Matches in SemOpenAlex for { <https://semopenalex.org/work/W2773723772> ?p ?o ?g. }
- W2773723772 abstract "Abstract Approaches based on scene parts are deemed to be one of the main streams for scene categorization. In previous methods, before one can utilize scene parts, models need to be constructed for them first. The quality of part models has a great influence on the final results. However, building high-quality scene part models is still an open question. To perform scene categorization based on parts effectively, in this paper we propose to explore scene part information without constructing explicit models for them. For this purpose, a cascading framework is used, at each of whose stages we aim to process image patches potentially corresponding to scene parts from different perspectives. Specifically, the first stage of the framework uses the selective search algorithm to extract possible object patches from images and represents obtained patches based on convolutional neural networks. Then, spectral clustering and linear support vector machines are adopted to select representative visual patterns for images in the second stage. In the third stage, random forest and multi-class support vector machines are combined to mine and classify image features for determining the categories of the images. Through using the cascading framework, we can explore scene part information step by step without needing to construct explicit models for them. Finally, extensive experiments are conducted to evaluate the proposed method on three well-known benchmark scene datasets, i.e. MIT Indoor 67, SUN397 and Places. Experiment results demonstrated the effectiveness of the proposed method." @default.
- W2773723772 created "2017-12-22" @default.
- W2773723772 creator A5024075471 @default.
- W2773723772 creator A5082604086 @default.
- W2773723772 date "2018-03-01" @default.
- W2773723772 modified "2023-09-24" @default.
- W2773723772 title "Categorizing scenes by exploring scene part information without constructing explicit models" @default.
- W2773723772 cites W12634471 @default.
- W2773723772 cites W1423339008 @default.
- W2773723772 cites W1524680991 @default.
- W2773723772 cites W1924160326 @default.
- W2773723772 cites W1966385142 @default.
- W2773723772 cites W1989684337 @default.
- W2773723772 cites W1998294030 @default.
- W2773723772 cites W1999478155 @default.
- W2773723772 cites W2017814585 @default.
- W2773723772 cites W2022508996 @default.
- W2773723772 cites W2027922120 @default.
- W2773723772 cites W2033832873 @default.
- W2773723772 cites W2034489756 @default.
- W2773723772 cites W2048852482 @default.
- W2773723772 cites W2070792803 @default.
- W2773723772 cites W2084435358 @default.
- W2773723772 cites W2087164515 @default.
- W2773723772 cites W2088049833 @default.
- W2773723772 cites W2090042335 @default.
- W2773723772 cites W2094618318 @default.
- W2773723772 cites W2098411764 @default.
- W2773723772 cites W2099528205 @default.
- W2773723772 cites W2104825706 @default.
- W2773723772 cites W2107698128 @default.
- W2773723772 cites W2108598243 @default.
- W2773723772 cites W2112796928 @default.
- W2773723772 cites W2115628259 @default.
- W2773723772 cites W2118585731 @default.
- W2773723772 cites W2119853387 @default.
- W2773723772 cites W2121947440 @default.
- W2773723772 cites W2126337883 @default.
- W2773723772 cites W2132914434 @default.
- W2773723772 cites W2133014420 @default.
- W2773723772 cites W2134670479 @default.
- W2773723772 cites W2135674549 @default.
- W2773723772 cites W2139427956 @default.
- W2773723772 cites W2147800946 @default.
- W2773723772 cites W2152161678 @default.
- W2773723772 cites W2155541015 @default.
- W2773723772 cites W2160815625 @default.
- W2773723772 cites W2161969291 @default.
- W2773723772 cites W2162915993 @default.
- W2773723772 cites W2163605009 @default.
- W2773723772 cites W2167828171 @default.
- W2773723772 cites W2168356304 @default.
- W2773723772 cites W2169177311 @default.
- W2773723772 cites W2531044305 @default.
- W2773723772 cites W280294731 @default.
- W2773723772 cites W2911964244 @default.
- W2773723772 cites W2950502861 @default.
- W2773723772 cites W2951702175 @default.
- W2773723772 cites W2953391683 @default.
- W2773723772 cites W3147600416 @default.
- W2773723772 doi "https://doi.org/10.1016/j.neucom.2017.12.003" @default.
- W2773723772 hasPublicationYear "2018" @default.
- W2773723772 type Work @default.
- W2773723772 sameAs 2773723772 @default.
- W2773723772 citedByCount "2" @default.
- W2773723772 countsByYear W27737237722019 @default.
- W2773723772 countsByYear W27737237722021 @default.
- W2773723772 crossrefType "journal-article" @default.
- W2773723772 hasAuthorship W2773723772A5024075471 @default.
- W2773723772 hasAuthorship W2773723772A5082604086 @default.
- W2773723772 hasConcept C111919701 @default.
- W2773723772 hasConcept C115961682 @default.
- W2773723772 hasConcept C119857082 @default.
- W2773723772 hasConcept C12267149 @default.
- W2773723772 hasConcept C13280743 @default.
- W2773723772 hasConcept C153180895 @default.
- W2773723772 hasConcept C154945302 @default.
- W2773723772 hasConcept C169760540 @default.
- W2773723772 hasConcept C185798385 @default.
- W2773723772 hasConcept C197654239 @default.
- W2773723772 hasConcept C199360897 @default.
- W2773723772 hasConcept C205649164 @default.
- W2773723772 hasConcept C26760741 @default.
- W2773723772 hasConcept C2777212361 @default.
- W2773723772 hasConcept C2780801425 @default.
- W2773723772 hasConcept C2781238097 @default.
- W2773723772 hasConcept C31972630 @default.
- W2773723772 hasConcept C41008148 @default.
- W2773723772 hasConcept C73555534 @default.
- W2773723772 hasConcept C81363708 @default.
- W2773723772 hasConcept C86803240 @default.
- W2773723772 hasConcept C94124525 @default.
- W2773723772 hasConcept C98045186 @default.
- W2773723772 hasConceptScore W2773723772C111919701 @default.
- W2773723772 hasConceptScore W2773723772C115961682 @default.
- W2773723772 hasConceptScore W2773723772C119857082 @default.
- W2773723772 hasConceptScore W2773723772C12267149 @default.
- W2773723772 hasConceptScore W2773723772C13280743 @default.
- W2773723772 hasConceptScore W2773723772C153180895 @default.
- W2773723772 hasConceptScore W2773723772C154945302 @default.