Filters








41 Hits in 2.4 sec

Retagging social images based on visual and semantic consistency

Dong Liu, Xian-Sheng Hua, Meng Wang, Hong-Jiang Zhang
2010 Proceedings of the 19th international conference on World wide web - WWW '10  
The refining process is formulated as an optimization framework based on the consistency between "visual similarity" and "semantic similarity" in social images.  ...  This paper proposes a social image "retagging" scheme that aims at assigning images with better content descriptors.  ...  In this work, we propose an optimization framework to improve the tag quality based on the following two observations in real-world social images.  ... 
doi:10.1145/1772690.1772848 dblp:conf/www/LiuHWZ10 fatcat:un7vi57pjfgf5lbfoblg6rcnwu

Image Retagging Using Collaborative Tag Propagation

Dong Liu, Shuicheng Yan, Xian-Sheng Hua, Hong-Jiang Zhang
2011 IEEE transactions on multimedia  
The retagging process is formulated as a multiple graph-based multi-label learning problem, which simultaneously explores the visual content of the images, semantic correlation of the tags as well as the  ...  Experimental results on two benchmark Flickr image datasets demonstrate the effectiveness of our proposed image retagging scheme.  ...  [23] proposed to refine the tags based on the visual and semantic consistency residing in the social images, which assigns similar tags to visually similar images.  ... 
doi:10.1109/tmm.2011.2134078 fatcat:pksmgazirverldql3o6y6yinti

Semantic Based Image Annotation Using Descriptive Features and Retagging approach

Nagarani P
2012 The International Journal of Multimedia & Its Applications  
The Semantic based annotation of an image is very important and a difficult task in content-based image retrieval (CBIR).  ...  The ability to annotate images semantically based on the objects that they contain is essential in image retrieval as it provides the mechanism to take advantage of existing text retrieval systems.  ...  To address this difficulty, another work proposed to refine the tags based on the visual and semantic consistency residing in the social images, which assigns similar tags to visually similar images.  ... 
doi:10.5121/ijma.2012.4102 fatcat:mrdi6h7ijjdqjchcv2lktlknny

Image retagging

Dong Liu, Xian-Sheng Hua, Meng Wang, Hong-Jiang Zhang
2010 Proceedings of the international conference on Multimedia - MM '10  
The refining process, including denoising and enriching, is formulated as an optimization framework based on the consistency between "visual similarity" and "semantic similarity" in social images, that  ...  is, the visually similar images tend to have similar semantic descriptors, and vice versa.  ...  EMPIRICAL STUDY We implement and evaluate our retagging approach on a collection of social images.  ... 
doi:10.1145/1873951.1874031 dblp:conf/mm/LiuHWZ10 fatcat:p4u2mu3dajhljdjt5b6qyxd5cu

Music retagging using label propagation and robust principal component analysis

Yi-Hsuan Yang, Dmitry Bogdanov, Perfecto Herrera, Mohamed Sordo
2012 Proceedings of the 21st international conference companion on World Wide Web - WWW '12 Companion  
In this paper, we present a preliminary study that aims at refining (retagging) social tags by exploiting the content similarity between tracks and the semantic redundancy of the track-tag matrix.  ...  The evaluated algorithms include a graph-based label propagation method that is often used in semi-supervised learning and a robust principal component analysis (PCA) algorithm that has led to state-of-the-art  ...  This work was supported by a grant from the National Science Council of Taiwan under contract NSC 100-2218-E-001-009 and partially supported by the following projects:  ... 
doi:10.1145/2187980.2188217 dblp:conf/www/YangBHS12 fatcat:rvtxphg3zja73foayyn5e7o2hm

Content-based tag processing for Internet social images

Dong Liu, Xian-Sheng Hua, Hong-Jiang Zhang
2010 Multimedia tools and applications  
Online social media services such as Flickr and Zooomr allow users to share their images with the others for social interaction.  ...  This paper provides a comprehensive survey of the technical achievements in the research area of content-based tag processing for social images, covering the research aspects on tag ranking, tag refinement  ...  Acknowledgements The authors would like to thank Xirong Li, Xiaobai Liu, and Dr. Guangyu Zhu who contribute the figures illustrating their works introduced in this paper.  ... 
doi:10.1007/s11042-010-0647-3 fatcat:7djlumhk6ncu5jymyae7ufp5ze

Social Anchor-Unit Graph Regularized Tensor Completion for Large-Scale Image Retagging [article]

Jinhui Tang, Xiangbo Shu, Zechao Li, Yu-Gang Jiang, Qi Tian
2018 arXiv   pre-print
Recent approaches simultaneously explore visual, user and tag information to improve the performance of image retagging by constructing and exploring an image-tag-user graph.  ...  Second, a tensor completion based on SUGAR is implemented on the original image-tag-user tensor to refine the tags of the anchor images.  ...  representative anchor units, where one anchor unit consists of an information, and user information for social image retagging.  ... 
arXiv:1804.04397v2 fatcat:fxzkgsdcfbfg5ekutmcmwduyru

Image Tag Refinement by Regularized Latent Dirichlet Allocation [article]

Jingdong Wang, Jiazhen Zhou, Hao Xu, Tao Mei, Xian-Sheng Hua, and Shipeng Li
2013 arXiv   pre-print
The experiments on tag ranking and image retrieval demonstrate the advantages of the proposed method.  ...  Moreover, both the statistics of tags and visual affinities of images in the corpus are explored to help topic modeling.  ...  Tag ranking based on visual and semantic consistency (TRVSC) [24] . This work follows RWR [32] using a random walk based method.  ... 
arXiv:1307.7974v1 fatcat:vl3wmkru3zgfrdirq7yghpw32e

Correlation consistency constrained probabilistic matrix factorization for social tag refinement

Jing Liu, Yifan Zhang, Zechao Li, Hanqing Lu
2013 Neurocomputing  
With the permeation of Web 2.0, large-scale user contributed images with tags are easily available on social websites.  ...  Besides, two types of correlation consistency, i.e., the image-bias correlation consistency (from image similarity to tag relevance) and the tag-bias correlation consistency (from tag relevance to image  ...  The first case, denoted as image-bias correlation consistency, is that visually similar images often reflect similar semantic themes and so should share similar tags, and vice versa is for the second type  ... 
doi:10.1016/j.neucom.2012.02.052 fatcat:tgv7oa4k7vci3fn5a57m36fgqq

Web video retagging

Zhineng Chen, Juan Cao, Tian Xia, Yicheng Song, Yongdong Zhang, Jintao Li
2010 Multimedia tools and applications  
Given a web video, video retagging first collect its textually and visually related neighbor videos.  ...  Two kinds of experiments, i.e., application-oriented video search and categorization and user-based subjective studies are carried out on a large-scale web video dataset, which demonstrate that in most  ...  Then they evaluate the visual consistence between the image and images collected from search engines by querying the candidate annotation.  ... 
doi:10.1007/s11042-010-0604-1 fatcat:pkecbwi6rnfkxl5bdu2fsxegbe

Semantic context learning with large-scale weakly-labeled image set

Yao Lu, Wei Zhang, Ke Zhang, Xiangyang Xue
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
Visual context, semantic context, and neighborhood consistency in both visual and semantic spaces are sufficiently leveraged in the proposed framework.  ...  Furthermore, semantics richness requires more than one label to describe one image in real applications, and multiple labels usually interact with each other in semantic space.  ...  By investigating the label confidence matrix for image exemplars from column and row views, our method sufficiently leverages visual context, semantic context, and neighborhood consistency in both visual  ... 
doi:10.1145/2396761.2398532 dblp:conf/cikm/LuZZX12 fatcat:vivhicveuvccrdjruj5y3mkrau

Learning to Hash-tag Videos with Tag2Vec [article]

Aditya Singh, Saurabh Saini, Rajvi Shah, PJ Narayanan
2016 arXiv   pre-print
User-given tags or labels are valuable resources for semantic understanding of visual media such as images and videos.  ...  Recently, a new type of labeling mechanism known as hash-tags have become increasingly popular on social media sites.  ...  Rajvi Shah and Saurabh Saini are supported respectively by Google and TCS PhD fellowships. We thank these organizations for their valuable support.  ... 
arXiv:1612.04061v1 fatcat:l45mrdvnc5a67ac4xkhmozkvq4

Hyrarchical Classification of Images to Predict Privacy Policy to Uploaded Images on Content Sharing Site

2017 International Journal of Science and Research (IJSR)  
Our solution relies on an image relegation framework for image categories which may be associated with homogeneous policies and on a policy presage algorithm to automatically engender a policy for each  ...  Some users over CSS affect user's privacy on their personal contents, where some users keep on sending unwanted comments and messages by taking advantage of the user's inherent trust in their relationship  ...  This framework is based on the consistency between "visual similarity" as well as "semantic similarity" in social images.  ... 
doi:10.21275/art20164243 fatcat:mtfssp2rxzemfnuffk2fzhubhy

Image Tag Recommendation based on Ranked Categorical Nearest Neighbors and Weighted Tag Features

Anupama D. Dondekar, Balwant A. Sonkamble
2020 Advances in Science, Technology and Engineering Systems  
On many image sharing websites, tags can be assigned by the users to an image that describes the contextual and visual description of an image.  ...  The huge number of images on the image sharing websites poses challenges for classification and retrieval of the images.  ...  In [7] an approach for retagging of social images with diverse semantics was presented.  ... 
doi:10.25046/aj0506166 fatcat:swsx3x46qfhvflfdgkrxphvk3u

The effects of multiple query evidences on social image retrieval

Zhiyong Cheng, Jialie Shen, Haiyan Miao
2014 Multimedia Systems  
Acknowledgments Jialie Shen and Zhiyong Cheng are partially supported by Mobile plus Cloud Computing Theme Research Program Award-Microsoft Research. Portions of this work appeared in [7, 52] .  ...  ., OKAPI-BM25 [26] and vector space model [49] ) on tag-based social image search.  ...  Performances of the CBIR systems The search performances based on different types of visual features on social image search are presented in Fig. 3 and Table 2 .  ... 
doi:10.1007/s00530-014-0432-7 fatcat:m6en7vwiv5cdxiphuj3mwozi4m
« Previous Showing results 1 — 15 out of 41 results