lecture Notes in Computer Science  
This framework aims at enhancing the management, retrieval and visualization of multimedia information resources based on semantic techniques.  ...  In this context, effective retrieval and usage of multimedia resources have to deal with the issues of creating efficient content based indexes, developing retrieval tools and improving user-oriented visualization  ...  These features become essential in multimedia retrieval which has a complex content hardly searched by "traditional" keyword-based searching.  ... 
doi:10.1007/978-3-642-21560-5_17 fatcat:yitknthx55gapmi63citwo2z7i

Content-based multimedia indexing and retrieval

C. Djeraba
2002 IEEE Multimedia  
Acknowledgment Many thanks to Bernard Merialdo (Eurecom, France) and Philippe Joly (IRIT, France) for valuable discussions.  ...  In "Unifying Keywords and Visual Contents in Image Retrieval," Zhou and Huang explore an image retrieval system that considers both high-level features (keywords) and low-level features (colors, textures  ...  Internet search engines such as Alta Vista, Google, and Lycos have become popular, because just by typing a few keywords, users have instant access to a vast amount of documents related to their topic  ... 
doi:10.1109/mmul.2002.998047 fatcat:nyiwgh3qfbfmtokezrji4jdq7i

Multimedia Search Without Visual Analysis: The Value of Linguistic and Contextual Information

Franciska M. G. de Jong, Thijs Westerveld, Arjen P. de Vries
2007 IEEE transactions on circuits and systems for video technology (Print)  
He has worked on a variety of research topics, including (multimedia) information retrieval, database architecture, query processing, retrieval system evaluation, and ambient intelligence.  ...  Index Terms-Context, language processing, multimedia search, semantic metadata, speech and audio analysis, surface features. 1051-8215/$25.00 © 2007 IEEE Arjen P. de Vries received the Ph.D. degree in  ...  The promising results on TRECVID data illustrate the advancements made for query-by-concept in comparison to the more "traditional" query-by-example or query-by-keyword methods, and how the integration  ... 
doi:10.1109/tcsvt.2007.890834 fatcat:fiybaunbjzdvddksqewudk7n7m

Content-based Search for Image Retrieval

Mohamed M. Fouad
2013 International Journal of Image Graphics and Signal Processing  
One can first place a keyword-based query, and then the desired images are retrieved by visual content-based query.  ...  The proposed approach uses two or more types of query for accessing images, textual annotation associated with images and visual appearance, such as colour, texture and positional features of objects in  ...  The image search servers periodically search for WWW new images, retrieve and extract visual features of new images, and then index these visual features with the URLs of the new images.  ... 
doi:10.5815/ijigsp.2013.11.05 fatcat:h67bxjvyh5a5fpvxkyu3obpjxm


Dr. Vijayakumar T., Vinothkanna R.
2020 Journal of Innovative Image Processing  
The image retrieval system is finalized by integrating a group sparse logistic regression model.  ...  The Itti visual saliency model is described here for generation of an overall saliency map with the integration of color saliency, intensity and direction maps.  ...  The traditional text description of images and keyword based matching techniques are replaced by the automatic extraction of visual features and characteristics of the images based on the similarity between  ... 
doi:10.36548/jiip.2020.2.005 fatcat:bxc4l5gnrbdg5geshnjre6gcia
« Previous Showing results 1 — 15 out of 7,397 results