FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890718122> ?p ?o ?g. }

• W2890718122 endingPage "1061" @default.
• W2890718122 startingPage "1047" @default.
• W2890718122 abstract "Recent artificial intelligence research has witnessed great interest in automatically generating text descriptions of images, which are known as the image captioning task. Remarkable success has been achieved on domains where a large number of paired data in multimedia are available. Nevertheless, annotating sufficient data is labor-intensive and time-consuming, establishing significant barriers for adapting the image captioning systems to new domains. In this study, we introduc a novel Multitask Learning Algorithm for cross-Domain Image Captioning (MLADIC). MLADIC is a multitask system that simultaneously optimizes two coupled objectives via a dual learning mechanism: image captioning and text-to-image synthesis, with the hope that by leveraging the correlation of the two dual tasks, we are able to enhance the image captioning performance in the target domain. Concretely, the image captioning task is trained with an encoder-decoder model (i.e., CNN-LSTM) to generate textual descriptions of the input images. The image synthesis task employs the conditional generative adversarial network (C-GAN) to synthesize plausible images based on text descriptions. In C-GAN, a generative model $G$ synthesizes plausible images given text descriptions, and a discriminative model $D$ tries to distinguish the images in training data from the generated images by $G$. The adversarial process can eventually guide $G$ to generate plausible and high-quality images. To bridge the gap between different domains, a two-step strategy is adopted in order to transfer knowledge from the source domains to the target domains. First, we pre-train the model to learn the alignment between the neural representations of images and that of text data with the sufficient labeled source domain data. Second, we fine-tune the learned model by leveraging the limited image-text pairs and unpaired data in the target domain. We conduct extensive experiments to evaluate the performance of MLADIC by using the MSCOCO as the source domain data, and using Flickr30k and Oxford-102 as the target domain data. The results demonstrate that MLADIC achieves substantially better performance than the strong competitors for the cross-domain image captioning task." @default.
• W2890718122 created "2018-09-27" @default.
• W2890718122 creator A5032148962 @default.
• W2890718122 creator A5053869416 @default.
• W2890718122 creator A5054067088 @default.
• W2890718122 creator A5067671443 @default.
• W2890718122 creator A5070905937 @default.
• W2890718122 creator A5078920845 @default.
• W2890718122 creator A5079260216 @default.
• W2890718122 date "2019-04-01" @default.
• W2890718122 modified "2023-10-16" @default.
• W2890718122 title "Multitask Learning for Cross-Domain Image Captioning" @default.
• W2890718122 cites W1566289585 @default.
• W2890718122 cites W1799946925 @default.
• W2890718122 cites W1895577753 @default.
• W2890718122 cites W1905882502 @default.
• W2890718122 cites W1956340063 @default.
• W2890718122 cites W1965963232 @default.
• W2890718122 cites W2022398331 @default.
• W2890718122 cites W2101105183 @default.
• W2890718122 cites W2117539524 @default.
• W2890718122 cites W2119717200 @default.
• W2890718122 cites W2173180041 @default.
• W2890718122 cites W2185175083 @default.
• W2890718122 cites W2194775991 @default.
• W2890718122 cites W2282219577 @default.
• W2890718122 cites W2294978630 @default.
• W2890718122 cites W2296385829 @default.
• W2890718122 cites W2340600463 @default.
• W2890718122 cites W2342543219 @default.
• W2890718122 cites W2523923895 @default.
• W2890718122 cites W2528841789 @default.
• W2890718122 cites W2533598788 @default.
• W2890718122 cites W2550553598 @default.
• W2890718122 cites W2739107216 @default.
• W2890718122 cites W2740309605 @default.
• W2890718122 cites W2951183276 @default.
• W2890718122 cites W2963084599 @default.
• W2890718122 cites W2963410018 @default.
• W2890718122 cites W2963444790 @default.
• W2890718122 cites W2963992143 @default.
• W2890718122 cites W2964024144 @default.
• W2890718122 cites W2964065937 @default.
• W2890718122 cites W3099884890 @default.
• W2890718122 cites W4239943352 @default.
• W2890718122 cites W92662927 @default.
• W2890718122 doi "https://doi.org/10.1109/tmm.2018.2869276" @default.
• W2890718122 hasPublicationYear "2019" @default.
• W2890718122 type Work @default.
• W2890718122 sameAs 2890718122 @default.
• W2890718122 citedByCount "78" @default.
• W2890718122 countsByYear W28907181222019 @default.
• W2890718122 countsByYear W28907181222020 @default.
• W2890718122 countsByYear W28907181222021 @default.
• W2890718122 countsByYear W28907181222022 @default.
• W2890718122 countsByYear W28907181222023 @default.
• W2890718122 crossrefType "journal-article" @default.
• W2890718122 hasAuthorship W2890718122A5032148962 @default.
• W2890718122 hasAuthorship W2890718122A5053869416 @default.
• W2890718122 hasAuthorship W2890718122A5054067088 @default.
• W2890718122 hasAuthorship W2890718122A5067671443 @default.
• W2890718122 hasAuthorship W2890718122A5070905937 @default.
• W2890718122 hasAuthorship W2890718122A5078920845 @default.
• W2890718122 hasAuthorship W2890718122A5079260216 @default.
• W2890718122 hasConcept C111919701 @default.
• W2890718122 hasConcept C115961682 @default.
• W2890718122 hasConcept C118505674 @default.
• W2890718122 hasConcept C134306372 @default.
• W2890718122 hasConcept C153180895 @default.
• W2890718122 hasConcept C154945302 @default.
• W2890718122 hasConcept C157657479 @default.
• W2890718122 hasConcept C162324750 @default.
• W2890718122 hasConcept C175154964 @default.
• W2890718122 hasConcept C187736073 @default.
• W2890718122 hasConcept C204321447 @default.
• W2890718122 hasConcept C2780451532 @default.
• W2890718122 hasConcept C33923547 @default.
• W2890718122 hasConcept C36503486 @default.
• W2890718122 hasConcept C39890363 @default.
• W2890718122 hasConcept C41008148 @default.
• W2890718122 hasConcept C97931131 @default.
• W2890718122 hasConceptScore W2890718122C111919701 @default.
• W2890718122 hasConceptScore W2890718122C115961682 @default.
• W2890718122 hasConceptScore W2890718122C118505674 @default.
• W2890718122 hasConceptScore W2890718122C134306372 @default.
• W2890718122 hasConceptScore W2890718122C153180895 @default.
• W2890718122 hasConceptScore W2890718122C154945302 @default.
• W2890718122 hasConceptScore W2890718122C157657479 @default.
• W2890718122 hasConceptScore W2890718122C162324750 @default.
• W2890718122 hasConceptScore W2890718122C175154964 @default.
• W2890718122 hasConceptScore W2890718122C187736073 @default.
• W2890718122 hasConceptScore W2890718122C204321447 @default.
• W2890718122 hasConceptScore W2890718122C2780451532 @default.
• W2890718122 hasConceptScore W2890718122C33923547 @default.
• W2890718122 hasConceptScore W2890718122C36503486 @default.
• W2890718122 hasConceptScore W2890718122C39890363 @default.
• W2890718122 hasConceptScore W2890718122C41008148 @default.
• W2890718122 hasConceptScore W2890718122C97931131 @default.

• next