Filters








120 Hits in 3.5 sec

Exploring Flickr's related tags for semantic annotation of web images

Hongtao Xu, Xiangdong Zhou, Mei Wang, Yu Xiang, Baile Shi
2009 Proceeding of the ACM International Conference on Image and Video Retrieval - CIVR '09  
In this paper, we first propose a novel approach to derive semantic correlation matrix from Flickr's related tags resource.  ...  We then develop a novel conditional random field model for Web image annotation, which integrates the keyword correlations derived from Flickr, and the textual and visual features of Web images into an  ...  In this paper, we first explore the Flickr's Related Tags to derive a semantic correlation matrix.  ... 
doi:10.1145/1646396.1646450 dblp:conf/civr/XuZWXS09 fatcat:goebeq2aozbidlkjzqpy3op6ea

Flickr: Organizing and Tagging Images Online

Emma Stuart
2019 Knowledge organization  
This article examines the links between Flickr's success and how images are organized within the site, as well as the types of people and organizations that use Flickr and their motivations for doing so  ...  Factors that have contributed to Flickr's demise in popularity will be explored, and the article finishes with some suggestions for how Flickr could develop in the future, along with some conclusions for  ...  The same is likely to be true for the automatic addition of semantic tags.  ... 
doi:10.5771/0943-7444-2019-3-223 fatcat:ej2vbviazrc4nln6ftufz4fk7a

Collecting, Analyzing and Predicting Socially-Driven Image Interestingness

Eloiise Berson, Q. K. Ngoc Duong, Claire-Helene Demarty
2019 2019 27th European Signal Processing Conference (EUSIPCO)  
To push forward research in this topic, a large-scale interestingness dataset (images and their associated metadata) is described in this paper and released for public use.  ...  We then propose computational models based on deep learning to predict image interestingness.  ...  Please note that because of copyright issues, we do not release the images but their links to Flickr's web site. 5 https://github.com/gyglim/personalized-highlights-dataset 6 http://www.acmmm.org/2017  ... 
doi:10.23919/eusipco.2019.8902803 dblp:conf/eusipco/BersonDD19 fatcat:fyugfhlwvndpvggl52njrk7wiy

A novel system for the semi automatic annotation of event images

Philip James McParlane, Joemon Jose
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
Specifically, we present a novel tag recommendation system for images taken at a popular music festival which allows the user to select relevant tags from related Tweets and Wikipedia content, thus reducing  ...  Many methods have therefore looked to exploit new sources of evidence for annotation purposes, such as image context for example.  ...  Organising these images is difficult, however, as a result of the semantic gap [3] and lack of annotations provided by users [4] ; an entire field of work has focused on the automatic annotation of  ... 
doi:10.1145/2600428.2611188 dblp:conf/sigir/McParlaneJ14a fatcat:nxpabochcjdehosskiqiqjrgym

Adaptive Model for Integrating Different Types of Associated Texts for Automated Annotation of Web Images [chapter]

Hongtao Xu, Xiangdong Zhou, Lan Lin, Mei Wang, Tat-Seng Chua
2009 Lecture Notes in Computer Science  
We also demonstrate that we can leverage the social tagging data of Web images, such as the Flickr's Related Tags, to enhance the performance of Web image annotation.  ...  It is well known that the semantics of Web images are well correlated with these associated texts, and thus they can be used to infer the semantics of Web images.  ...  Acknowledgment This work was partially supported by the NRF of Singapore Grant R-252-000-325-279, NSF of China Grant 60403018 and 60773077.  ... 
doi:10.1007/978-3-540-92892-8_3 fatcat:2ennuzcu5jfxjjw7urooohxkxm

Word2Image

Haojie Li, Jinhui Tang, Guangda Li, Tat-Seng Chua
2008 Proceeding of the 16th ACM international conference on Multimedia - MM '08  
In this paper, we explore how to leverage the web image collections to fulfill such task and develop a novel multimedia application system, Word2Image.  ...  Various techniques, including the correlation analysis, semantic and visual clustering are adapted into our system to produce sets of high quality, precise, diverse and representative images to visually  ...  Flickr's Related Tags is "a list of tags 'related' to the given tag, based on clustered usage analysis" [3] .  ... 
doi:10.1145/1459359.1459494 dblp:conf/mm/LiTLC08 fatcat:rszsdpypbvffra62n6orlqcini

Multimedia Indexing, Search, and Retrieval in Large Databases of Social Networks [chapter]

Theodoros Semertzidis, Dimitrios Rafailidis, Eleftherios Tiakas, Michael G. Strintzis, Petros Daras
2012 Computer Communications and Networks  
This plethora of content created the need for finding the desired media in the social media universe.  ...  /smart-phones, and web/digital cameras.  ...  Use case: Flickr's 1 Million Images In this Section we present a case study of Flickr's 1 Million image dataset 1 [18, 19] .  ... 
doi:10.1007/978-1-4471-4555-4_3 dblp:series/ccn/SemertzidisRTSD13 fatcat:6l3whv5qcjgshmjwcqh6dgelb4

On the sampling of web images for learning visual concept classifiers

Shiai Zhu, Gang Wang, Chong-Wah Ngo, Yu-Gang Jiang
2010 Proceedings of the ACM International Conference on Image and Video Retrieval - CIVR '10  
In addition, we propose a simple approach, named semantic field, for predicting the relevance between a target concept and the tag list associated with the images.  ...  This paper empirically studies the impact of exploiting the tagged images towards concept learning, investigating the issue of how the quality of pseudo training images affects concept detection performance  ...  Kennedy et al. explored the trade-off in acquiring training data by automated web image search as opposed to human annotation [13] .  ... 
doi:10.1145/1816041.1816051 dblp:conf/civr/ZhuWNJ10 fatcat:rgbjgykfgjbf5d5pn3lrix7iky

Can Global Visual Features Improve Tag Recommendation for Image Annotation?

Mathias Lux, Arthur Pitman, Oge Marques
2010 Future Internet  
., in the form of tags, photos are difficult to find and organize. In this paper, we describe a system that recommends tags for image annotation.  ...  Recent advances in the fields of digital photography, networking and computing, have made it easier than ever for users to store and share photographs.  ...  This assumption has recently been challenged in many ways, e.g., the availability of Semantic Web-related ontologies [5] , the popularity of image labeling games [6] , and the willingness of users to  ... 
doi:10.3390/fi2030341 fatcat:3oofufzkuvhppdfwx7ep6atf6y

Exploiting semantics on external resources to gather visual examples for video retrieval

David Vallet, Iván Cantador, Joemon M. Jose
2012 International Journal of Multimedia Information Retrieval  
Most of the current Web video retrieval systems rely on manual textual annotations to provide keyword-based search interfaces.  ...  An alternative commonly used approach is to ask the user for an image example, and exploit the low-level features of the image to find video content whose keyframes are similar to the image.  ...  [19] spread manual annotations across Flickr's image collection to develop effective concept detectors for image and video retrieval.  ... 
doi:10.1007/s13735-012-0017-1 fatcat:ikj64d4tdjcarbbyr5cwtjifda

Retrieving Diverse Social Images at MediaEval 2016: Challenge, Dataset and Evaluation

Bogdan Ionescu, Alexandru-Lucian Gînsca, Maia Zaharieva, Bogdan Boteanu, Mihai Lupu, Henning Müller
2016 MediaEval Benchmarking Initiative for Multimedia Evaluation  
This paper provides an overview of the Retrieving Diverse Social Images task that is organized as part of the Media-Eval 2016 Benchmarking Initiative for Multimedia Evaluation.  ...  The task addresses the problem of result diversification in the context of social photo retrieval where images, metadata, text information, user tagging profiles and content and text models are available  ...  of tags users put for their images), meanTagRank (mean rank of a user's tags in a list in which the tags are sorted in descending order according the the number of appearances in a large subsample of  ... 
dblp:conf/mediaeval/IonescuGZBLM16 fatcat:ljsbzwt6orba3l46qkvvzowtju

Exploiting User-supplied Tags for Flickr Photos Annotation

Zheng Liu, Hua Yan
2011 Journal of Software  
Afterwards, the initial tags are ranked using manifoldranking algorithm, by which regions of the photo to be annotated are served as queries to launch the manifoldranking algorithm which ranks the initial  ...  Next, using Flickr API, top ranked initial annotations are expanded by a weighted voting scheme. Finally, we combine top ranked initial tags with expanding tags to construct final annotations.  ...  Obtaining Related Tags by Flickr API According to the Flickr's Related Tag API which is named flickr.tags.getRelated, each tag has a list of "related" tags.  ... 
doi:10.4304/jsw.6.10.1898-1905 fatcat:ikf3gsyb45hfdh7vuffswv6iou

AVA: A large-scale database for aesthetic visual analysis

N. Murray, L. Marchesotti, F. Perronnin
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
It contains over 250,000 images along with a rich variety of meta-data including a large number of aesthetic scores for each image, semantic labels for over 60 categories as well as labels related to photographic  ...  We show the advantages of AVA with respect to existing databases in terms of scale, diversity, and heterogeneity of annotations.  ...  Semantic annotations: We provide 66 textual tags describing the semantics of the images. Approximately 200,000 images contain at least one tag, and 150,000 images contain 2 tags.  ... 
doi:10.1109/cvpr.2012.6247954 dblp:conf/cvpr/MurrayMP12 fatcat:xv6ngzlnqrfdleza3p72cu6vmm

Towards user‐centered indexing in digital image collections

Krystyna K. Matusiak
2006 OCLC Systems & Services  
Social tagging is perceived as a tool for enhancing description of digital objects and providing a venue for user input and greater user engagement.  ...  Practical implications -Social tagging can be implemented as a supplement to professionally created metadata records to provide an opportunity for users to comment on images.  ...  The Guggenheim Museum began a preliminary exploration through a prototype application, where users are encouraged to annotate a collection of images.  ... 
doi:10.1108/10650750610706998 fatcat:dnliaxeklfbzxgda75k5oraisa

An Overview of Social Tagging and Applications [chapter]

Manish Gupta, Rui Li, Zhijun Yin, Jiawei Han
2011 Social Network Data Analytics  
Metadata generated in the form of tags can be efficiently used to improve web search, for web object classification, for generating ontologies, for enhanced browsing etc.  ...  Broadly, we would discuss about properties of tag streams, tagging models, tag semantics, generating recommendations using tags, visualizations of tags, applications of tags, integration of different tagging  ...  ELSABer has the following features: (1) the semantic relations between annotations are explored for browsing of similar resources; (2) the hierarchical relations between annotations are constructed for  ... 
doi:10.1007/978-1-4419-8462-3_16 fatcat:czs2um2xvrd6vnfpefzae2ftwq
« Previous Showing results 1 — 15 out of 120 results