Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313641566> ?p ?o ?g. }
- W4313641566 endingPage "552" @default.
- W4313641566 startingPage "536" @default.
- W4313641566 abstract "Traditional Generative Adversarial Network (GAN) based Generalized Zero Shot Learning (GZSL) methods usually suffer from a problem that these methods ignore the differences between classes when using the standard normal distribution to fit the true distribution of each category, and the incompleteness of a single adversarial training makes the model unable to capture all the characteristics of the samples. To address this problem, a data-driven recurrent adversarial generative network is proposed in this paper. We first synthesize visual prototypes for unseen classes using the transformation from semantic attributes to visual prototypes learned on seen classes. Then, some noise is generated from these prototypes to synthesize the unseen samples according to the corresponding semantic attributes. During the sample generation process, a recurrent generative adversarial network is designed to facilitate the generated visual features to be more representative. Extensive experiments on five popular datasets as well as detailed ablation studies demonstrate the effectiveness and superiority of the proposed method." @default.
- W4313641566 created "2023-01-07" @default.
- W4313641566 creator A5011037821 @default.
- W4313641566 creator A5063481044 @default.
- W4313641566 creator A5064008061 @default.
- W4313641566 creator A5073501391 @default.
- W4313641566 creator A5086986505 @default.
- W4313641566 creator A5088888083 @default.
- W4313641566 date "2023-05-01" @default.
- W4313641566 modified "2023-10-16" @default.
- W4313641566 title "Data driven recurrent generative adversarial network for generalized zero shot image classification" @default.
- W4313641566 cites W2032699694 @default.
- W4313641566 cites W2098411764 @default.
- W4313641566 cites W2108598243 @default.
- W4313641566 cites W2400717490 @default.
- W4313641566 cites W2864476761 @default.
- W4313641566 cites W2887567284 @default.
- W4313641566 cites W2888198675 @default.
- W4313641566 cites W2898502605 @default.
- W4313641566 cites W2962689421 @default.
- W4313641566 cites W2962785568 @default.
- W4313641566 cites W2962791511 @default.
- W4313641566 cites W2963283377 @default.
- W4313641566 cites W2963499153 @default.
- W4313641566 cites W2963960318 @default.
- W4313641566 cites W2964024144 @default.
- W4313641566 cites W2964248207 @default.
- W4313641566 cites W2964307109 @default.
- W4313641566 cites W2998708909 @default.
- W4313641566 cites W2999343096 @default.
- W4313641566 cites W3000538487 @default.
- W4313641566 cites W3001100505 @default.
- W4313641566 cites W3025895701 @default.
- W4313641566 cites W3026651144 @default.
- W4313641566 cites W3089741414 @default.
- W4313641566 cites W3097309192 @default.
- W4313641566 cites W3102100346 @default.
- W4313641566 cites W3109994846 @default.
- W4313641566 cites W3110183969 @default.
- W4313641566 cites W3113767342 @default.
- W4313641566 cites W3121070744 @default.
- W4313641566 cites W3143107425 @default.
- W4313641566 cites W3158436118 @default.
- W4313641566 cites W3167705651 @default.
- W4313641566 cites W3178621454 @default.
- W4313641566 cites W3183803087 @default.
- W4313641566 cites W3195163009 @default.
- W4313641566 cites W3199619261 @default.
- W4313641566 cites W4220673387 @default.
- W4313641566 cites W18035983 @default.
- W4313641566 doi "https://doi.org/10.1016/j.ins.2023.01.039" @default.
- W4313641566 hasPublicationYear "2023" @default.
- W4313641566 type Work @default.
- W4313641566 citedByCount "1" @default.
- W4313641566 countsByYear W43136415662023 @default.
- W4313641566 crossrefType "journal-article" @default.
- W4313641566 hasAuthorship W4313641566A5011037821 @default.
- W4313641566 hasAuthorship W4313641566A5063481044 @default.
- W4313641566 hasAuthorship W4313641566A5064008061 @default.
- W4313641566 hasAuthorship W4313641566A5073501391 @default.
- W4313641566 hasAuthorship W4313641566A5086986505 @default.
- W4313641566 hasAuthorship W4313641566A5088888083 @default.
- W4313641566 hasConcept C104317684 @default.
- W4313641566 hasConcept C115961682 @default.
- W4313641566 hasConcept C119857082 @default.
- W4313641566 hasConcept C153180895 @default.
- W4313641566 hasConcept C154945302 @default.
- W4313641566 hasConcept C167966045 @default.
- W4313641566 hasConcept C185592680 @default.
- W4313641566 hasConcept C198531522 @default.
- W4313641566 hasConcept C204241405 @default.
- W4313641566 hasConcept C2988773926 @default.
- W4313641566 hasConcept C37736160 @default.
- W4313641566 hasConcept C39890363 @default.
- W4313641566 hasConcept C41008148 @default.
- W4313641566 hasConcept C43617362 @default.
- W4313641566 hasConcept C55493867 @default.
- W4313641566 hasConceptScore W4313641566C104317684 @default.
- W4313641566 hasConceptScore W4313641566C115961682 @default.
- W4313641566 hasConceptScore W4313641566C119857082 @default.
- W4313641566 hasConceptScore W4313641566C153180895 @default.
- W4313641566 hasConceptScore W4313641566C154945302 @default.
- W4313641566 hasConceptScore W4313641566C167966045 @default.
- W4313641566 hasConceptScore W4313641566C185592680 @default.
- W4313641566 hasConceptScore W4313641566C198531522 @default.
- W4313641566 hasConceptScore W4313641566C204241405 @default.
- W4313641566 hasConceptScore W4313641566C2988773926 @default.
- W4313641566 hasConceptScore W4313641566C37736160 @default.
- W4313641566 hasConceptScore W4313641566C39890363 @default.
- W4313641566 hasConceptScore W4313641566C41008148 @default.
- W4313641566 hasConceptScore W4313641566C43617362 @default.
- W4313641566 hasConceptScore W4313641566C55493867 @default.
- W4313641566 hasFunder F4320321001 @default.
- W4313641566 hasFunder F4320322769 @default.
- W4313641566 hasLocation W43136415661 @default.
- W4313641566 hasOpenAccess W4313641566 @default.
- W4313641566 hasPrimaryLocation W43136415661 @default.
- W4313641566 hasRelatedWork W2901368259 @default.