Filters








1,973 Hits in 5.5 sec

Unsupervised auxiliary visual words discovery for large-scale image object retrieval

Yin-Hsi Kuo, Hsuan-Tien Lin, Wen-Huang Cheng, Yi-Hsuan Yang, Winston H. Hsu
2011 CVPR 2011  
The AVWs are automatically discovered by feature propagation and selection in textual and visual image graphs in an unsupervised manner.  ...  Meanwhile, the selection process can also notably reduce the number of features (to 1.4%) and can further facilitate indexing in large-scale image object retrieval.  ...  ., [4] ) to construct the large-scale image graph by MapReduce. To cluster images on the image graph, we apply affinity propagation (AP) [5] for graph-based clustering.  ... 
doi:10.1109/cvpr.2011.5995639 dblp:conf/cvpr/KuoLCYH11 fatcat:22isjgfpancspgtiigczwh2ip4

Affinity Propagation for Class Exemplar Mining [chapter]

Shengping Xia, Rui Song, Edwin R. Hancock
2010 Lecture Notes in Computer Science  
Firstly, we obtain an object specific cluster of graphs using a similarity propagation based graph clustering (SPGC) method.  ...  The popular affinity propagation based clustering algorithm is then individually applied to each object specific cluster.  ...  Similarity Propagation Based Graph Clustering(SPGC) In the text retrieval literature, a standard method for improving performance is query expansion.  ... 
doi:10.1007/978-3-642-14980-1_18 fatcat:lluxbbdkbvazpdfg6qjj3be4ou

Unsupervised Semantic Feature Discovery for Image Object Retrieval and Tag Refinement

Yin-Hsi Kuo, Wen-Huang Cheng, Hsuan-Tien Lin, Winston H. Hsu
2012 IEEE transactions on multimedia  
Index Terms-Image graph, image object retrieval, semantic feature discovery, tag refinement. Taiwan.  ...  The proposed framework can be directly applied to various applications, such as keyword-based image search, image object retrieval, and tag refinement.  ...  To cluster images on the image graph, we apply affinity propagation (AP) [28] for graph-based clustering.  ... 
doi:10.1109/tmm.2012.2190386 fatcat:midugvtgbfefzgmewb5soaesda

A Scalable Graph-Based Semi-Supervised Ranking System for Content-Based Image Retrieval

Xiaojun Qi, Ran Chang
2013 International Journal of Multimedia Data Engineering and Management  
The authors propose a scalable graph-based semi-supervised ranking system for image retrieval.  ...  An asymmetric relevance vector is created for each second layer graph by propagating initial scores from the first layer.  ...  CONCLUSION AND FUTURE WORK We propose a novel scalable graph-based semi-supervised ranking system for image retrieval.  ... 
doi:10.4018/ijmdem.2013100102 fatcat:c4b76naaejhyhcwxghskmk7lte

Local similarity learning for pairwise constraint propagation

Zhenyong Fu, Zhiwu Lu, Horace H. S. Ip, Hongtao Lu, Yunyun Wang
2014 Multimedia tools and applications  
Effective propagation algorithms have previously been designed based on the graph-based semi-supervised learning framework.  ...  Pairwise constraint propagation studies the problem of propagating the scarce pairwise constraints across the entire dataset.  ...  and the source are credited.  ... 
doi:10.1007/s11042-013-1796-y fatcat:ydgaumee7vg6dei3tmcq3wb6vu

Regularized Diffusion Process on Bidirectional Context for Object Retrieval

Song Bai, Xiang Bai, Qi Tian, Longin Jan Latecki
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Consequently, RDP, ARDP and HRDP constitute a generic tool for object retrieval in most commonly-used settings, no matter the input relationships between objects are derived from the same domain or not  ...  , and in pairwise formulation or not.  ...  Xiang Bai by the National Program for Support of Top-notch Young Professionals and the Program for HUST Academic Frontier Youth Team, to Dr.  ... 
doi:10.1109/tpami.2018.2828815 pmid:29993682 fatcat:vtzomm3nvndypdonvkjxelgsby

Scalable Face Track Retrieval in Video Archives Using Bag-of-Faces Sparse Representation

Bor-Chun Chen, Yan-Ying Chen, Yin-Hsi Kuo, Thanh Duc Ngo, Duy-Dinh Le, Shin'ichi Satoh, Winston H. Hsu
2017 IEEE transactions on circuits and systems for video technology (Print)  
between performance and retrieval time.  ...  Using the proposed method, a face track is encoded as a single bag-of-faces sparse representation and therefore allowing efficient indexing method to handle large-scale data.  ...  Once the graph is constructed, finally, propagation algorithm is applied to compute the of people names for clusters by propagating name by cluster similarities from neighboring clusters.  ... 
doi:10.1109/tcsvt.2016.2538520 fatcat:kz5hizoemvc2vellnonmocc44i

Congruency-Based Reranking

Itai Ben-Shalom, Noga Levy, Lior Wolf, Nachum Dershowitz, Adiel Ben-Shalom, Roni Shweka, Yaacov Choueka, Tamir Hazan, Yaniv Bar
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
We present a tool for re-ranking the results of a specific query by considering the (n+1)×(n+1) matrix of pairwise similarities among the elements of the set of n retrieved results and the query itself  ...  The tool is based on graphical Bayesian models, which reinforce retrieved items strongly linked to other retrievals, and on repeated clustering to measure the stability of the obtained associations.  ...  The prior probabilities of the l ij variables are derived from the pairwise handwriting-based image similarity of i and j, and are expressed by the pairwise models γ ij (l ij ).  ... 
doi:10.1109/cvpr.2014.270 dblp:conf/cvpr/Ben-ShalomLWDBSCHB14 fatcat:prmbvndp5fhblgacbpshebxnu4

Active Congruency-Based Reranking

Itai Ben Shalom, Noga Levy, Lior Wolf, Nachum Dershowitz, Adiel Ben Shalom, Roni Shweka, Yaacov Choueka, Tamir Hazan, Yaniv Bar
2016 Frontiers in Digital Humanities  
We present a tool for re-ranking the results of a specific query by considering the matrix of pairwise similarities among the elements of the set of retrieved results and the query itself.  ...  The tool is based on graphical Bayesian models, which reinforce retrieved items strongly linked to other retrievals, and on repeated clustering to measure the stability of the obtained associations.  ...  The prior probabilities of the l ij variables are derived from the pairwise handwriting-based 130 image similarity of i and j, and are expressed by the pairwise models γ ij (l ij ).  ... 
doi:10.3389/fdigh.2016.00007 fatcat:imaybbxhhrf6hcl2gqqn7velee

Re-ranking by Multi-feature Fusion with Diffusion for Image Retrieval

Fan Yang, Bogdan Matei, Larry S. Davis
2015 2015 IEEE Winter Conference on Applications of Computer Vision  
In addition, we utilize a probabilistic model based on the statistics of similarity scores of similar and dissimilar image pairs to determine the weight for each graph.  ...  We present a re-ranking algorithm for image retrieval by fusing multi-feature information. We utilize pairwise similarity scores between images to exploit the underlying relationships among images.  ...  For each feature, given the query and initially retrieved images, we construct an undirected graph whose vertices represent these images and in which edge strength is the pairwise similarity score between  ... 
doi:10.1109/wacv.2015.82 dblp:conf/wacv/YangMD15 fatcat:fk7gfojn5bg7to2rlhtxkm5dfm

Google based name search: Resolving mixed entities on the web

Byung-Won On, Ingyu Lee
2009 2009 Fourth International Conference on Digital Information Management  
In particular, since the correct number of clusters is often unknown, we study a state-of-the-art unsupervised clustering solution based on propagation of pairwise similarities of entities.  ...  For development of such a system, we propose a web service based interface, an unsupervised clustering scheme, and cluster ranking algorithms.  ...  On et al. introduced multilevel graph partitioning scheme to address the scalable issue of name disambiguation problem on both bibliographic and information retrieval domains [10] .  ... 
doi:10.1109/icdim.2009.5356763 dblp:conf/icdim/OnL09 fatcat:62s2p4e7ebelpbzvjknnl5l3li

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Scenes Shape-based Similarity Retrieval of Doppler Images for Clinical Decision Support Türetken, Engin Delineating Trees in Noisy 2D Images and 3D Image-Stacks Turk, Matthew Workshop: Location-based  ...  Affinities for Spectral Segmentation Authority-Shift Clustering: Hierarchical Clustering by Authority Seeking on Graphs Unsupervised Detection and Segmentation of Identical Objects Nonparametric  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Community Detection in Multiplex Networks [article]

Matteo Magnani, Obaida Hanteer, Roberto Interdonato, Luca Rossi, Andrea Tagarelli
2021 arXiv   pre-print
community structures and to what extent the evaluated methods are scalable.  ...  We characterize the different algorithms based on various properties and we discuss the type of communities detected by each method.  ...  Figure 16 reports on the results of pairwise analysis among Pillar Equal Partitioning and Semi-Pillar Non-equal Partitioning, with Omega index values for the pairwise similarities.  ... 
arXiv:1910.07646v3 fatcat:vxfxgpohurg4pf4tgr57cmljcm

Web-Scale Responsive Visual Search at Bing [article]

Houdong Hu, Yan Wang, Linjun Yang, Pavel Komlev, Li Huang, Xi Chen, Jiapei Huang, Ye Wu, Meenaz Merchant, Arun Sacheti
2018 arXiv   pre-print
The system accommodates tens of billions of images in the index, with thousands of features for each image, and can respond in less than 200 ms.  ...  In order to overcome the challenges in relevance, latency, and scalability in such large scale of data, we employ a cascaded learning-to-rank framework based on various latest deep learning visual features  ...  Image retrieval: The heavy lifting happens in the image retrieval module, which retrieves visually similar images based on the extracted features and intents.  ... 
arXiv:1802.04914v2 fatcat:unw36qpu7fdcjg46tnuvj4xtje

Spectral Clustering and Vantage Point Indexing for Efficient Data Retrieval

Pushpalatha R., K. Meenakshi Sundaram
2018 International Journal of Electrical and Computer Engineering (IJECE)  
The technique clusters and indexes the densely populated high dimensional data points for effective data retrieval based on user query.  ...  In order to overcome the limitation, Spectral Clustering Based VP Tree Indexing Technique is introduced.  ...  Spectral Clustering is to form a pairwise similarity matrix "S", compute Laplacian matrix "L" and eigenvectors of "L".  ... 
doi:10.11591/ijece.v8i4.pp2261-2271 fatcat:tcallsen7fdknfd2ohqedjw4t4
« Previous Showing results 1 — 15 out of 1,973 results