CVPR 2019 Open Access Repository

Discovering Visual Patterns in Art Collections With Spatially-Consistent Feature Learning Abstract Our goal in this paper is to discover near duplicate patterns in large collections of artworks. This is harder than standard instance mining due to differences in the artistic media (oil, pastel, drawing, etc), and imperfections inherent in the copying process. Our key technical insight is to adapt a standard deep feature to this task by fine-tuning it on the specific art collection using self-su

1 mentions: @t_Signull
Keywords: cvpr
Date: 2019/06/14 14:17

Referring Tweets

@t_Signull Efrosセンセが著者に入ってるこの論文タイトルだけで面白いとわかる Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning https://t.co/XlHNthLh4T

Related Entries

Read more 教師なし画像特徴表現学習の動向 {Un, Self} supervised representation learning (CVPR 2…
0 users, 0 mentions 2018/10/17 06:23
Read more CVPR 2019 速報
20 users, 28 mentions 2019/06/21 03:47
Read more CVPR 2017 速報
0 users, 0 mentions 2018/04/22 03:41
Read more [MIRU 2018 招待講演] Neural 3D Mesh Renderer (CVPR 2018)
0 users, 0 mentions 2018/08/06 13:00
Read more CVPR 2018 速報
25 users, 2 mentions 2019/01/23 02:15