Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Martin Engilberge"'
Publikováno v:
ICCV
Humans share a strong tendency to memorize/forget some of the visual information they encounter. This paper focuses on providing computational models for the prediction of the intrinsic memorability of visual content. To address this new challenge, w
Publikováno v:
CVPR
CVPR 2019-2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition
CVPR 2019-2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2019, Long Beach, United States
CVPR 2019-2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition
CVPR 2019-2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2019, Long Beach, United States
Several tasks in machine learning are evaluated using non-differentiable metrics such as mean average precision or Spearman correlation. However, their non-differentiability prevents from using them as objective functions in a learning framework. Sur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b6be37fb94ef90f786d622b9492e2642
https://hal.archives-ouvertes.fr/hal-02171870
https://hal.archives-ouvertes.fr/hal-02171870
Publikováno v:
ICIP
Convolutional neural networks are top-performers on image classification tasks. Understanding how they make use of color information in images may be useful for various tasks. In this paper we analyze the representation learned by a popular CNN to de