原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
Figure 51.12: Four representations computed from the input on the left. The input image itself (its pixel values) is in fact a fifth representation of the scene. Think about the relative merits of each of these representations, and what advantages or disadvantages text might have over these other kinds of visual representation. Text is a powerful visual representation because it interfaces with language models. This
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c051.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8