Corpus ID: 222177833

ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization

@inproceedings{PazArgaman2020ZESTZL,
  title={ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization},
  author={Tzuf Paz-Argaman and Y. Atzmon and Gal Chechik and Reut Tsarfaty},
  booktitle={EMNLP},
  year={2020}
}
  • Tzuf Paz-Argaman, Y. Atzmon, +1 author Reut Tsarfaty
  • Published in EMNLP 2020
  • Computer Science
  • We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds' images with free-text descriptions of their species, we learn to classify images of previously-unseen species based on specie descriptions. This setup has been studied in the vision community under the name zero-shot learning from text, focusing on learning to transfer knowledge about visual aspects of birds from seen classes to previously-unseen ones. Here, we suggest… CONTINUE READING

    Figures and Tables from this paper.

    References

    SHOWING 1-10 OF 37 REFERENCES
    Link the Head to the "Beak": Zero Shot Learning from Noisy Text Description at Part Precision
    • 60
    • Highly Influential
    • PDF
    Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions
    • 275
    • PDF
    Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions
    • 217
    • Highly Influential
    • PDF
    Less is More: Zero-Shot Learning from Online Textual Documents with Noise Suppression
    • 112
    • Highly Influential
    • PDF
    Learning Deep Representations of Fine-Grained Visual Descriptions
    • 420
    • Highly Influential
    • PDF
    Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning
    • 16
    • PDF
    Write a Classifier: Predicting Visual Classifiers from Unstructured Text
    • 30
    • Highly Influential
    • PDF
    Multi-cue Zero-Shot Learning with Strong Supervision
    • 93
    • Highly Influential
    • PDF
    A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts
    • 159
    • Highly Influential
    • PDF
    Detecting Visually Relevant Sentences for Fine-Grained Classification
    • 1
    • PDF