Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207264003> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3207264003 endingPage "14" @default.
- W3207264003 startingPage "3" @default.
- W3207264003 abstract "Image captioning is a complex artificial intelligence task that involves many fundamental questions of data representation, learning, and natural language processing. In addition, most of the work in this domain addresses the English language because of the high availability of annotated training data compared to other languages. Therefore, we investigate methods for image captioning in German that transfer knowledge from English training data. We explore four different methods for generating image captions in German, two baseline methods and two more advanced ones based on transfer learning. The baseline methods are based on a state-of-the-art model which we train using a translated version of the English MS COCO dataset and the smaller German Multi30K dataset, respectively. Both advanced methods are pre-trained using the translated MS COCO dataset and fine-tuned for German on the Multi30K dataset. One of these methods uses an alternative attention mechanism from the literature that showed a good performance in English image captioning. We compare the performance of all methods for the Multi30K test set in German using common automatic evaluation metrics. We show that our advanced method with the alternative attention mechanism presents a new baseline for German BLEU, ROUGE, CIDEr, and SPICE scores, and achieves a relative improvement of 21.2% in BLEU-4 score compared to the current state-of-the-art in German image captioning." @default.
- W3207264003 created "2021-10-25" @default.
- W3207264003 creator A5002721360 @default.
- W3207264003 creator A5037664911 @default.
- W3207264003 creator A5045623158 @default.
- W3207264003 creator A5069432042 @default.
- W3207264003 date "2021-01-01" @default.
- W3207264003 modified "2023-09-26" @default.
- W3207264003 title "Improving German Image Captions Using Machine Translation and Transfer Learning" @default.
- W3207264003 cites W1861492603 @default.
- W3207264003 cites W1956340063 @default.
- W3207264003 cites W2064675550 @default.
- W3207264003 cites W2101105183 @default.
- W3207264003 cites W2108598243 @default.
- W3207264003 cites W2194775991 @default.
- W3207264003 cites W2293344577 @default.
- W3207264003 cites W2506483933 @default.
- W3207264003 cites W2509282593 @default.
- W3207264003 cites W2509490957 @default.
- W3207264003 cites W2513263213 @default.
- W3207264003 cites W2749708282 @default.
- W3207264003 cites W2758123554 @default.
- W3207264003 cites W2933138175 @default.
- W3207264003 cites W2963048642 @default.
- W3207264003 cites W2963331233 @default.
- W3207264003 cites W2963909453 @default.
- W3207264003 cites W2964959218 @default.
- W3207264003 cites W2976515606 @default.
- W3207264003 cites W3034180655 @default.
- W3207264003 cites W3041019899 @default.
- W3207264003 doi "https://doi.org/10.1007/978-3-030-89579-2_1" @default.
- W3207264003 hasPublicationYear "2021" @default.
- W3207264003 type Work @default.
- W3207264003 sameAs 3207264003 @default.
- W3207264003 citedByCount "1" @default.
- W3207264003 countsByYear W32072640032022 @default.
- W3207264003 crossrefType "book-chapter" @default.
- W3207264003 hasAuthorship W3207264003A5002721360 @default.
- W3207264003 hasAuthorship W3207264003A5037664911 @default.
- W3207264003 hasAuthorship W3207264003A5045623158 @default.
- W3207264003 hasAuthorship W3207264003A5069432042 @default.
- W3207264003 hasConcept C104317684 @default.
- W3207264003 hasConcept C105580179 @default.
- W3207264003 hasConcept C115961682 @default.
- W3207264003 hasConcept C138885662 @default.
- W3207264003 hasConcept C149364088 @default.
- W3207264003 hasConcept C150899416 @default.
- W3207264003 hasConcept C154775046 @default.
- W3207264003 hasConcept C154945302 @default.
- W3207264003 hasConcept C185592680 @default.
- W3207264003 hasConcept C203005215 @default.
- W3207264003 hasConcept C204321447 @default.
- W3207264003 hasConcept C41008148 @default.
- W3207264003 hasConcept C41895202 @default.
- W3207264003 hasConcept C55493867 @default.
- W3207264003 hasConceptScore W3207264003C104317684 @default.
- W3207264003 hasConceptScore W3207264003C105580179 @default.
- W3207264003 hasConceptScore W3207264003C115961682 @default.
- W3207264003 hasConceptScore W3207264003C138885662 @default.
- W3207264003 hasConceptScore W3207264003C149364088 @default.
- W3207264003 hasConceptScore W3207264003C150899416 @default.
- W3207264003 hasConceptScore W3207264003C154775046 @default.
- W3207264003 hasConceptScore W3207264003C154945302 @default.
- W3207264003 hasConceptScore W3207264003C185592680 @default.
- W3207264003 hasConceptScore W3207264003C203005215 @default.
- W3207264003 hasConceptScore W3207264003C204321447 @default.
- W3207264003 hasConceptScore W3207264003C41008148 @default.
- W3207264003 hasConceptScore W3207264003C41895202 @default.
- W3207264003 hasConceptScore W3207264003C55493867 @default.
- W3207264003 hasLocation W32072640031 @default.
- W3207264003 hasOpenAccess W3207264003 @default.
- W3207264003 hasPrimaryLocation W32072640031 @default.
- W3207264003 hasRelatedWork W1484029852 @default.
- W3207264003 hasRelatedWork W1512718085 @default.
- W3207264003 hasRelatedWork W1585034923 @default.
- W3207264003 hasRelatedWork W1592339875 @default.
- W3207264003 hasRelatedWork W1697423248 @default.
- W3207264003 hasRelatedWork W2313858059 @default.
- W3207264003 hasRelatedWork W2435130738 @default.
- W3207264003 hasRelatedWork W2747680751 @default.
- W3207264003 hasRelatedWork W3107474891 @default.
- W3207264003 hasRelatedWork W2610387714 @default.
- W3207264003 isParatext "false" @default.
- W3207264003 isRetracted "false" @default.
- W3207264003 magId "3207264003" @default.
- W3207264003 workType "book-chapter" @default.