Filters








404 Hits in 3.8 sec

The MIR flickr retrieval evaluation

Mark J. Huiskes, Michael S. Lew
2008 Proceeding of the 1st ACM international conference on Multimedia information retrieval - MIR '08  
In this paper we present a collection for the MIR community comprising 25000 images from the Flickr website which are redistributable for research purposes and represent a real community of users both  ...  In most well known image retrieval test sets, the imagery typically cannot be freely distributed or is not representative of a large community of users.  ...  MIR Flickr set The tags can be subdivided in various categories.  ... 
doi:10.1145/1460096.1460104 dblp:conf/mir/HuiskesL08 fatcat:5m3xz3ivmfbstnwua5dwlka65u

The MIR Flickr Retrieval Evaluation Proposal Based on User Tags and Textual Passwords

Pavan Gujjar Panduranga Rao, Dr. P. Srinivasa Rao, Dr. G. Lavanya Devi
2017 International Journal of Advanced engineering Management and Science  
In this paper we present a collection for the MIR community comprising 69,000 images from the Flickr website which are redistributable for research purposes and represent a real community of users both  ...  In most well known image retrieval test sets, the imagery typically cannot be freely distributed or is not representative of a large community of users.  ...  The MIR Flickr Retrieval Evaluation Proposal Based on User Tags and Textual Passwords I.  ... 
doi:10.24001/ijaems.3.4.10 fatcat:jjyqzqpdovhcjdkpug6yxc2so4

New trends and ideas in visual concept detection

Mark J. Huiskes, Bart Thomee, Michael S. Lew
2010 Proceedings of the international conference on Multimedia information retrieval - MIR '10  
The MIR Flickr collection consists of 25000 high-quality photographic images of thousands of Flickr users, made available under the Creative Commons license.  ...  To keep the MIR Flickr collection upto-date on these developments, we have formulated two new initiatives to extend the original image collection.  ...  The MIR Flickr annotations were set up with the goal of evaluating the performance of retrieval systems based on relevance feedback.  ... 
doi:10.1145/1743384.1743475 dblp:conf/mir/HuiskesTL10 fatcat:cvnawyrgzrd3zodaxbkxeu2ae4

RetrievalLab

Ard Oerlemans, Michael S. Lew
2011 Proceedings of the 1st ACM International Conference on Multimedia Retrieval - ICMR '11  
It is a tool to facilitate the testing of new features, segmentations, machine learning approaches, and evaluation methods, by presenting a Matlab-like programming interface which illuminates the fundamental  ...  processes and algorithms in content based retrieval.  ...  We added support for loading ground truth for the MIR-FLICKR [4, 11] and IMAGECLEF [6] datasets. > db=loaddatabase("D:\MIR-Flickr\") > loadmirflickrtags(db, "D:\tree_r1.txt") > loadfeature(db, "hsv  ... 
doi:10.1145/1991996.1992067 dblp:conf/mir/OerlemansL11 fatcat:nzng5aoklzen7gzo24y4ttngem

Evaluating Temporal Information for Social Image Annotation and Retrieval [chapter]

Tiberio Uricchio, Lamberto Ballan, Marco Bertini, Alberto Del Bimbo
2013 Lecture Notes in Computer Science  
and MIR-Flickr-1M.  ...  Can we use the temporal evolution of annotations in Web images to improve tasks such as annotation, indexing and retrieval? This important question is the main motivation for this work.  ...  ] [23] [17] [3] : NUS-WIDE [5] and MIR-Flickr-1M [9] .  ... 
doi:10.1007/978-3-642-41181-6_73 fatcat:jo3j45eafvchxeggcxg2vqxcbu

Combining Convolutional Neural Network and Markov Random Field for Semantic Image Retrieval

Haijiao Xu, Changqin Huang, Xiaodi Huang, Chunyan Xu, Muxiong Huang
2018 Advances in Multimedia  
With the rapidly growing number of images over the Internet, efficient scalable semantic image retrieval becomes increasingly important.  ...  This paper presents a novel approach for semantic image retrieval by combining Convolutional Neural Network (CNN) and Markov Random Field (MRF).  ...  Figure 4 :Figure 5 : 45 MAPs and P@10s (%) of semantic image retrieval for rare concepts and frequent concepts on MIR Flickr 2011.  ... 
doi:10.1155/2018/6153607 fatcat:tgiiawr63bgbbk23mxqptjoiky

Online Cross-Modal Hashing for Web Image Retrieval

Liang Xie, Jialie Shen, Lei Zhu
2016 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Experimental results on two real-world multi-modal web image datasets: MIR Flickr and NUS-WIDE, demonstrate the effectiveness and efficiency of OCMH for online cross-modal web image retrieval.  ...  Cross-modal hashing (CMH) is an efficient technique for the fast retrieval of web image data, and it has gained a lot of attentions recently.  ...  Experiments Datasets and Features In our experiments, two real-world web image datasets: MIR Flickr and NUS-WIDE, are used to evaluate the effectiveness and efficiency of OCMH.  ... 
doi:10.1609/aaai.v30i1.9982 fatcat:qj6ayzdsb5apzafnidlvgej25q

TELECOM ParisTech at ImageCLEF 2010 Photo Annotation Task: Combining Tags and Visual Features for Learning-Based Image Annotation

Hichem Sahbi, Xi Li
2010 Conference and Labs of the Evaluation Forum  
The results clearly corroborate (i) the complementarity of tags and visual descriptors and (ii) the effectiveness of SVM classifiers in photo annotation.  ...  In this paper, we describe the participation of TELECOM ParisTech in the ImageCLEF 2010 Photo Annotation challenge.  ...  Acknowledgement This work is supported by the French National Research Agency (ANR) under the AVEIR project.  ... 
dblp:conf/clef/SahbiL10 fatcat:whbokooqf5hdnf63zdjw2fkanq

A comparative study of similarity measures for content-based multimedia retrieval

Christian Beecks, Merih Seran Uysal, Thomas Seidl
2010 2010 IEEE International Conference on Multimedia and Expo  
Our findings can be used in guiding the development of content-based retrieval applications for numerous domains.  ...  Furthermore, we study the behavior of the similarity measures by discussing their properties.  ...  [25] , the MIR Flickr database [26] , and the 101objects database [27] .  ... 
doi:10.1109/icme.2010.5582949 dblp:conf/icmcs/BeecksUS10 fatcat:gwtpohet4fdn3jvh7anlszfovu

Image annotation with tagprop on the MIRFLICKR set

Jakob Verbeek, Matthieu Guillaumin, Thomas Mensink, Cordelia Schmid
2010 Proceedings of the international conference on Multimedia information retrieval - MIR '10  
We would like to thank the ANR project R2I as well as the QUAERO project for their financial support.  ...  Image annotation is an important computer vision problem where the goal is to determine the relevance of annotation terms for images.  ...  The MIR Flickr set The MIR Flickr set has been recently introduced [11] to evaluate keyword-based image retrieval methods.  ... 
doi:10.1145/1743384.1743476 dblp:conf/mir/VerbeekGMS10 fatcat:p6qsxkvfgnggzk5mw7362eq4vy

Task-adaptive Asymmetric Deep Cross-modal Hashing [article]

Fengling Li, Tong Wang, Lei Zhu, Zheng Zhang, Xinhua Wang
2022 arXiv   pre-print
However, existing researches equally handle the different tasks of cross-modal retrieval, and simply learn the same couple of hash functions in a symmetric way for them.  ...  Under such circumstance, the uniqueness of different cross-modal retrieval tasks are ignored and sub-optimal performance may be brought.  ...  MIR Flickr is offered by the LIACS Media Lab at Leiden University. The images of MIR Flickr are downloaded from the social photography site Flickr.  ... 
arXiv:2004.00197v2 fatcat:osykjo375jdy5hkpo6kbhxnbsq

Identification of MIR-Flickr Near-duplicate Images - A Benchmark Collection for Near-duplicate Detection

Richard Connor, Stewart MacKenzie-Leigh, Franco Alberto Cardillo, Robert Moss
2015 Proceedings of the 10th International Conference on Computer Vision Theory and Applications  
Having observed that the MIR-Flickr 1M image set contains a significant number of near-duplicate images, we have discovered the majority of these.  ...  2015) Identification of MIR-Flickr nearduplicate images : a benchmark collection for near-duplicate detection.  ...  ACKNOWLEDGEMENTS We would like to acknowledge help and advice from Mark Huiskes of Leiden University and Kenneth Pollock of North Carolina State University, for sharing their knowledge about the MIR-Flickr  ... 
doi:10.5220/0005359705650571 dblp:conf/visapp/ConnorMCM15 fatcat:23dpyamsafh4bpjrfkvzbeshme

Latent Factors of Visual Popularity Prediction

Spencer Cappallo, Thomas Mensink, Cees G.M. Snoek
2015 Proceedings of the 5th ACM on International Conference on Multimedia Retrieval - ICMR '15  
Our approach is evaluated on two large-scale datasets consisting of images from the photo-sharing website Flickr; the MIR-1M dataset and the Visual Sentiment Ontology dataset.  ...  The proposed approach yields state of the art results, and allows for insight into the semantics of image popularity on social networks.  ...  Our approach is evaluated on two large-scale datasets consisting of images from the photo-sharing website Flickr; the MIR-1M dataset and the Visual Sentiment Ontology dataset.  ... 
doi:10.1145/2671188.2749405 dblp:conf/mir/CappalloMS15 fatcat:tbmjftw3hrhxtgb66g42lfqpry

Deep Multi-Modal Metric Learning with Multi-Scale Correlation for Image-Text Retrieval

Yan Hua, Yingyun Yang, Jianhe Du
2020 Electronics  
Experiments validate the effectiveness of our proposed method on multi-modal retrieval tasks, and our method outperforms state-of-the-art methods on NUS-WIDE, MIR Flickr, and Wikipedia datasets.  ...  can be compared directly; thus, inter-modal retrieval can be achieved by the nearest neighboring search.  ...  Take the retrieval results on MIR Flickr in Figure 8 as example.  ... 
doi:10.3390/electronics9030466 fatcat:32bdzztgx5g3vbrrxutyfebufq

Dynamic Multi-View Hashing for Online Image Retrieval

Liang Xie, Jialie Shen, Jungong Han, Lei Zhu, Ling Shao
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
Advanced hashing technique is essential to facilitate effective large scale online image organization and retrieval, where image contents could be frequently changed.  ...  It can increase the code length when current code is not able to represent new images effectively.  ...  Similar to MIR Flickr, on NUS-WIDE we evaluate the MAP scores at different sizes, the best code length of compared methods is set to 128 bits.  ... 
doi:10.24963/ijcai.2017/437 dblp:conf/ijcai/XieSHZS17 fatcat:ctaisylrxnhihgrln4kdvgmyrm
« Previous Showing results 1 — 15 out of 404 results