2,916 Hits in 6.1 sec

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.  ...  This book chapter is structured in four sections: visual methods, textual methods, cross-media technique and diversity-focused retrieval.  ...  Diversity focused Multimedia Retrieval In the 2008 and 2009 sessions an additional sub-task to multimedia retrieval was asked to be adressed by the participants.  ... 
doi:10.1007/978-3-642-15181-1_17 fatcat:je7zmhdtlvd6vcbbefuipmcz2q

Evaluation of Diversity-Focused Strategies for Multimedia Retrieval [chapter]

Julien Ah-Pine, Gabriela Csurka, Jean-Michel Renders
2009 Lecture Notes in Computer Science  
In this paper, we propose and evaluate different strategies to promote diversity in the top results of multimedia retrieval systems.  ...  Results show that most of these strategies succeed in increasing a diversity performance measure, while keeping or slightly degrading precision of the top list and, more interestingly, they achieve this  ...  Another cause of failure stems from the cross-media pseudo-relevance feedback mechanism that is the basis for our cross-media similarity measure.  ... 
doi:10.1007/978-3-642-04447-2_85 fatcat:moastqtxnbdxxobs3ra7cj62bq

High diversity transforms multimedia information retrieval into a cross-cutting field

James Z. Wang, Nozha Boujemaa, Yixin Chen
2007 SIGMOD record  
Researchers in multimedia, databases, computer vision, machine learning, signal and image processing and statistics have worked on multimedia information retrieval (MIR) for over a decade.  ...  ., TRECVID for video retrieval) in the field of multimedia information retrieval. Does benchmarking kill innovation? Do existing benchmark initiatives cover diverse multimedia retrieval tasks?  ... 
doi:10.1145/1276301.1276315 fatcat:cdowdmpllbcf3mea7m2wotbuyq

Crossing textual and visual content in different application scenarios

Julien Ah-Pine, Marco Bressan, Stephane Clinchant, Gabriela Csurka, Yves Hoppenot, Jean-Michel Renders
2008 Multimedia tools and applications  
We also introduce the monomodal similarity measures for text and images that serve as basic components for both proposed trans-media similarities.  ...  We show how one can frame a large variety of problem in order to address them with the proposed techniques: image annotation or captioning, text illustration and multimedia retrieval and clustering.  ...  Acknowledgements The authors want to thank particularly INA for their contributions in our work and Florent Perronin for his greatly appreciated help in applying some of the Generic Visual Categorizer  ... 
doi:10.1007/s11042-008-0246-8 fatcat:w3ilxvdl65bgpl453z7izlnzbq

Cross-Lingual Cross-Media Content Linking: Annotations and Joint Representations (Dagstuhl Seminar 15201)

Alexander G. Hauptmann, James Hodson, Juanzi Li, Nicu Sebe, Achim Rettinger, Marc Herbstritt
2015 Dagstuhl Reports  
Dagstuhl Seminar 15201 was conducted on "Cross-Lingual Cross-Media Content Linking: Annotations and Joint Representations".  ...  Except where otherwise noted, content of this report is licensed under a Creative Commons BY 3.0 Unported license Cross-Lingual Cross-Media  ...  In this aspect, leveraging data generated from videos, images and text to support various applications by finding cross-modal semantic similarity.  ... 
doi:10.4230/dagrep.5.5.43 dblp:journals/dagstuhl-reports/HauptmannHLSR15 fatcat:sjqptft2m5cufcpzslggt7la5i

From text question-answering to multimedia QA on web-scale media resources

Tat-Seng Chua, Richang Hong, Guangda Li, Jinhui Tang
2009 Proceedings of the First ACM workshop on Large-scale multimedia retrieval and mining - LS-MMRM '09  
The system will be designed to find multimedia answers from Web-scale media resources such as Flicker and YouTube.  ...  With the proliferation of text and multimedia information, users are now able to find answers to almost any questions on the Web.  ...  This paper describes the architecture and our recent research on various types of multimedia QA for a range of applications. It focuses only on visual media such as image and video.  ... 
doi:10.1145/1631058.1631069 dblp:conf/mm/ChuaHLT09 fatcat:yqb5axen7vetlbreeaiy74reue

Knowledge discovery over community-sharing media: From signal to intelligence

Winston Hsu, Tao Mei, Rong Yan
2009 2009 IEEE International Conference on Multimedia and Expo  
and pose new challenges for the design of efficient search, mining, and visualization methods for manipulation.  ...  We review the research advances for enabling such applications and present a brief outlook on open issues and major opportunities.  ...  In response to user controls, the system retrieves the most similar images from several million images, displays them in correct geometric and photometric alignment with respect to the current photo.  ... 
doi:10.1109/icme.2009.5202775 dblp:conf/icmcs/HsuMY09 fatcat:nzblrwkfjfdcvfhlc65pvkotbi

Context Aware Location Identification in Social Media Environment

2015 International Journal of Science and Research (IJSR)  
The explosive growth of photos/videos and the advent of media sharing services have drastically increased the volume of user contributed multimedia resources, which bring profound social impacts to the  ...  society and pose new challenges for the design of efficient search, mining, and visualization methods for manipulation.  ...  In response to user controls, the system retrieves the most similar images from several million images, displays them in correct geometric and photometric alignment with respect to the current photo.  ... 
doi:10.21275/v4i11.nov151065 fatcat:74uzbph3jvb7za4u6fqx4ckrqi

Event analysis in social multimedia: a survey

Xueliang Liu, Meng Wang, Benoit Huet
2015 Frontiers of Computer Science  
multimedia requires more scalable, effective and robust technologies to manage and index them.  ...  The age of huge amount of media collection provides users facilities to share and access data, while it also demands the revolution of data management techniques, since the exponential growth of social  ...  Then, for each event, both relevant tweets on Twitter and compelling images from Google image search are retrieved.  ... 
doi:10.1007/s11704-015-4583-2 fatcat:zzorgzefyfdiremape4xi2u5bi

Content-Based Multimedia Recommendation Systems: Definition and Application Domains

Yashar Deldjoo, Markus Schedl, Paolo Cremonesi, Gabriella Pasi
2018 Italian Information Retrieval Workshop  
of multimedia content for solving a variety of tasks related to recommendation.  ...  The goal of this work is to formally provide a general definition of a multimedia recommendation system (MMRS), in particular a content-based MMRS (CB-MMRS), and to shed light on different applications  ...  In [24] the authors propose a knowledge-driven cross-media semantic matching framework that leverages two large high-quality knowledge sources ImageNet (for image) and Wikipedia (for text).  ... 
dblp:conf/iir/DeldjooSCP18 fatcat:guhkkc7zqvahxfu6oabatyl6xe

Multimodal Multimedia Retrieval with vitrivr

Ralph Gasser, Luca Rossetto, Heiko Schuldt
2019 Proceedings of the 2019 on International Conference on Multimedia Retrieval - ICMR '19  
Hence, they are limited when it comes to crossing these silos for accessing objects. In this paper, we present vitrivr, a general-purpose content-based multimedia retrieval stack.  ...  Nevertheless, existing multimedia management and retrieval systems are mostly organized in silos and treat different media types separately.  ...  RELATED WORK Information retrieval in multimedia collections is an important topic in computer science with research focusing on many different domains, such as image and video retrieval [4, 16] , music  ... 
doi:10.1145/3323873.3326921 dblp:conf/mir/GasserRS19 fatcat:cr7iqzlznneptha3ik4whfomkq

Deep Learning Techniques for Future Intelligent Cross-Media Retrieval [article]

Sadaqat ur Rehman, Muhammad Waqas, Shanshan Tu, Anis Koubaa, Obaid ur Rehman, Jawad Ahmad, Muhammad Hanif, Zhu Han
2020 arXiv   pre-print
Then, we present some well-known cross-media datasets used for retrieval, considering the importance of these datasets in the context in of deep learning based cross-media retrieval approaches.  ...  and the potential solutions of deep learning assisted cross-media retrieval.  ...  Text Image and Audio Image and Text Supervised Semantic Hashing (DVSH) model for cross-media retrieval.  ... 
arXiv:2008.01191v1 fatcat:t63bg55w2vdqjcprzaaidrmprq

Large-scale cross-media analysis and mining from socially curated contents

Akisato KIMURA
2014 Progress in Informatics  
Following this trend, this paper presents recent developments and growth of social curation services, and reviews several research trials for cross-media analysis and mining from socially curated contents  ...  This paper focuses on another emerging trend called social curation, a human-in-the-loop alternative to automatic algorithms for social media analysis.  ...  Acknowledgment I would like to thank all the research collaborators and supporters of our successive researches, most notably, Prof.  ... 
doi:10.2201/niipi.2014.11.4 fatcat:gmelnpaf5bgmnegai7fox3g2b4

Web-Scale Multimedia Information Networks

Guo-Jun Qi, Min-Hsuan Tsai, Shen-Fu Tsai, Liangliang Cao, Thomas S. Huang
2012 Proceedings of the IEEE  
In this paper, we introduce a unified STRUCTURED representation called multimedia information networks (MINets), which incorporates ontology and cross-media links, covering both content and context knowledge  ...  Ontology and cross-media structures are constructed and expanded by automatically constructing MINets from web-scale data by state-of-the-art information extraction and knowledge-based population techniques  ...  On the other hand, there have been some works focusing on hierarchical classification and retrieval for ontology inference.  ... 
doi:10.1109/jproc.2012.2201909 fatcat:4hcia4agvbaija2kx5ynj2esse

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 particularly examine two of such methods: cross-media similarities and random walk based scores.  ...  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.  ...  On the one hand, we analyze the cross-media similarity approach proposed in for image retrieval in the context of ImageCLEF multimedia retrieval tasks.  ... 
doi:10.1145/2699668 fatcat:p3bqd767sjcbbdn2hn3fpxmp2i
« Previous Showing results 1 — 15 out of 2,916 results