Matches in SemOpenAlex for { <https://semopenalex.org/work/W2023200607> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2023200607 endingPage "115" @default.
- W2023200607 startingPage "106" @default.
- W2023200607 abstract "This paper presents and evaluates a framework to improve the performance of visual object classification methods, which are based on the usage of image feature descriptors as inputs. The goal of the proposed framework is to learn the best descriptor for each image in a given database. This goal is reached by means of a reinforcement learning process using the minimum information. The visual classification system used to demonstrate the proposed framework is based on a bag of features scheme, and the reinforcement learning technique is implemented through the Q-learning approach. The behavior of the reinforcement learning with different state definitions is evaluated. Additionally, a method that combines all these states is formulated in order to select the optimal state. Finally, the chosen actions are obtained from the best set of image descriptors in the literature: PHOW, SIFT, C-SIFT, SURF and Spin. Experimental results using two public databases (ETH and COIL) are provided showing both the validity of the proposed approach and comparisons with state of the art. In all the cases the best results are obtained with the proposed approach." @default.
- W2023200607 created "2016-06-24" @default.
- W2023200607 creator A5002373986 @default.
- W2023200607 creator A5009238076 @default.
- W2023200607 creator A5038950226 @default.
- W2023200607 date "2015-02-01" @default.
- W2023200607 modified "2023-09-26" @default.
- W2023200607 title "Adaptive feature descriptor selection based on a multi-table reinforcement learning strategy" @default.
- W2023200607 cites W150164295 @default.
- W2023200607 cites W1504678489 @default.
- W2023200607 cites W1531621014 @default.
- W2023200607 cites W1677409904 @default.
- W2023200607 cites W1994757995 @default.
- W2023200607 cites W1996738877 @default.
- W2023200607 cites W2069891133 @default.
- W2023200607 cites W2074142320 @default.
- W2023200607 cites W2107034620 @default.
- W2023200607 cites W2111308925 @default.
- W2023200607 cites W2112074816 @default.
- W2023200607 cites W2119823327 @default.
- W2023200607 cites W2126833203 @default.
- W2023200607 cites W2128189052 @default.
- W2023200607 cites W2133059825 @default.
- W2023200607 cites W2144967509 @default.
- W2023200607 cites W2148596671 @default.
- W2023200607 cites W2151103935 @default.
- W2023200607 cites W2162762921 @default.
- W2023200607 cites W2162803672 @default.
- W2023200607 cites W2177274842 @default.
- W2023200607 cites W2181775184 @default.
- W2023200607 cites W4205398292 @default.
- W2023200607 doi "https://doi.org/10.1016/j.neucom.2014.03.080" @default.
- W2023200607 hasPublicationYear "2015" @default.
- W2023200607 type Work @default.
- W2023200607 sameAs 2023200607 @default.
- W2023200607 citedByCount "1" @default.
- W2023200607 countsByYear W20232006072015 @default.
- W2023200607 crossrefType "journal-article" @default.
- W2023200607 hasAuthorship W2023200607A5002373986 @default.
- W2023200607 hasAuthorship W2023200607A5009238076 @default.
- W2023200607 hasAuthorship W2023200607A5038950226 @default.
- W2023200607 hasConcept C111919701 @default.
- W2023200607 hasConcept C115961682 @default.
- W2023200607 hasConcept C119857082 @default.
- W2023200607 hasConcept C124101348 @default.
- W2023200607 hasConcept C138885662 @default.
- W2023200607 hasConcept C148483581 @default.
- W2023200607 hasConcept C153180895 @default.
- W2023200607 hasConcept C154945302 @default.
- W2023200607 hasConcept C177264268 @default.
- W2023200607 hasConcept C199360897 @default.
- W2023200607 hasConcept C2776401178 @default.
- W2023200607 hasConcept C41008148 @default.
- W2023200607 hasConcept C41895202 @default.
- W2023200607 hasConcept C61265191 @default.
- W2023200607 hasConcept C97541855 @default.
- W2023200607 hasConcept C98045186 @default.
- W2023200607 hasConceptScore W2023200607C111919701 @default.
- W2023200607 hasConceptScore W2023200607C115961682 @default.
- W2023200607 hasConceptScore W2023200607C119857082 @default.
- W2023200607 hasConceptScore W2023200607C124101348 @default.
- W2023200607 hasConceptScore W2023200607C138885662 @default.
- W2023200607 hasConceptScore W2023200607C148483581 @default.
- W2023200607 hasConceptScore W2023200607C153180895 @default.
- W2023200607 hasConceptScore W2023200607C154945302 @default.
- W2023200607 hasConceptScore W2023200607C177264268 @default.
- W2023200607 hasConceptScore W2023200607C199360897 @default.
- W2023200607 hasConceptScore W2023200607C2776401178 @default.
- W2023200607 hasConceptScore W2023200607C41008148 @default.
- W2023200607 hasConceptScore W2023200607C41895202 @default.
- W2023200607 hasConceptScore W2023200607C61265191 @default.
- W2023200607 hasConceptScore W2023200607C97541855 @default.
- W2023200607 hasConceptScore W2023200607C98045186 @default.
- W2023200607 hasFunder F4320326826 @default.
- W2023200607 hasLocation W20232006071 @default.
- W2023200607 hasOpenAccess W2023200607 @default.
- W2023200607 hasPrimaryLocation W20232006071 @default.
- W2023200607 hasRelatedWork W1981153982 @default.
- W2023200607 hasRelatedWork W2006247668 @default.
- W2023200607 hasRelatedWork W2009824857 @default.
- W2023200607 hasRelatedWork W2015538044 @default.
- W2023200607 hasRelatedWork W2098658853 @default.
- W2023200607 hasRelatedWork W2342738858 @default.
- W2023200607 hasRelatedWork W2345915074 @default.
- W2023200607 hasRelatedWork W2729514902 @default.
- W2023200607 hasRelatedWork W2787306535 @default.
- W2023200607 hasRelatedWork W2889582799 @default.
- W2023200607 hasVolume "150" @default.
- W2023200607 isParatext "false" @default.
- W2023200607 isRetracted "false" @default.
- W2023200607 magId "2023200607" @default.
- W2023200607 workType "article" @default.