Matches in SemOpenAlex for { <https://semopenalex.org/work/W1965536286> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W1965536286 abstract "Visual learning with weak supervision is a promising research area, since it offers the possibility to build large image datasets at reasonable cost. In this paper, we address the problem of weakly supervised object detection, where the goal is to predict the label of the image using object position as latent variable. We propose a new method that builds upon the Latent Structural SVM (LSSVM) formalism. Specifically, we introduce an original coarse-to-fine approach that limits the evolution of the latent parameter subspace. This incremental strategy drives the learning towards better solutions, providing a model with increased predictive accuracy. In addition, this leads to a significant speed up during learning and inference compared to standard sliding window methods. Experiments carried out on Mammal dataset validate the good performances and fast training of the method compared to state-of-the-art works." @default.
- W1965536286 created "2016-06-24" @default.
- W1965536286 creator A5002574498 @default.
- W1965536286 creator A5017490804 @default.
- W1965536286 creator A5022871131 @default.
- W1965536286 creator A5067565254 @default.
- W1965536286 date "2014-10-01" @default.
- W1965536286 modified "2023-10-06" @default.
- W1965536286 title "Incremental learning of latent structural SVM for weakly supervised image classification" @default.
- W1965536286 cites W1603728330 @default.
- W1965536286 cites W1978493028 @default.
- W1965536286 cites W1985012902 @default.
- W1965536286 cites W1991378610 @default.
- W1965536286 cites W2031248101 @default.
- W1965536286 cites W2066941820 @default.
- W1965536286 cites W2087164515 @default.
- W1965536286 cites W2099528205 @default.
- W1965536286 cites W2117103983 @default.
- W1965536286 cites W2131846894 @default.
- W1965536286 cites W2132984949 @default.
- W1965536286 cites W2144982973 @default.
- W1965536286 cites W2147196093 @default.
- W1965536286 cites W2147238549 @default.
- W1965536286 cites W2152617463 @default.
- W1965536286 cites W2162915993 @default.
- W1965536286 cites W2163605009 @default.
- W1965536286 cites W2166765763 @default.
- W1965536286 cites W2167912153 @default.
- W1965536286 cites W2168356304 @default.
- W1965536286 cites W2169177311 @default.
- W1965536286 cites W2171822841 @default.
- W1965536286 cites W2296073425 @default.
- W1965536286 cites W25195181 @default.
- W1965536286 doi "https://doi.org/10.1109/icip.2014.7025862" @default.
- W1965536286 hasPublicationYear "2014" @default.
- W1965536286 type Work @default.
- W1965536286 sameAs 1965536286 @default.
- W1965536286 citedByCount "5" @default.
- W1965536286 countsByYear W19655362862015 @default.
- W1965536286 countsByYear W19655362862016 @default.
- W1965536286 crossrefType "proceedings-article" @default.
- W1965536286 hasAuthorship W1965536286A5002574498 @default.
- W1965536286 hasAuthorship W1965536286A5017490804 @default.
- W1965536286 hasAuthorship W1965536286A5022871131 @default.
- W1965536286 hasAuthorship W1965536286A5067565254 @default.
- W1965536286 hasConcept C115961682 @default.
- W1965536286 hasConcept C119857082 @default.
- W1965536286 hasConcept C12267149 @default.
- W1965536286 hasConcept C153180895 @default.
- W1965536286 hasConcept C154945302 @default.
- W1965536286 hasConcept C2776214188 @default.
- W1965536286 hasConcept C32834561 @default.
- W1965536286 hasConcept C41008148 @default.
- W1965536286 hasConcept C51167844 @default.
- W1965536286 hasConcept C75294576 @default.
- W1965536286 hasConceptScore W1965536286C115961682 @default.
- W1965536286 hasConceptScore W1965536286C119857082 @default.
- W1965536286 hasConceptScore W1965536286C12267149 @default.
- W1965536286 hasConceptScore W1965536286C153180895 @default.
- W1965536286 hasConceptScore W1965536286C154945302 @default.
- W1965536286 hasConceptScore W1965536286C2776214188 @default.
- W1965536286 hasConceptScore W1965536286C32834561 @default.
- W1965536286 hasConceptScore W1965536286C41008148 @default.
- W1965536286 hasConceptScore W1965536286C51167844 @default.
- W1965536286 hasConceptScore W1965536286C75294576 @default.
- W1965536286 hasLocation W19655362861 @default.
- W1965536286 hasLocation W19655362862 @default.
- W1965536286 hasLocation W19655362863 @default.
- W1965536286 hasOpenAccess W1965536286 @default.
- W1965536286 hasPrimaryLocation W19655362861 @default.
- W1965536286 hasRelatedWork W1120847856 @default.
- W1965536286 hasRelatedWork W1799971747 @default.
- W1965536286 hasRelatedWork W1861706286 @default.
- W1965536286 hasRelatedWork W1980381208 @default.
- W1965536286 hasRelatedWork W2147442033 @default.
- W1965536286 hasRelatedWork W2149583853 @default.
- W1965536286 hasRelatedWork W2167092671 @default.
- W1965536286 hasRelatedWork W2219338811 @default.
- W1965536286 hasRelatedWork W2364594919 @default.
- W1965536286 hasRelatedWork W4293472652 @default.
- W1965536286 isParatext "false" @default.
- W1965536286 isRetracted "false" @default.
- W1965536286 magId "1965536286" @default.
- W1965536286 workType "article" @default.