Matches in SemOpenAlex for { <https://semopenalex.org/work/W93016980> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W93016980 abstract "Abstract: Several recent publications have proposed methods for mapping images into continuous semantic embedding spaces. In some cases the embedding space is trained jointly with the image transformation. In other cases the semantic embedding space is established by an independent natural language processing task, and then the image transformation into that space is learned in a second stage. Proponents of these image embedding systems have stressed their advantages over the traditional nway{} classification framing of image understanding, particularly in terms of the promise for zero-shot learning -- the ability to correctly annotate images of previously unseen object categories. In this paper, we propose a simple method for constructing an image embedding system from any existing nway{} image classifier and a semantic word embedding model, which contains the $n$ class labels in its vocabulary. Our method maps images into the semantic embedding space via convex combination of the class label embedding vectors, and requires no additional training. We show that this simple and direct method confers many of the advantages associated with more complex image embedding schemes, and indeed outperforms state of the art methods on the ImageNet zero-shot learning task." @default.
- W93016980 created "2016-06-24" @default.
- W93016980 creator A5017529415 @default.
- W93016980 creator A5018912210 @default.
- W93016980 creator A5019861361 @default.
- W93016980 creator A5020917394 @default.
- W93016980 creator A5032356827 @default.
- W93016980 creator A5043872671 @default.
- W93016980 creator A5050591232 @default.
- W93016980 creator A5068955381 @default.
- W93016980 date "2014-01-01" @default.
- W93016980 modified "2023-09-27" @default.
- W93016980 title "Zero-Shot Learning by Convex Combination of Semantic Embeddings" @default.
- W93016980 cites W100623710 @default.
- W93016980 cites W1499991161 @default.
- W93016980 cites W1614298861 @default.
- W93016980 cites W2098411764 @default.
- W93016980 cites W21006490 @default.
- W93016980 cites W2108598243 @default.
- W93016980 cites W2115733720 @default.
- W93016980 cites W2123024445 @default.
- W93016980 cites W2124033848 @default.
- W93016980 cites W2133774033 @default.
- W93016980 cites W2134270519 @default.
- W93016980 cites W2150295085 @default.
- W93016980 cites W2155853132 @default.
- W93016980 cites W2163605009 @default.
- W93016980 cites W2294130536 @default.
- W93016980 cites W2401823607 @default.
- W93016980 cites W27961112 @default.
- W93016980 hasPublicationYear "2014" @default.
- W93016980 type Work @default.
- W93016980 sameAs 93016980 @default.
- W93016980 citedByCount "334" @default.
- W93016980 countsByYear W930169802013 @default.
- W93016980 countsByYear W930169802014 @default.
- W93016980 countsByYear W930169802015 @default.
- W93016980 countsByYear W930169802016 @default.
- W93016980 countsByYear W930169802017 @default.
- W93016980 countsByYear W930169802018 @default.
- W93016980 countsByYear W930169802019 @default.
- W93016980 countsByYear W930169802020 @default.
- W93016980 countsByYear W930169802021 @default.
- W93016980 countsByYear W930169802023 @default.
- W93016980 crossrefType "proceedings-article" @default.
- W93016980 hasAuthorship W93016980A5017529415 @default.
- W93016980 hasAuthorship W93016980A5018912210 @default.
- W93016980 hasAuthorship W93016980A5019861361 @default.
- W93016980 hasAuthorship W93016980A5020917394 @default.
- W93016980 hasAuthorship W93016980A5032356827 @default.
- W93016980 hasAuthorship W93016980A5043872671 @default.
- W93016980 hasAuthorship W93016980A5050591232 @default.
- W93016980 hasAuthorship W93016980A5068955381 @default.
- W93016980 hasConcept C115961682 @default.
- W93016980 hasConcept C153180895 @default.
- W93016980 hasConcept C154945302 @default.
- W93016980 hasConcept C2777212361 @default.
- W93016980 hasConcept C2777462759 @default.
- W93016980 hasConcept C41008148 @default.
- W93016980 hasConcept C41608201 @default.
- W93016980 hasConcept C75294576 @default.
- W93016980 hasConceptScore W93016980C115961682 @default.
- W93016980 hasConceptScore W93016980C153180895 @default.
- W93016980 hasConceptScore W93016980C154945302 @default.
- W93016980 hasConceptScore W93016980C2777212361 @default.
- W93016980 hasConceptScore W93016980C2777462759 @default.
- W93016980 hasConceptScore W93016980C41008148 @default.
- W93016980 hasConceptScore W93016980C41608201 @default.
- W93016980 hasConceptScore W93016980C75294576 @default.
- W93016980 hasLocation W930169801 @default.
- W93016980 hasOpenAccess W93016980 @default.
- W93016980 hasPrimaryLocation W930169801 @default.
- W93016980 hasRelatedWork W1797268635 @default.
- W93016980 hasRelatedWork W2098411764 @default.
- W93016980 hasRelatedWork W2108598243 @default.
- W93016980 hasRelatedWork W2117539524 @default.
- W93016980 hasRelatedWork W2123024445 @default.
- W93016980 hasRelatedWork W2128532956 @default.
- W93016980 hasRelatedWork W2134270519 @default.
- W93016980 hasRelatedWork W2153579005 @default.
- W93016980 hasRelatedWork W2171061940 @default.
- W93016980 hasRelatedWork W2194775991 @default.
- W93016980 hasRelatedWork W2250539671 @default.
- W93016980 hasRelatedWork W2289084343 @default.
- W93016980 hasRelatedWork W2334493732 @default.
- W93016980 hasRelatedWork W2552383788 @default.
- W93016980 hasRelatedWork W2611632661 @default.
- W93016980 hasRelatedWork W2950276680 @default.
- W93016980 hasRelatedWork W2963960318 @default.
- W93016980 hasRelatedWork W2964086552 @default.
- W93016980 hasRelatedWork W3100093508 @default.
- W93016980 hasRelatedWork W652269744 @default.
- W93016980 isParatext "false" @default.
- W93016980 isRetracted "false" @default.
- W93016980 magId "93016980" @default.
- W93016980 workType "article" @default.