Tagging photos using users' vocabularies

Qian, Xueming; Liu, Xiaoxiao; Chao, Zheng; Du, Youtian; Hou, Xingsong

doi:10.1016/j.neucom.2012.12.021

Cited by 60 publications

(27 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another common measurement of evaluating the performance is Average Precision shown as (12), where R is the number of all the relevant images in image set, is the number of relevant images among the top j ranked images, and if the j-th images is relevant = 1, otherwise = 0. And the result is shown in TABLE II.…”

Section: Tag De-noisingmentioning

confidence: 99%

“…Many outstanding works focus on the social image tags relevance learning from multiple perspectives: [12] proposes a tag recommender system by using social images' meta-data, such as images' GPS information and photo taken time, etc. ; [1,[13][14][15][16][17][18] study the tags relevance by textual information, for example [1,13,17,18] calculate the tags concurrence probability and analyze the semantical relevance between tags, [14] analyzes the ontological relationship for tags, [1,15] assume that the important tags' positions are prior to those irrelevant ones; [19,20] argue that tags are content-related to the image, and after comparing to other 3 factors, [19] concludes that the image content is the key factor for tag relevance learning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Social Image Tag Relevance Learning based on Pixel Voting

Liu¹,

Ruan²,

Cai³

et al. 2018

dtcse

View full text Add to dashboard Cite

Social image platforms allow their users sharing and searching their photos based on images' tags. These tags are provided by different users. Inevitably, the tags are spontaneously ambiguous, and personalized. So, learning the relevance between tags and images is playing an important role in tag-based retrieval systems. Choosing visual neighbors for seed images as voters is a widely used method for learning tag relevance. However, most existing methods of choosing visual neighbors for seed images are based on the global features of the whole images, ignoring the local features. In this paper we propose a pixel voting method to choose the visual neighbors for seed images. Experiment shows that this method is a more natural way to measure the similarity of images. Based the selected neighbors we learn the tag relevance, and the experiment on the MIR Flickr dataset shows that our algorithm is effective in tag de-noising and tag ranking.

show abstract

Section: Tag De-noisingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Social Image Tag Relevance Learning based on Pixel Voting

Liu¹,

Ruan²,

Cai³

et al. 2018

dtcse

View full text Add to dashboard Cite

show abstract

“…Flickr.com is a rich image sharing site which lets to download the publically shared photographs through its open API [8], [13].The data set for my paper is downloaded using this API of Flickr for two cities of Los Angeles and Berlin. Using the data set directly would lead to many errors.…”

Section: Data Collectionmentioning

confidence: 99%

Hybrid Approach for Location Based Customized POI Travel Recommendation System

Chitra¹,

A²

2016

IJECS

View full text Add to dashboard Cite

Abstract:The creation of world of internet lead to many advancements in the technical as well as non-technical fields. Many thriving industries gained enormous advantages through the development of internet. Tourism is one among the flourishing industries of this era. Earlier the approach to visit a place is far beyond what is available today. Ranging from pamphlet to maps were made use to visit a place. Routing of places was done using maps and travel guides. Unlike before, the tourism industry has grown to great heights and handles the tours and travel without any manual intercession. The places are endorsed to users automatically using the recommendation system. Existing recommendation systems suffer from a problem of sparsity. Sparsity problem deals with inadequate data related to a user or any travel region. The proposed approach concentrate on eliminating this snag in the existing approach and generating a travel recommendation structure which focus on customized suggestions for users. The tags as well as geotags of images uploaded by the users on social sites like Flickr is made use in order to recommend the points of interest (POI) to the users. A hybrid approach with use of tags, geotags and the owner (author) of the image is proposed in this paper. User based collaborative filtering is used to create suggestions for the users. The benefits of the proposed approach is manifested by experimental analysis on a large cluster of data.

show abstract

“…et al [11] mentions that users in this case it would be the researchers, if they are to upload images themselves they would most likely give images tags according to their own vocabularies to describe the contents of their images. Wang.…”

Section: Image Tagging / Annotationmentioning

confidence: 99%

Intra Organisational Information Retrieval System for an Agricultural Research Institute in South Africa

2016

International Conference on Advances in Science, Engineering, Technology and Natural Resources (ICASETNR-16) Nov. 24-25, 2016 P

View full text Add to dashboard Cite

Abstract-Intra organisational information sharing is a tool that can ensure efficiency within the organization. Benefits of this include amongst others; conservation of vital information, time saving, reduced expenditure, and minimisation of information duplication. We investigate the benefits of intra organisational information sharing as a tool in an organisation. The study characterised, examined and discussed detail information sharing, image annotation, content based image retrieval, as well as semantic tagging and taxonomy. The crucial element of this tool is annotation, and the significant role it plays in the success of intra organisational information sharing. Furthermore; since the users are the outlets of the information that will be fed into the intra organisational information sharing; the study also investigates the manner in which users approach the indexing of information to be shared. We also investigate manners in which the shared information should be described during indexing, and how the description impacts on the ease of other users to access and annotate the information and the contents. The study also investigated existing methods that influence the manner in which users tag and these include; amongst others; model based, descriptive as well as categorised. These are methods that are commonly recommended to ensure simplicityof sharing and retrieving of information by receipt users from the framework created. Methods that are used to retrieve information from the system itself were also investigated. These are tailored into the six design science (DS) steps using programming language and specific design and development methodsts the footnote at the bottom of this column.

show abstract

Tagging photos using users' vocabularies

Cited by 60 publications

References 21 publications

Social Image Tag Relevance Learning based on Pixel Voting

Social Image Tag Relevance Learning based on Pixel Voting

Hybrid Approach for Location Based Customized POI Travel Recommendation System

Intra Organisational Information Retrieval System for an Agricultural Research Institute in South Africa

Contact Info

Product

Resources

About