1,029 Hits in 9.1 sec

Improving image annotation via ranking-oriented neighbor search and learning-based keyword propagation

Chaoran Cui, Jun Ma, Tao Lian, Zhumin Chen, Shuaiqiang Wang
2014 Journal of the Association for Information Science and Technology  
In the phase of neighbor search, different from existing work discovering the nearest neighbors with the predicted distance, we introduce a ranking-oriented neighbor search mechanism (RNSM), where the  ...  In this article, we propose a novel approach for image annotation, which simultaneously improves both phases of the nearest-neighbor-based scheme.  ...  Learning-Based Keyword Propagation Strategy With the set of neighbor images N H new x ( ) , the next step is to evaluate the relevance of the keywords associated with the neighbors and to propagate the  ... 
doi:10.1002/asi.23163 fatcat:ip6lazw64vb6hmtxyvciyk5w6y

Ranking-oriented nearest-neighbor based method for automatic image annotation

Chaoran Cui, Jun Ma, Tao Lian, Xiaofang Wang, Zhaochun Ren
2013 Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval - SIGIR '13  
Given a new image, the scheme is to first find its most similar neighbors from labeled images, and then propagate the keywords associated with the neighbors to it.  ...  Recently, the nearest-neighbor based scheme has been proposed and achieved good performance for image annotation.  ...  CONCLUSIONS In this paper, we have introduced a novel image annotation method, which adapts the conventional nearest-neighbor based approaches with a ranking-oriented neighbor search mechanism.  ... 
doi:10.1145/2484028.2484113 dblp:conf/sigir/CuiMLWR13 fatcat:f7us5ca22vhexjeogrbyvpqayy

An Architecture of a Web-Based Collaborative Image Search Engine [chapter]

Wei-Cheng Lai, Gerard Sychay, Edward Chang
2002 Lecture Notes in Computer Science  
On the one hand, the improved annotation can help provide better initial keyword-search results to seed perception-based image retrieval.  ...  We show that the learner can collect user feedback and use it to perform collaborative image annotation in addition to learning subjective query concepts.  ...  When a text-based search is initiated with keywords, images are ranked and retrieved based on their combined con dence factors in the matching labels.  ... 
doi:10.1007/3-540-36124-3_23 fatcat:2zc3ji7avfcx7gougum3uec7oy

Frontiers in multimedia search

Alan Hanjalic, Martha Larson
2011 Proceedings of the 19th ACM international conference on Multimedia - MM '11  
Larson • Requirements regarding usefulness of multimedia search systems • Frontiers of MIR and beyond A. Hanjalic & M.  ...  Larson • Requirements regarding usefulness of multimedia search systems • Frontiers of MIR and beyond A. Hanjalic & M.  ...  Frontiers in Multimedia Search, ACM Multimedia, Scottsdale, US, November 2011 Revealing Hidden Cool Places Near2Me video (9 minutes)  ... 
doi:10.1145/2072298.2072398 dblp:conf/mm/HanjalicL11 fatcat:txi4arbwdfcyhgqk25cdqfvxbm

Social tag relevance learning via ranking-oriented neighbor voting

Chaoran Cui, Jialie Shen, Jun Ma, Tao Lian
2016 Multimedia tools and applications  
In this paper, we investigate the problem from a new perspective of learning to rank, and develop a novel approach to facilitate tag relevance learning to directly optimize the ranking performance of tag-based  ...  High quality tags play a critical role in applications involving online multimedia search, such as social image annotation, sharing and browsing.  ...  Based on the formulation, the ranking-oriented learning determines the parameters to directly optimize the ranking performance of tagbased image search.  ... 
doi:10.1007/s11042-016-3512-1 fatcat:oxwe4wikgff2tcpccvg3vchi5u

Improving the quality of K-NN graphs through vector sparsification: application to image databases

Michael E. Houle, Xiguo Ma, Vincent Oria, Jichao Sun
2014 International Journal of Multimedia Information Retrieval  
These techniques are then applied to image applications such as content-based image retrieval and image label propagation.  ...  image retrieval and automated image annotation.  ...  Chapter 2 reviews research literature that is related to this work, including work on content-based similarity search and image retrieval, image annotation and label propagation, feature learning and metric  ... 
doi:10.1007/s13735-014-0067-7 fatcat:2w3k3fcexjax5i6h42hqqcrtzi

Semi-supervised learning for scalable and robust visual search

Jun Wang
2011 ACM SIGMultimedia Records  
for the bivariate optimization procedure; c) novel applications of the proposed techniques, such as interactive image retrieval, automatic re-ranking for text based image search, and a brain computer  ...  The graph-based approaches are used to improve accuracy, while hashing approaches are used to improve efficiency and cope with large-scale applications.  ...  In Section 5.3, we apply the LDST algorithm to improve web image search by re-ranking initial search results based on keywords.  ... 
doi:10.1145/2069210.2069213 fatcat:hblb5ncrprcrlgi6ugph6naucy

[Invited Paper] A Review of Web Image Mining

Keiji Yanai
2015 ITE Transactions on Media Technology and Applications  
of visual concept database for image/video recognition, (2) Web image application for visual concept analysis and data-driven computer graphics, and (3) real-world sensing through Web images to detect  ...  In this paper, we review works related to big visual data on the Web in the literature of computer vision and multimedia research regarding the following points: (1) Web image acquisition for construction  ...  Do Hang Nga and anonymous reviewers.  ... 
doi:10.3169/mta.3.156 fatcat:gduk25dp7nedvm65xurbwzdu3y

Image search—from thousands to billions in 20 years

Lei Zhang, Yong Rui
2013 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
feedback and crowdsourcing, mobile image search, and creative multimedia interfaces.  ...  Based on the review, the concluding section discusses open research challenges and suggests future research directions in effective visual representation, image knowledge base construction, implicit user  ...  with the authors on the large-scale image search and annotation problems.  ... 
doi:10.1145/2490823 fatcat:cor23f3c7nb7fimy4ixp32bdk4

Image Annotation by Graph-Based Inference With Integrated Multiple/Single Instance Representations

Jinhui Tang, Haojie Li, Guo-Jun Qi, Tat-Seng Chua
2010 IEEE transactions on multimedia  
In most of the learning-based image annotation approaches, images are represented using multiple-instance (local) or single-instance (global) features.  ...  Thus this paper explores a unified learning framework that combines the multiple-instance and single-instance representations for image annotation.  ...  To support this, keywords describing the images are required to retrieve and rank images. Manual annotation is a direct way to obtain these keywords. However, it is labor-intensive and error-prone.  ... 
doi:10.1109/tmm.2009.2037373 fatcat:vwujl4ttk5frvhahz2me7i6cdi

Assistive tagging

Meng Wang, Bingbing Ni, Xian-Sheng Hua, Tat-Seng Chua
2012 ACM Computing Surveys  
Therefore, a set of new techniques has been developed by combining humans and computers for more accurate and efficient multimedia tagging, such as batch tagging, active tagging, tag recommendation, and  ...  We first introduce the status of automatic tagging and manual tagging and then state why assistive tagging can be a good solution.  ...  Search-based methods predict the tags of a new sample via finding its neighbors in the training set.  ... 
doi:10.1145/2333112.2333120 fatcat:cvlxcazimvdjxigdvchjinnewe

Geotag Propagation with User Trust Modeling [chapter]

Ivan Ivanov, Peter Vajda, Jong-Seok Lee, Pavel Korshunov, Touradj Ebrahimi
2012 Computer Communications and Networks  
For each tagged image, similar untagged images are found by the robust graph-based object duplicate detection, and the known tags are propagated accordingly.  ...  The tag propagation in images relies on the similarity between image content (famous landmarks) and its context (associated geotags).  ...  manually annotated via geocoding.  ... 
doi:10.1007/978-1-4471-4555-4_13 dblp:series/ccn/IvanovVLKE13 fatcat:jmcuzfxn5zbvjmjsioskqnnkc4

Image Retrieval: Modelling Keywords via Low-level Features

Zenonas Theodosiou
2015 ELCVIA Electronic Letters on Computer Vision and Image Analysis  
In recent years, much effort has been invested on automatic image annotation methods, since the manual assignment of keywords (which is necessary for text-based image retrieval) is a time consuming and  ...  However, text-based image retrieval requires images to be annotated i.e. they are related to text information.  ...  [52] to improve the text-based Web image search. The algorithm utilizes visual features to discard irrelevant images from the image list returned by a text-based image search engine. Wang et al.  ... 
doi:10.5565/rev/elcvia.725 fatcat:zbpgc3jstnd5nf5ltcly3rdbhi

On the Annotation of Web Videos by Efficient Near-Duplicate Search

Wan-Lei Zhao, Xiao Wu, Chong-Wah Ngo
2010 IEEE transactions on multimedia  
Second, based on the outcome of near-duplicate search, we explore the potential that the data-driven annotation could be successful when huge volume of tagged web videos is freely accessible online.  ...  Experiments on cross sources (annotating Google videos and Yahoo!  ...  Tag Annotation The performance of semantic-based image/video search depends largely on the quality of the keywords or annotation.  ... 
doi:10.1109/tmm.2010.2050651 fatcat:awgmbmsniraktfgmk37lf2u3tu

Leveraging Features from Background and Salient Regions for Automatic Image Annotation

Supheakmungkol Sarin, Michael Fahrmair, Matthias Wagner, Wataru Kameyama
2012 Journal of Information Processing  
We chose two publicly available datasets manually annotated with diverse nature of images for our experiments, namely, the Corel5K and ESP Game datasets.  ...  In this era of information explosion, automating the annotation process of digital images is a crucial step towards efficient and effective management of this increasingly high volume of content.  ...  Acknowledgments The authors would like to thank anonymous reviewers and Dr. Roman Katz for their constructive comments that helped us to improve the manuscript.  ... 
doi:10.2197/ipsjjip.20.250 fatcat:rklqzbcrdfd2lfn4togs3erkom
« Previous Showing results 1 — 15 out of 1,029 results