Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945149253> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2945149253 endingPage "23" @default.
- W2945149253 startingPage "11" @default.
- W2945149253 abstract "Abstract Although Boosting approach has been proved to be a very successful ensemble learning technology, the conventional ones are limited to two classes or single modality. In this paper, to deal with multiclass setting and heterogeneous modalities, we propose a multimodal multiclass Boosting framework called MMBoost, in which the intra-modal semantic information and inter-modal semantic correlation can be captured at the same time. By utilizing the multiclass exponential and logistic loss functions, we further acquire two new versions of MMBoost, namely MMBoost_exp and MMBoost_log. The empirical risk, which simultaneously considers the intra-modal and inter-modal losses, is designed and then minimized by gradient descent in the multidimensional functional spaces. More concretely, the optimization problem is solved in turn for each modality. The posterior probability of semantic category can be naturally attained by applying sigmoid function to the multiclass margin. A series of experiments on the Wiki and NUS-WIDE datasets demonstrate that the performance of our proposed method significantly outperforms those of existing Boosting approaches for cross-modal retrieval." @default.
- W2945149253 created "2019-05-29" @default.
- W2945149253 creator A5035095972 @default.
- W2945149253 creator A5057724775 @default.
- W2945149253 creator A5059541904 @default.
- W2945149253 creator A5064736086 @default.
- W2945149253 creator A5075089700 @default.
- W2945149253 creator A5081234576 @default.
- W2945149253 date "2019-09-01" @default.
- W2945149253 modified "2023-10-14" @default.
- W2945149253 title "Multimodal Multiclass Boosting and its Application to Cross-modal Retrieval" @default.
- W2945149253 cites W1968969471 @default.
- W2945149253 cites W1986114064 @default.
- W2945149253 cites W1988790447 @default.
- W2945149253 cites W2006671292 @default.
- W2945149253 cites W2011143997 @default.
- W2945149253 cites W2012844989 @default.
- W2945149253 cites W2022356888 @default.
- W2945149253 cites W2024046085 @default.
- W2945149253 cites W2081773958 @default.
- W2945149253 cites W2100235303 @default.
- W2945149253 cites W2138118304 @default.
- W2945149253 cites W2151103935 @default.
- W2945149253 cites W2274047922 @default.
- W2945149253 cites W2318752590 @default.
- W2945149253 cites W2512032049 @default.
- W2945149253 cites W2526152041 @default.
- W2945149253 cites W2550617901 @default.
- W2945149253 cites W2606965845 @default.
- W2945149253 cites W2778854158 @default.
- W2945149253 cites W2809841383 @default.
- W2945149253 doi "https://doi.org/10.1016/j.neucom.2019.05.040" @default.
- W2945149253 hasPublicationYear "2019" @default.
- W2945149253 type Work @default.
- W2945149253 sameAs 2945149253 @default.
- W2945149253 citedByCount "4" @default.
- W2945149253 countsByYear W29451492532021 @default.
- W2945149253 countsByYear W29451492532022 @default.
- W2945149253 crossrefType "journal-article" @default.
- W2945149253 hasAuthorship W2945149253A5035095972 @default.
- W2945149253 hasAuthorship W2945149253A5057724775 @default.
- W2945149253 hasAuthorship W2945149253A5059541904 @default.
- W2945149253 hasAuthorship W2945149253A5064736086 @default.
- W2945149253 hasAuthorship W2945149253A5075089700 @default.
- W2945149253 hasAuthorship W2945149253A5081234576 @default.
- W2945149253 hasConcept C119857082 @default.
- W2945149253 hasConcept C153180895 @default.
- W2945149253 hasConcept C154945302 @default.
- W2945149253 hasConcept C185592680 @default.
- W2945149253 hasConcept C188027245 @default.
- W2945149253 hasConcept C41008148 @default.
- W2945149253 hasConcept C46686674 @default.
- W2945149253 hasConcept C71139939 @default.
- W2945149253 hasConceptScore W2945149253C119857082 @default.
- W2945149253 hasConceptScore W2945149253C153180895 @default.
- W2945149253 hasConceptScore W2945149253C154945302 @default.
- W2945149253 hasConceptScore W2945149253C185592680 @default.
- W2945149253 hasConceptScore W2945149253C188027245 @default.
- W2945149253 hasConceptScore W2945149253C41008148 @default.
- W2945149253 hasConceptScore W2945149253C46686674 @default.
- W2945149253 hasConceptScore W2945149253C71139939 @default.
- W2945149253 hasFunder F4320311345 @default.
- W2945149253 hasFunder F4320321001 @default.
- W2945149253 hasFunder F4320323845 @default.
- W2945149253 hasFunder F4320324174 @default.
- W2945149253 hasLocation W29451492531 @default.
- W2945149253 hasOpenAccess W2945149253 @default.
- W2945149253 hasPrimaryLocation W29451492531 @default.
- W2945149253 hasRelatedWork W1996541855 @default.
- W2945149253 hasRelatedWork W2003125512 @default.
- W2945149253 hasRelatedWork W2010832783 @default.
- W2945149253 hasRelatedWork W2108043611 @default.
- W2945149253 hasRelatedWork W3151529617 @default.
- W2945149253 hasRelatedWork W3159988495 @default.
- W2945149253 hasRelatedWork W3200719183 @default.
- W2945149253 hasRelatedWork W4292969247 @default.
- W2945149253 hasRelatedWork W4313488044 @default.
- W2945149253 hasRelatedWork W1930011471 @default.
- W2945149253 hasVolume "357" @default.
- W2945149253 isParatext "false" @default.
- W2945149253 isRetracted "false" @default.
- W2945149253 magId "2945149253" @default.
- W2945149253 workType "article" @default.