Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309397148> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4309397148 endingPage "1003" @default.
- W4309397148 startingPage "995" @default.
- W4309397148 abstract "In this work, we study the application of multimodal analogical reasoning to image retrieval. Multimodal analogy questions are given in a form of tuples of words and images, e.g., “cat”:“dog”::[an image of a cat sitting on a bench]:?, to search for an image of a dog sitting on a bench. Retrieving desired images given these tuples can be seen as a task of finding images whose relation between the query image is close to that of query words. One way to achieve the task is building a common vector space that exhibits analogical regularities. To learn such an embedding, we propose a quadruple neural network called multimodal siamese network. The network consists of recurrent neural networks and convolutional neural networks based on the siamese architecture. We also introduce an effective procedure to generate analogy examples from an image-caption dataset for training of our network. In our experiments, we test our model on analogy-based image retrieval tasks. The results show that our method outperforms the previous work in qualitative evaluation." @default.
- W4309397148 created "2022-11-26" @default.
- W4309397148 creator A5013836679 @default.
- W4309397148 creator A5020482990 @default.
- W4309397148 creator A5044491436 @default.
- W4309397148 creator A5050979241 @default.
- W4309397148 date "2022-11-20" @default.
- W4309397148 modified "2023-09-26" @default.
- W4309397148 title "Multimodal Analogy-Based Image Retrieval by Improving Semantic Embeddings" @default.
- W4309397148 cites W1861492603 @default.
- W4309397148 cites W1905882502 @default.
- W4309397148 cites W2127589108 @default.
- W4309397148 cites W2194775991 @default.
- W4309397148 cites W2250539671 @default.
- W4309397148 cites W2546696630 @default.
- W4309397148 cites W2778940641 @default.
- W4309397148 cites W2963351113 @default.
- W4309397148 cites W2963389687 @default.
- W4309397148 cites W2963966654 @default.
- W4309397148 cites W2964024144 @default.
- W4309397148 cites W2982147439 @default.
- W4309397148 cites W3034655362 @default.
- W4309397148 doi "https://doi.org/10.20965/jaciii.2022.p0995" @default.
- W4309397148 hasPublicationYear "2022" @default.
- W4309397148 type Work @default.
- W4309397148 citedByCount "0" @default.
- W4309397148 crossrefType "journal-article" @default.
- W4309397148 hasAuthorship W4309397148A5013836679 @default.
- W4309397148 hasAuthorship W4309397148A5020482990 @default.
- W4309397148 hasAuthorship W4309397148A5044491436 @default.
- W4309397148 hasAuthorship W4309397148A5050979241 @default.
- W4309397148 hasBestOaLocation W43093971481 @default.
- W4309397148 hasConcept C115961682 @default.
- W4309397148 hasConcept C118615104 @default.
- W4309397148 hasConcept C118930307 @default.
- W4309397148 hasConcept C124101348 @default.
- W4309397148 hasConcept C138885662 @default.
- W4309397148 hasConcept C153180895 @default.
- W4309397148 hasConcept C154945302 @default.
- W4309397148 hasConcept C162324750 @default.
- W4309397148 hasConcept C1667742 @default.
- W4309397148 hasConcept C187736073 @default.
- W4309397148 hasConcept C204321447 @default.
- W4309397148 hasConcept C25343380 @default.
- W4309397148 hasConcept C2780451532 @default.
- W4309397148 hasConcept C33923547 @default.
- W4309397148 hasConcept C41008148 @default.
- W4309397148 hasConcept C41608201 @default.
- W4309397148 hasConcept C41895202 @default.
- W4309397148 hasConcept C50644808 @default.
- W4309397148 hasConcept C521332185 @default.
- W4309397148 hasConcept C81363708 @default.
- W4309397148 hasConceptScore W4309397148C115961682 @default.
- W4309397148 hasConceptScore W4309397148C118615104 @default.
- W4309397148 hasConceptScore W4309397148C118930307 @default.
- W4309397148 hasConceptScore W4309397148C124101348 @default.
- W4309397148 hasConceptScore W4309397148C138885662 @default.
- W4309397148 hasConceptScore W4309397148C153180895 @default.
- W4309397148 hasConceptScore W4309397148C154945302 @default.
- W4309397148 hasConceptScore W4309397148C162324750 @default.
- W4309397148 hasConceptScore W4309397148C1667742 @default.
- W4309397148 hasConceptScore W4309397148C187736073 @default.
- W4309397148 hasConceptScore W4309397148C204321447 @default.
- W4309397148 hasConceptScore W4309397148C25343380 @default.
- W4309397148 hasConceptScore W4309397148C2780451532 @default.
- W4309397148 hasConceptScore W4309397148C33923547 @default.
- W4309397148 hasConceptScore W4309397148C41008148 @default.
- W4309397148 hasConceptScore W4309397148C41608201 @default.
- W4309397148 hasConceptScore W4309397148C41895202 @default.
- W4309397148 hasConceptScore W4309397148C50644808 @default.
- W4309397148 hasConceptScore W4309397148C521332185 @default.
- W4309397148 hasConceptScore W4309397148C81363708 @default.
- W4309397148 hasIssue "6" @default.
- W4309397148 hasLocation W43093971481 @default.
- W4309397148 hasOpenAccess W4309397148 @default.
- W4309397148 hasPrimaryLocation W43093971481 @default.
- W4309397148 hasRelatedWork W2399159263 @default.
- W4309397148 hasRelatedWork W2605526599 @default.
- W4309397148 hasRelatedWork W2767651786 @default.
- W4309397148 hasRelatedWork W2912288872 @default.
- W4309397148 hasRelatedWork W2915781047 @default.
- W4309397148 hasRelatedWork W3006672880 @default.
- W4309397148 hasRelatedWork W3185614091 @default.
- W4309397148 hasRelatedWork W4299912061 @default.
- W4309397148 hasRelatedWork W4381744223 @default.
- W4309397148 hasRelatedWork W564581980 @default.
- W4309397148 hasVolume "26" @default.
- W4309397148 isParatext "false" @default.
- W4309397148 isRetracted "false" @default.
- W4309397148 workType "article" @default.