Abstract | ||
---|---|---|
This paper presents a novel random forest learning framework to construct a discriminative and informative mid-level feature from low-level features. Since a single low-level feature based representation is not enough to capture the variations of human appearance, multiple low-level features (i.e., optical flow and histogram of gradient 3D features) are fused to further improve recognition performance. The mid-level feature is employed by a random forest classifier for robust action recognition. Experiments on two publicly available action datasets demonstrate that using both the mid-level feature and the fusion of multiple low-level features leads to a superior performance over previous methods. |
Year | Venue | Keywords |
---|---|---|
2012 | ICPR | random forest classifier,histogram-of-gradient 3d features,image fusion,random processes,learning (artificial intelligence),robust action recognition,feature extraction,image classification,random forest learning framework,discriminative midlevel features,image sequences,informative midlevel feature,optical flow,learning artificial intelligence |
Field | DocType | ISSN |
Computer vision,Histogram,Feature detection (computer vision),Pattern recognition,Computer science,Feature (computer vision),Feature extraction,Feature (machine learning),Artificial intelligence,Contextual image classification,Random forest,Discriminative model | Conference | 1051-4651 |
ISBN | Citations | PageRank |
978-1-4673-2216-4 | 3 | 0.38 |
References | Authors | |
11 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cuiwei Liu | 1 | 54 | 3.04 |
Yu Kong | 2 | 412 | 24.72 |
Xinxiao Wu | 3 | 272 | 20.21 |
Yunde Jia | 4 | 958 | 84.33 |