Speedy Neural Networks for Smart Auto-Cropping of Images
Left: Our face detector is unable to detect cats and other objects. Right: Our new cropping mechanism is able to focus on the most interesting part of the image. Cropping using saliency A better way to crop is to focus on “salient†image regions. A region having high saliency means that a person is likely to look at it when freely viewing the image. Academics have studied and measured saliency by
1
リリースã€éšœå®³æƒ…å ±ãªã©ã®ã‚µãƒ¼ãƒ“スã®ãŠçŸ¥ã‚‰ã›
最新ã®äººæ°—エントリーã®é…ä¿¡
処ç†ã‚’実行ä¸ã§ã™
j次ã®ãƒ–ックマーク
kå‰ã®ãƒ–ックマーク
lã‚ã¨ã§èªã‚€
eコメント一覧を開ã
oページを開ã
https://alex-xun-xu.github.io/Doc/Publication/2018/ZhangZXXLT_SPIC2018.pdf
https://arxiv.org/pdf/1812.07989.pdf
Automatic Image Cropping : A Computational Complexity Study
http://arxiv.org/pdf/1701.01480
http://arxiv.org/pdf/1712.09048
{{#tags}}- {{label}}
{{/tags}}