一直在关注Action Classification,VOC2010结果发布之后,大体看了一下,基本上就那些图像特征的使用(dense SIFT+Spatial Pyramid),然后就是乱七八糟的融合了,归结都低就是Multiple Kernel Learning以及一些近似的算法。
下面看看VOC2010关于ActionClassification部分的结果:
Average Precision (AP %)
phoning
playing
instrument
reading
riding
bike
riding
horse
running
taking
photo
using
computer
walking
BONN_ACTION
47.5
51.1
31.9
64.5
69.1
78.5
32.4
53.9
61.1
CVC_BASE
56.2
56.5
34....
Action Classification, Computer Vision, HOG, Multiple Kernel, SIFT, Spatial Pyramid, 机器学习, 视觉阅读全文
SIFT: Scale Invariant Feature Transform
by Utkarsh in Computer Vision,Featured
Matching features across different images in a common problem in computer vision. When all images are similar in nature (same scale, orientation, etc) simple corner detectors can work. But when you have images of different scales and rotations, you need to use the Scale Invariant Feature Transform.
Why care about SIFT
SIFT isn’t just scale invariant. You can change the following, and still...
SIFT, 图像处理, 图像检索阅读全文





最新评论
博主 找工作了?诶,foll
挺佩服这些人 的
请问下, X是m*n的矩阵
懂了,应该不行,因为X不一定
请问下,这里: θ = (
丕子师兄,呵呵 你女友不看
看老朋友来了,最近好像没有更
很好,很详细 :razz:
新年快乐,大吉大利!
新年快乐!天天快乐!愿望都实