BOW模型丢弃了关于特征的空间布局信息，所以无法捕捉结构信息或者将对象从背景中分割出来。BOVW模型完全缺失了特征点的位置信息。
解决思路：
1） to augment a basic bag-of-features representation with pairwise relations
between neighboring local features
2）increase the level of invariance of local features (e.g., by using affine-invariant detectors)
Beyond Bags of Features: Spatial Pyramid Matching
思路：重复地划分图像区域，计算局部特征的直方图（在高分辨率下）
multiresolution histogram:对一副图像多次降采样计算像素值的整体直方图，对于直方图的分辨率（intensity scale）其实是固定的。
固定计算特征时图像的分辨率，而对spatial resolution进行变化。将图像分成若干块(sub-regions)，分别统计每一子块的特征，最后将所有块的特征拼接起来，形成完整的特征。这就是SPM中的Spatial。
补充知识：Spatial resolution states that the clarity of an image cannot be determined by the pixel resolution. The number of pixels in an image does not matter.
Spatial resolution can be defined as the smallest discernible detail in an image Or in other way we can define spatial resolution as the number of independent pixels values per inch.
MEASURING SPATIAL RESOLUTION:
Since the spatial resolution refers to clarity , so for different devices , different measure has been made to measure it.
- Dots per inch(DPI)
- Lines per inch(LPI)
- Pixels per inch(PPI)
在分块的细节上，作者采用了一种多尺度的分块方法，即分块的粒度越大越细(increasingly fine)，呈现出一种层次金字塔的结构，这就是SPM中的Pyramid。