FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2804574209> ?p ?o ?g. }

• W2804574209 abstract "Motivated by the recent success of supervised and weakly supervised common object discovery, in this paper, we move forward one step further to tackle common object discovery in a fully unsupervised way. Generally, object co-localization aims at simultaneously localizing objects of the same class across a group of images. Traditional object localization/detection usually trains specific object detectors which require bounding box annotations of object instances, or at least image-level labels to indicate the presence/absence of objects in an image. Given a collection of images without any annotations, our proposed fully unsupervised method is to simultaneously discover images that contain common objects and also localize common objects in corresponding images. Without requiring to know the total number of common objects, we formulate this unsupervised object discovery as a sub-graph mining problem from a weighted graph of object proposals, where nodes correspond to object proposals, and edges represent the similarities between neighbouring proposals. The positive images and common objects are jointly discovered by finding sub-graphs of strongly connected nodes, with each sub-graph capturing one object pattern. The optimization problem can be efficiently solved by our proposed maximal-flow-based algorithm. Instead of assuming that each image contains only one common object, our proposed solution can better address wild images where each image may contain multiple common objects or even no common object. Moreover, our proposed method can be easily tailored to the task of image retrieval in which the nodes correspond to the similarity between query and reference images. Extensive experiments on PASCAL VOC 2007 and Object Discovery data sets demonstrate that even without any supervision, our approach can discover/localize common objects of various classes in the presence of scale, view point, appearance variation, and partial occlusions. We also conduct broad experiments on image retrieval benchmarks, Holidays and Oxford5k data sets, to show that our proposed method, which considers both the similarity between query and reference images and also similarities among reference images, can help to improve the retrieval results significantly." @default.
• W2804574209 created "2018-06-01" @default.
• W2804574209 creator A5075444205 @default.
• W2804574209 creator A5085245110 @default.
• W2804574209 date "2018-09-01" @default.
• W2804574209 modified "2023-09-24" @default.
• W2804574209 title "Simultaneously Discovering and Localizing Common Objects in Wild Images" @default.
• W2804574209 cites W1556531089 @default.
• W2804574209 cites W1575299770 @default.
• W2804574209 cites W1578066333 @default.
• W2804574209 cites W1590510366 @default.
• W2804574209 cites W1903797731 @default.
• W2804574209 cites W1919709169 @default.
• W2804574209 cites W1924929788 @default.
• W2804574209 cites W1925596459 @default.
• W2804574209 cites W1952794764 @default.
• W2804574209 cites W1963920598 @default.
• W2804574209 cites W1966229885 @default.
• W2804574209 cites W1970899458 @default.
• W2804574209 cites W1984034752 @default.
• W2804574209 cites W1996140089 @default.
• W2804574209 cites W2016016818 @default.
• W2804574209 cites W2020477327 @default.
• W2804574209 cites W2025360228 @default.
• W2804574209 cites W2043521128 @default.
• W2804574209 cites W2061629163 @default.
• W2804574209 cites W2062118960 @default.
• W2804574209 cites W2071486728 @default.
• W2804574209 cites W2086052791 @default.
• W2804574209 cites W2090359754 @default.
• W2804574209 cites W2095840396 @default.
• W2804574209 cites W2097482646 @default.
• W2804574209 cites W2099528205 @default.
• W2804574209 cites W2112301665 @default.
• W2804574209 cites W2113137767 @default.
• W2804574209 cites W2116946038 @default.
• W2804574209 cites W2117573774 @default.
• W2804574209 cites W2141362318 @default.
• W2804574209 cites W2163605009 @default.
• W2804574209 cites W2165835468 @default.
• W2804574209 cites W2170969455 @default.
• W2804574209 cites W2171240872 @default.
• W2804574209 cites W2171322814 @default.
• W2804574209 cites W2179042386 @default.
• W2804574209 cites W2179146407 @default.
• W2804574209 cites W2204975001 @default.
• W2804574209 cites W2211996548 @default.
• W2804574209 cites W2214871046 @default.
• W2804574209 cites W2220111505 @default.
• W2804574209 cites W2298532145 @default.
• W2804574209 cites W2441255125 @default.
• W2804574209 cites W2471206083 @default.
• W2804574209 cites W2519284461 @default.
• W2804574209 cites W2567687466 @default.
• W2804574209 cites W2604390606 @default.
• W2804574209 cites W2606831796 @default.
• W2804574209 cites W2666251054 @default.
• W2804574209 cites W2728817152 @default.
• W2804574209 cites W2963125676 @default.
• W2804574209 cites W2963166708 @default.
• W2804574209 cites W2963542991 @default.
• W2804574209 cites W2963603913 @default.
• W2804574209 cites W2963934231 @default.
• W2804574209 cites W318792885 @default.
• W2804574209 cites W7746136 @default.
• W2804574209 cites W88469699 @default.
• W2804574209 doi "https://doi.org/10.1109/tip.2018.2839901" @default.
• W2804574209 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29897875" @default.
• W2804574209 hasPublicationYear "2018" @default.
• W2804574209 type Work @default.
• W2804574209 sameAs 2804574209 @default.
• W2804574209 citedByCount "9" @default.
• W2804574209 countsByYear W28045742092019 @default.
• W2804574209 countsByYear W28045742092020 @default.
• W2804574209 countsByYear W28045742092021 @default.
• W2804574209 countsByYear W28045742092022 @default.
• W2804574209 crossrefType "journal-article" @default.
• W2804574209 hasAuthorship W2804574209A5075444205 @default.
• W2804574209 hasAuthorship W2804574209A5085245110 @default.
• W2804574209 hasConcept C115961682 @default.
• W2804574209 hasConcept C132525143 @default.
• W2804574209 hasConcept C147037132 @default.
• W2804574209 hasConcept C153180895 @default.
• W2804574209 hasConcept C154945302 @default.
• W2804574209 hasConcept C1667742 @default.
• W2804574209 hasConcept C2776151529 @default.
• W2804574209 hasConcept C2781238097 @default.
• W2804574209 hasConcept C31972630 @default.
• W2804574209 hasConcept C41008148 @default.
• W2804574209 hasConcept C63584917 @default.
• W2804574209 hasConcept C80444323 @default.
• W2804574209 hasConceptScore W2804574209C115961682 @default.
• W2804574209 hasConceptScore W2804574209C132525143 @default.
• W2804574209 hasConceptScore W2804574209C147037132 @default.
• W2804574209 hasConceptScore W2804574209C153180895 @default.
• W2804574209 hasConceptScore W2804574209C154945302 @default.
• W2804574209 hasConceptScore W2804574209C1667742 @default.
• W2804574209 hasConceptScore W2804574209C2776151529 @default.
• W2804574209 hasConceptScore W2804574209C2781238097 @default.
• W2804574209 hasConceptScore W2804574209C31972630 @default.

• next