Large-scale learning of discriminative image representations
<p>This thesis addresses the problem of designing discriminative image representations for a variety of computer vision tasks. Our approach is to employ large-scale machine learning to obtain novel representations and improve the existing ones. This allows us to propose descriptors for a va...
第一著者: | Simonyan, K |
---|---|
その他の著者: | Zisserman, A |
フォーマット: | 学位論文 |
言語: | English |
出版事項: |
2013
|
主題: |
類似資料
-
Self-supervised learning of structural representations of visual objects
著者:: Jakab, T
出版事項: (2021) -
Representation of spatial transformations in deep neural networks
著者:: Lenc, K
出版事項: (2017) -
Self-supervised video representation learning
著者:: Han, T
出版事項: (2022) -
Algorithms for image saliency via sparse representation and multi-scale inputs image retargeting
著者:: Hoang, Minh Chau
出版事項: (2012) -
Learning to understand large-scale 3D point clouds
著者:: Qingyong, H
出版事項: (2022)