Matches in SemOpenAlex for { <https://semopenalex.org/work/W1969700546> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W1969700546 abstract "We propose a new framework for image recognition by selectively pooling local visual descriptors, and show its superior discriminative power on fine-grained image classification tasks. The representation is based on selecting the most confident local descriptors for nonlinear function learning using a linear approximation in an embedded higher dimensional space. The advantage of our Selective Pooling Vector over the previous state-of-the-art Super Vector and Fisher Vector representations, is that it ensures a more accurate learning function, which proves to be important for classifying details in fine-grained image recognition. Our experimental results corroborate this claim: with a simple linear SVM as the classifier, the selective pooling vector achieves significant performance gains on standard benchmark datasets for various fine-grained tasks such as the CMU Multi-PIE dataset for face recognition, the Caltech-UCSD Bird dataset and the Stanford Dogs dataset for fine-grained object categorization. On all datasets we outperform the state of the arts and boost the recognition rates to 96.4%, 48.9%, 52.0% respectively." @default.
- W1969700546 created "2016-06-24" @default.
- W1969700546 creator A5003681868 @default.
- W1969700546 creator A5022951785 @default.
- W1969700546 creator A5023292508 @default.
- W1969700546 creator A5024777042 @default.
- W1969700546 creator A5038815767 @default.
- W1969700546 creator A5063499488 @default.
- W1969700546 date "2015-01-01" @default.
- W1969700546 modified "2023-10-16" @default.
- W1969700546 title "Selective Pooling Vector for Fine-Grained Recognition" @default.
- W1969700546 cites W1966385142 @default.
- W1969700546 cites W1972715665 @default.
- W1969700546 cites W1994213117 @default.
- W1969700546 cites W1995543189 @default.
- W1969700546 cites W2012592962 @default.
- W1969700546 cites W2027922120 @default.
- W1969700546 cites W2110015572 @default.
- W1969700546 cites W2118696714 @default.
- W1969700546 cites W2124351162 @default.
- W1969700546 cites W2129812935 @default.
- W1969700546 cites W2135706578 @default.
- W1969700546 cites W2136705357 @default.
- W1969700546 cites W2162762921 @default.
- W1969700546 cites W2162915993 @default.
- W1969700546 cites W2168356304 @default.
- W1969700546 doi "https://doi.org/10.1109/wacv.2015.119" @default.
- W1969700546 hasPublicationYear "2015" @default.
- W1969700546 type Work @default.
- W1969700546 sameAs 1969700546 @default.
- W1969700546 citedByCount "18" @default.
- W1969700546 countsByYear W19697005462015 @default.
- W1969700546 countsByYear W19697005462016 @default.
- W1969700546 countsByYear W19697005462017 @default.
- W1969700546 countsByYear W19697005462018 @default.
- W1969700546 countsByYear W19697005462019 @default.
- W1969700546 countsByYear W19697005462020 @default.
- W1969700546 countsByYear W19697005462022 @default.
- W1969700546 countsByYear W19697005462023 @default.
- W1969700546 crossrefType "proceedings-article" @default.
- W1969700546 hasAuthorship W1969700546A5003681868 @default.
- W1969700546 hasAuthorship W1969700546A5022951785 @default.
- W1969700546 hasAuthorship W1969700546A5023292508 @default.
- W1969700546 hasAuthorship W1969700546A5024777042 @default.
- W1969700546 hasAuthorship W1969700546A5038815767 @default.
- W1969700546 hasAuthorship W1969700546A5063499488 @default.
- W1969700546 hasConcept C115961682 @default.
- W1969700546 hasConcept C119857082 @default.
- W1969700546 hasConcept C12267149 @default.
- W1969700546 hasConcept C13280743 @default.
- W1969700546 hasConcept C153180895 @default.
- W1969700546 hasConcept C154945302 @default.
- W1969700546 hasConcept C185798385 @default.
- W1969700546 hasConcept C205649164 @default.
- W1969700546 hasConcept C41008148 @default.
- W1969700546 hasConcept C52622490 @default.
- W1969700546 hasConcept C64876066 @default.
- W1969700546 hasConcept C70437156 @default.
- W1969700546 hasConcept C75294576 @default.
- W1969700546 hasConcept C95623464 @default.
- W1969700546 hasConcept C97931131 @default.
- W1969700546 hasConceptScore W1969700546C115961682 @default.
- W1969700546 hasConceptScore W1969700546C119857082 @default.
- W1969700546 hasConceptScore W1969700546C12267149 @default.
- W1969700546 hasConceptScore W1969700546C13280743 @default.
- W1969700546 hasConceptScore W1969700546C153180895 @default.
- W1969700546 hasConceptScore W1969700546C154945302 @default.
- W1969700546 hasConceptScore W1969700546C185798385 @default.
- W1969700546 hasConceptScore W1969700546C205649164 @default.
- W1969700546 hasConceptScore W1969700546C41008148 @default.
- W1969700546 hasConceptScore W1969700546C52622490 @default.
- W1969700546 hasConceptScore W1969700546C64876066 @default.
- W1969700546 hasConceptScore W1969700546C70437156 @default.
- W1969700546 hasConceptScore W1969700546C75294576 @default.
- W1969700546 hasConceptScore W1969700546C95623464 @default.
- W1969700546 hasConceptScore W1969700546C97931131 @default.
- W1969700546 hasLocation W19697005461 @default.
- W1969700546 hasOpenAccess W1969700546 @default.
- W1969700546 hasPrimaryLocation W19697005461 @default.
- W1969700546 hasRelatedWork W1835905048 @default.
- W1969700546 hasRelatedWork W2041636156 @default.
- W1969700546 hasRelatedWork W2112343299 @default.
- W1969700546 hasRelatedWork W2126384842 @default.
- W1969700546 hasRelatedWork W2291847203 @default.
- W1969700546 hasRelatedWork W2514274290 @default.
- W1969700546 hasRelatedWork W2547591540 @default.
- W1969700546 hasRelatedWork W2807311372 @default.
- W1969700546 hasRelatedWork W2905846897 @default.
- W1969700546 hasRelatedWork W4200301313 @default.
- W1969700546 isParatext "false" @default.
- W1969700546 isRetracted "false" @default.
- W1969700546 magId "1969700546" @default.
- W1969700546 workType "article" @default.