Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289388289> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4289388289 abstract "As deep learning approaches to scene recognition emerge, they have continued to leverage discriminative regions at multiple scales, building on practices established by conventional image classification research. However, approaches remain largely generic, and do not carefully consider the special properties of scenes. In this paper, inspired by the intuitive differences between scenes and objects, we propose Adi-Red, an adaptive approach to discriminative region discovery for scene recognition. Adi-Red uses a CNN classifier, which was pre-trained using only image-level scene labels, to discover discriminative image regions directly. These regions are then used as a source of features to perform scene recognition. The use of the CNN classifier makes it possible to adapt the number of discriminative regions per image using a simple, yet elegant, threshold, at relatively low computational cost. Experimental results on the scene recognition benchmark dataset SUN397 demonstrate the ability of Adi-Red to outperform the state of the art. Additional experimental analysis on the Places dataset reveals the advantages of Adi-Red, and highlight how they are specific to scenes. We attribute the effectiveness of Adi-Red to the ability of adaptive region discovery to avoid introducing noise, while also not missing out on important information." @default.
- W4289388289 created "2022-08-02" @default.
- W4289388289 creator A5056272341 @default.
- W4289388289 creator A5058084433 @default.
- W4289388289 date "2018-10-15" @default.
- W4289388289 modified "2023-10-01" @default.
- W4289388289 title "From Volcano to Toyshop" @default.
- W4289388289 cites W1524680991 @default.
- W4289388289 cites W1566135517 @default.
- W4289388289 cites W1977766639 @default.
- W4289388289 cites W1984309565 @default.
- W4289388289 cites W1991367009 @default.
- W4289388289 cites W1994488211 @default.
- W4289388289 cites W2033832873 @default.
- W4289388289 cites W2048852482 @default.
- W4289388289 cites W2070792803 @default.
- W4289388289 cites W2077069816 @default.
- W4289388289 cites W2088049833 @default.
- W4289388289 cites W2151103935 @default.
- W4289388289 cites W2161969291 @default.
- W4289388289 cites W2162915993 @default.
- W4289388289 cites W2191616647 @default.
- W4289388289 cites W2289772031 @default.
- W4289388289 cites W2295107390 @default.
- W4289388289 cites W2527800741 @default.
- W4289388289 cites W2579549467 @default.
- W4289388289 cites W2602364336 @default.
- W4289388289 cites W2732026016 @default.
- W4289388289 cites W2755125693 @default.
- W4289388289 cites W2766126435 @default.
- W4289388289 cites W3101522362 @default.
- W4289388289 cites W3103844505 @default.
- W4289388289 cites W3104752576 @default.
- W4289388289 cites W99353449 @default.
- W4289388289 doi "https://doi.org/10.1145/3240508.3240698" @default.
- W4289388289 hasPublicationYear "2018" @default.
- W4289388289 type Work @default.
- W4289388289 citedByCount "15" @default.
- W4289388289 countsByYear W42893882892019 @default.
- W4289388289 countsByYear W42893882892020 @default.
- W4289388289 countsByYear W42893882892021 @default.
- W4289388289 countsByYear W42893882892022 @default.
- W4289388289 countsByYear W42893882892023 @default.
- W4289388289 crossrefType "proceedings-article" @default.
- W4289388289 hasAuthorship W4289388289A5056272341 @default.
- W4289388289 hasAuthorship W4289388289A5058084433 @default.
- W4289388289 hasBestOaLocation W42893882892 @default.
- W4289388289 hasConcept C108583219 @default.
- W4289388289 hasConcept C115961682 @default.
- W4289388289 hasConcept C13280743 @default.
- W4289388289 hasConcept C153083717 @default.
- W4289388289 hasConcept C153180895 @default.
- W4289388289 hasConcept C154945302 @default.
- W4289388289 hasConcept C185798385 @default.
- W4289388289 hasConcept C205649164 @default.
- W4289388289 hasConcept C31972630 @default.
- W4289388289 hasConcept C41008148 @default.
- W4289388289 hasConcept C75294576 @default.
- W4289388289 hasConcept C95623464 @default.
- W4289388289 hasConcept C97931131 @default.
- W4289388289 hasConceptScore W4289388289C108583219 @default.
- W4289388289 hasConceptScore W4289388289C115961682 @default.
- W4289388289 hasConceptScore W4289388289C13280743 @default.
- W4289388289 hasConceptScore W4289388289C153083717 @default.
- W4289388289 hasConceptScore W4289388289C153180895 @default.
- W4289388289 hasConceptScore W4289388289C154945302 @default.
- W4289388289 hasConceptScore W4289388289C185798385 @default.
- W4289388289 hasConceptScore W4289388289C205649164 @default.
- W4289388289 hasConceptScore W4289388289C31972630 @default.
- W4289388289 hasConceptScore W4289388289C41008148 @default.
- W4289388289 hasConceptScore W4289388289C75294576 @default.
- W4289388289 hasConceptScore W4289388289C95623464 @default.
- W4289388289 hasConceptScore W4289388289C97931131 @default.
- W4289388289 hasLocation W42893882891 @default.
- W4289388289 hasLocation W42893882892 @default.
- W4289388289 hasLocation W42893882893 @default.
- W4289388289 hasOpenAccess W4289388289 @default.
- W4289388289 hasPrimaryLocation W42893882891 @default.
- W4289388289 hasRelatedWork W2024160000 @default.
- W4289388289 hasRelatedWork W2129933262 @default.
- W4289388289 hasRelatedWork W2563096758 @default.
- W4289388289 hasRelatedWork W2729514902 @default.
- W4289388289 hasRelatedWork W2742991909 @default.
- W4289388289 hasRelatedWork W2773500201 @default.
- W4289388289 hasRelatedWork W2905846897 @default.
- W4289388289 hasRelatedWork W2972035100 @default.
- W4289388289 hasRelatedWork W4288040045 @default.
- W4289388289 hasRelatedWork W2073139667 @default.
- W4289388289 isParatext "false" @default.
- W4289388289 isRetracted "false" @default.
- W4289388289 workType "article" @default.