Matches in SemOpenAlex for { <https://semopenalex.org/work/W2026188082> ?p ?o ?g. }
- W2026188082 abstract "Bag-of-Feature (BoF) representations and spatial constraints have been popular in image classification research. One of the most successful methods uses sparse coding and spatial pooling to build discriminative features. However, minimizing the reconstruction error by sparse coding only considers the similarity between the input and codebooks. In contrast, this paper describes a novel feature learning approach for image classification by considering the dissimilarity between inputs and prototype images, or what we called reference basis (RB). First, we learn the feature representation by max-margin criterion between the input and the RB. The learned hyperplane is stored as the relative feature. Second, we propose an adaptive pooling technique to assemble multiple relative features generated by different RBs under the SVM framework, where the classifier and the pooling weights are jointly learned. Experiments based on three challenging datasets: Caltech-101, Scene 15 and Willow-Actions, demonstrate the effectiveness and generality of our framework." @default.
- W2026188082 created "2016-06-24" @default.
- W2026188082 creator A5001819736 @default.
- W2026188082 creator A5005819096 @default.
- W2026188082 creator A5008831111 @default.
- W2026188082 creator A5026512168 @default.
- W2026188082 creator A5028762600 @default.
- W2026188082 creator A5065250332 @default.
- W2026188082 date "2014-07-01" @default.
- W2026188082 modified "2023-09-24" @default.
- W2026188082 title "Learning relative features through adaptive pooling for image classification" @default.
- W2026188082 cites W1652450286 @default.
- W2026188082 cites W2001519147 @default.
- W2026188082 cites W2017814585 @default.
- W2026188082 cites W2027922120 @default.
- W2026188082 cites W2036054070 @default.
- W2026188082 cites W2054653913 @default.
- W2026188082 cites W2062671023 @default.
- W2026188082 cites W2097018403 @default.
- W2026188082 cites W2097622337 @default.
- W2026188082 cites W2100295890 @default.
- W2026188082 cites W2103519186 @default.
- W2026188082 cites W2104978738 @default.
- W2026188082 cites W2105464873 @default.
- W2026188082 cites W2107034620 @default.
- W2026188082 cites W2109449402 @default.
- W2026188082 cites W2112447569 @default.
- W2026188082 cites W2116360511 @default.
- W2026188082 cites W2129933262 @default.
- W2026188082 cites W2134789674 @default.
- W2026188082 cites W2139212933 @default.
- W2026188082 cites W2139338362 @default.
- W2026188082 cites W2150409012 @default.
- W2026188082 cites W2151408393 @default.
- W2026188082 cites W2158234032 @default.
- W2026188082 cites W2162915993 @default.
- W2026188082 cites W2162931300 @default.
- W2026188082 cites W2170608400 @default.
- W2026188082 cites W2171149816 @default.
- W2026188082 doi "https://doi.org/10.1109/icme.2014.6890269" @default.
- W2026188082 hasPublicationYear "2014" @default.
- W2026188082 type Work @default.
- W2026188082 sameAs 2026188082 @default.
- W2026188082 citedByCount "8" @default.
- W2026188082 countsByYear W20261880822015 @default.
- W2026188082 countsByYear W20261880822016 @default.
- W2026188082 countsByYear W20261880822017 @default.
- W2026188082 countsByYear W20261880822018 @default.
- W2026188082 countsByYear W20261880822023 @default.
- W2026188082 crossrefType "proceedings-article" @default.
- W2026188082 hasAuthorship W2026188082A5001819736 @default.
- W2026188082 hasAuthorship W2026188082A5005819096 @default.
- W2026188082 hasAuthorship W2026188082A5008831111 @default.
- W2026188082 hasAuthorship W2026188082A5026512168 @default.
- W2026188082 hasAuthorship W2026188082A5028762600 @default.
- W2026188082 hasAuthorship W2026188082A5065250332 @default.
- W2026188082 hasBestOaLocation W20261880822 @default.
- W2026188082 hasConcept C115961682 @default.
- W2026188082 hasConcept C119857082 @default.
- W2026188082 hasConcept C12267149 @default.
- W2026188082 hasConcept C138885662 @default.
- W2026188082 hasConcept C153180895 @default.
- W2026188082 hasConcept C154945302 @default.
- W2026188082 hasConcept C15744967 @default.
- W2026188082 hasConcept C2524010 @default.
- W2026188082 hasConcept C2776401178 @default.
- W2026188082 hasConcept C2780767217 @default.
- W2026188082 hasConcept C33923547 @default.
- W2026188082 hasConcept C41008148 @default.
- W2026188082 hasConcept C41895202 @default.
- W2026188082 hasConcept C52622490 @default.
- W2026188082 hasConcept C542102704 @default.
- W2026188082 hasConcept C68693459 @default.
- W2026188082 hasConcept C70437156 @default.
- W2026188082 hasConcept C75294576 @default.
- W2026188082 hasConcept C95623464 @default.
- W2026188082 hasConcept C97931131 @default.
- W2026188082 hasConceptScore W2026188082C115961682 @default.
- W2026188082 hasConceptScore W2026188082C119857082 @default.
- W2026188082 hasConceptScore W2026188082C12267149 @default.
- W2026188082 hasConceptScore W2026188082C138885662 @default.
- W2026188082 hasConceptScore W2026188082C153180895 @default.
- W2026188082 hasConceptScore W2026188082C154945302 @default.
- W2026188082 hasConceptScore W2026188082C15744967 @default.
- W2026188082 hasConceptScore W2026188082C2524010 @default.
- W2026188082 hasConceptScore W2026188082C2776401178 @default.
- W2026188082 hasConceptScore W2026188082C2780767217 @default.
- W2026188082 hasConceptScore W2026188082C33923547 @default.
- W2026188082 hasConceptScore W2026188082C41008148 @default.
- W2026188082 hasConceptScore W2026188082C41895202 @default.
- W2026188082 hasConceptScore W2026188082C52622490 @default.
- W2026188082 hasConceptScore W2026188082C542102704 @default.
- W2026188082 hasConceptScore W2026188082C68693459 @default.
- W2026188082 hasConceptScore W2026188082C70437156 @default.
- W2026188082 hasConceptScore W2026188082C75294576 @default.
- W2026188082 hasConceptScore W2026188082C95623464 @default.
- W2026188082 hasConceptScore W2026188082C97931131 @default.
- W2026188082 hasLocation W20261880821 @default.
- W2026188082 hasLocation W20261880822 @default.
- W2026188082 hasOpenAccess W2026188082 @default.