Matches in SemOpenAlex for { <https://semopenalex.org/work/W3010982166> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3010982166 endingPage "115836" @default.
- W3010982166 startingPage "115836" @default.
- W3010982166 abstract "Abstract Considering the image captioning problem, it is difficult to correctly extract the global features of the images. At the same time, most attention methods force each word to correspond to the image region, ignoring the phenomenon that words such as “the” in the description text cannot correspond to the image region. To address these problems, an adaptive attention model with a visual sentinel is proposed in this paper. In the encoding phase, the model introduces DenseNet to extract the global features of the image. At the same time, on each time axis, the sentinel gate is set by the adaptive attention mechanism to decide whether to use the image feature information for word generation. In the decoding phase, the long short-term memory (LSTM) network is applied as a language generation model for image captioning tasks to improve the quality of image caption generation. Experiments on the Flickr30k and COCO datasets indicate that the proposed model exhibits significant improvement in terms ofthe BLEU and METEOR evaluation criteria." @default.
- W3010982166 created "2020-03-23" @default.
- W3010982166 creator A5015789129 @default.
- W3010982166 creator A5016884163 @default.
- W3010982166 creator A5020677950 @default.
- W3010982166 creator A5038510002 @default.
- W3010982166 creator A5045514825 @default.
- W3010982166 date "2020-07-01" @default.
- W3010982166 modified "2023-10-16" @default.
- W3010982166 title "Image captioning using DenseNet network and adaptive attention" @default.
- W3010982166 cites W1895577753 @default.
- W3010982166 cites W1969616664 @default.
- W3010982166 cites W2131179926 @default.
- W3010982166 cites W2149557440 @default.
- W3010982166 cites W2159564241 @default.
- W3010982166 cites W2185175083 @default.
- W3010982166 cites W2194775991 @default.
- W3010982166 cites W2220981600 @default.
- W3010982166 cites W2302086703 @default.
- W3010982166 cites W2550553598 @default.
- W3010982166 cites W2552161745 @default.
- W3010982166 cites W2575842049 @default.
- W3010982166 cites W2745461083 @default.
- W3010982166 cites W2765627079 @default.
- W3010982166 cites W2808773462 @default.
- W3010982166 cites W2888680923 @default.
- W3010982166 cites W2895407085 @default.
- W3010982166 cites W2963084599 @default.
- W3010982166 cites W2963446712 @default.
- W3010982166 cites W2964018924 @default.
- W3010982166 doi "https://doi.org/10.1016/j.image.2020.115836" @default.
- W3010982166 hasPublicationYear "2020" @default.
- W3010982166 type Work @default.
- W3010982166 sameAs 3010982166 @default.
- W3010982166 citedByCount "30" @default.
- W3010982166 countsByYear W30109821662020 @default.
- W3010982166 countsByYear W30109821662021 @default.
- W3010982166 countsByYear W30109821662022 @default.
- W3010982166 countsByYear W30109821662023 @default.
- W3010982166 crossrefType "journal-article" @default.
- W3010982166 hasAuthorship W3010982166A5015789129 @default.
- W3010982166 hasAuthorship W3010982166A5016884163 @default.
- W3010982166 hasAuthorship W3010982166A5020677950 @default.
- W3010982166 hasAuthorship W3010982166A5038510002 @default.
- W3010982166 hasAuthorship W3010982166A5045514825 @default.
- W3010982166 hasConcept C115961682 @default.
- W3010982166 hasConcept C154945302 @default.
- W3010982166 hasConcept C157657479 @default.
- W3010982166 hasConcept C28490314 @default.
- W3010982166 hasConcept C31972630 @default.
- W3010982166 hasConcept C41008148 @default.
- W3010982166 hasConceptScore W3010982166C115961682 @default.
- W3010982166 hasConceptScore W3010982166C154945302 @default.
- W3010982166 hasConceptScore W3010982166C157657479 @default.
- W3010982166 hasConceptScore W3010982166C28490314 @default.
- W3010982166 hasConceptScore W3010982166C31972630 @default.
- W3010982166 hasConceptScore W3010982166C41008148 @default.
- W3010982166 hasFunder F4320321001 @default.
- W3010982166 hasFunder F4320325705 @default.
- W3010982166 hasLocation W30109821661 @default.
- W3010982166 hasOpenAccess W3010982166 @default.
- W3010982166 hasPrimaryLocation W30109821661 @default.
- W3010982166 hasRelatedWork W2005185696 @default.
- W3010982166 hasRelatedWork W2092957489 @default.
- W3010982166 hasRelatedWork W2130228941 @default.
- W3010982166 hasRelatedWork W2161229648 @default.
- W3010982166 hasRelatedWork W2235753890 @default.
- W3010982166 hasRelatedWork W2366116130 @default.
- W3010982166 hasRelatedWork W2795359650 @default.
- W3010982166 hasRelatedWork W2923366293 @default.
- W3010982166 hasRelatedWork W2993674027 @default.
- W3010982166 hasRelatedWork W3008515501 @default.
- W3010982166 hasVolume "85" @default.
- W3010982166 isParatext "false" @default.
- W3010982166 isRetracted "false" @default.
- W3010982166 magId "3010982166" @default.
- W3010982166 workType "article" @default.