Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209022602> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3209022602 endingPage "108402" @default.
- W3209022602 startingPage "108402" @default.
- W3209022602 abstract "Scene classification is an important basis for many modern intelligent applications, however the performance of pattern recognition or deep learning-based methods are still not sufficient since complicated structure and context of scene images. In this paper, we propose a novel fusion framework of adaptive nonnegative feature fusion (AdaNFF) for scene classification. The AdaNFF integrates nonnegative matrix factorization, adaptive feature fusion and feature fusion boosting into an end-to-end process. Firstly, feature fusion is known as a general strategy to strengthen weak features, and we observe that pixel values and most hand-craft features of the scene image are naturally nonnegative. Therefore we are motivated to build a fusion method based on nonnegative matrix factorization, which can preserve features nonnegative properties and improve their representation performance. Secondly, with the results of fused single or multiple features fusion, we develop an adaptive feature fusion and boosting algorithm to improve the efficiency of image features. Finally, a normalized l2-norm classifier and a deep-learning like multilayer perceptron (MLP) classifier are trained to predict label of scene image. Under this framework, there are two versions of the proposed feature fusion method for nonnegative single-feature fusion and multi-feature fusion. All methods were validated on scene classification benchmarks. Experiment results suggest that the proposed methods can deal with multi-class scene problems and achieve remarkable classification performance." @default.
- W3209022602 created "2021-11-08" @default.
- W3209022602 creator A5007723033 @default.
- W3209022602 creator A5035252092 @default.
- W3209022602 creator A5075717701 @default.
- W3209022602 date "2022-03-01" @default.
- W3209022602 modified "2023-10-13" @default.
- W3209022602 title "AdaNFF: A new method for adaptive nonnegative multi-feature fusion to scene classification" @default.
- W3209022602 cites W1566135517 @default.
- W3209022602 cites W1902027874 @default.
- W3209022602 cites W2008340903 @default.
- W3209022602 cites W2032699694 @default.
- W3209022602 cites W2097117768 @default.
- W3209022602 cites W2105277784 @default.
- W3209022602 cites W2110096996 @default.
- W3209022602 cites W2134705329 @default.
- W3209022602 cites W2147800946 @default.
- W3209022602 cites W2169383490 @default.
- W3209022602 cites W2222577885 @default.
- W3209022602 cites W2562520146 @default.
- W3209022602 cites W2732026016 @default.
- W3209022602 cites W2755125693 @default.
- W3209022602 cites W2908709000 @default.
- W3209022602 cites W2919115771 @default.
- W3209022602 cites W2930181195 @default.
- W3209022602 cites W2974118232 @default.
- W3209022602 cites W3000312913 @default.
- W3209022602 cites W3102094077 @default.
- W3209022602 cites W4235129407 @default.
- W3209022602 cites W591046810 @default.
- W3209022602 doi "https://doi.org/10.1016/j.patcog.2021.108402" @default.
- W3209022602 hasPublicationYear "2022" @default.
- W3209022602 type Work @default.
- W3209022602 sameAs 3209022602 @default.
- W3209022602 citedByCount "5" @default.
- W3209022602 countsByYear W32090226022022 @default.
- W3209022602 countsByYear W32090226022023 @default.
- W3209022602 crossrefType "journal-article" @default.
- W3209022602 hasAuthorship W3209022602A5007723033 @default.
- W3209022602 hasAuthorship W3209022602A5035252092 @default.
- W3209022602 hasAuthorship W3209022602A5075717701 @default.
- W3209022602 hasConcept C115961682 @default.
- W3209022602 hasConcept C121332964 @default.
- W3209022602 hasConcept C138885662 @default.
- W3209022602 hasConcept C152671427 @default.
- W3209022602 hasConcept C153180895 @default.
- W3209022602 hasConcept C154945302 @default.
- W3209022602 hasConcept C158525013 @default.
- W3209022602 hasConcept C158693339 @default.
- W3209022602 hasConcept C2776401178 @default.
- W3209022602 hasConcept C41008148 @default.
- W3209022602 hasConcept C41895202 @default.
- W3209022602 hasConcept C42355184 @default.
- W3209022602 hasConcept C46686674 @default.
- W3209022602 hasConcept C52622490 @default.
- W3209022602 hasConcept C62520636 @default.
- W3209022602 hasConcept C69744172 @default.
- W3209022602 hasConcept C75294576 @default.
- W3209022602 hasConcept C95623464 @default.
- W3209022602 hasConceptScore W3209022602C115961682 @default.
- W3209022602 hasConceptScore W3209022602C121332964 @default.
- W3209022602 hasConceptScore W3209022602C138885662 @default.
- W3209022602 hasConceptScore W3209022602C152671427 @default.
- W3209022602 hasConceptScore W3209022602C153180895 @default.
- W3209022602 hasConceptScore W3209022602C154945302 @default.
- W3209022602 hasConceptScore W3209022602C158525013 @default.
- W3209022602 hasConceptScore W3209022602C158693339 @default.
- W3209022602 hasConceptScore W3209022602C2776401178 @default.
- W3209022602 hasConceptScore W3209022602C41008148 @default.
- W3209022602 hasConceptScore W3209022602C41895202 @default.
- W3209022602 hasConceptScore W3209022602C42355184 @default.
- W3209022602 hasConceptScore W3209022602C46686674 @default.
- W3209022602 hasConceptScore W3209022602C52622490 @default.
- W3209022602 hasConceptScore W3209022602C62520636 @default.
- W3209022602 hasConceptScore W3209022602C69744172 @default.
- W3209022602 hasConceptScore W3209022602C75294576 @default.
- W3209022602 hasConceptScore W3209022602C95623464 @default.
- W3209022602 hasFunder F4320321001 @default.
- W3209022602 hasFunder F4320322919 @default.
- W3209022602 hasLocation W32090226021 @default.
- W3209022602 hasOpenAccess W3209022602 @default.
- W3209022602 hasPrimaryLocation W32090226021 @default.
- W3209022602 hasRelatedWork W1964120219 @default.
- W3209022602 hasRelatedWork W2108629388 @default.
- W3209022602 hasRelatedWork W2382607599 @default.
- W3209022602 hasRelatedWork W2546942002 @default.
- W3209022602 hasRelatedWork W2563096758 @default.
- W3209022602 hasRelatedWork W2738461075 @default.
- W3209022602 hasRelatedWork W2742991909 @default.
- W3209022602 hasRelatedWork W2940977206 @default.
- W3209022602 hasRelatedWork W2972035100 @default.
- W3209022602 hasRelatedWork W4320802741 @default.
- W3209022602 hasVolume "123" @default.
- W3209022602 isParatext "false" @default.
- W3209022602 isRetracted "false" @default.
- W3209022602 magId "3209022602" @default.
- W3209022602 workType "article" @default.