Item Infomation

Full metadata record
DC FieldValueLanguage
dc.contributor.authorCelina, Hanouti-
dc.contributor.authorHervé Le, Borgne-
dc.date.accessioned2023-03-31T09:26:09Z-
dc.date.available2023-03-31T09:26:09Z-
dc.date.issued2023-
dc.identifier.urihttps://link.springer.com/article/10.1007/s11042-023-14877-1-
dc.identifier.urihttps://dlib.phenikaa-uni.edu.vn/handle/PNK/7403-
dc.descriptionCC BYvi
dc.description.abstractZero-shot learning (ZSL) aims at recognizing classes for which no visual sample is available at training time. To address this issue, one can rely on a semantic description of each class. A typical ZSL model learns a mapping between the visual samples of seen classes and the corresponding semantic descriptions, in order to do the same on unseen classes at test time. State of the art approaches rely on generative models that synthesize visual features from the prototype of a class, such that a classifier can then be learned in a supervised manner. However, these approaches are usually biased towards seen classes whose visual instances are the only one that can be matched to a given class prototype.vi
dc.language.isoenvi
dc.publisherSpringervi
dc.subjectZero-shot learningvi
dc.subjectsynthesize visual featuresvi
dc.titleLearning semantic ambiguities for zero-shot learningvi
dc.typeBookvi
Appears in CollectionsOER - Công nghệ thông tin

Files in This Item:
Thumbnail
  • Learning semantic ambiguities for zero-shot learning-2023.pdf
      Restricted Access
    • Size : 1,45 MB

    • Format : Adobe PDF