Paper Info
Title
Stratified pooling based deep convolutional neural networks for human action recognition.
Abstract
Video based human action recognition is an active and challenging topic in computer vision. Over the last few years, deep convolutional neural networks (CNN) has become the most popular method and achieved the state-of-the-art performance on several datasets, such as HMDB-51 and UCF-101. Since each video has a various number of frame-level features, how to combine these features to acquire good video-level feature becomes a challenging task. Therefore, this paper proposed a novel action recognition method named stratified pooling, which is based on deep convolutional neural networks (SP-CNN). The process is mainly composed of five parts: (i) fine-tuning a pre-trained CNN on the target dataset, (ii) frame-level features extraction; (iii) the principal component analysis (PCA) method for feature dimensionality reduction; (iv) stratified pooling frame-level features to get video-level feature; and (v) SVM for multiclass classification. Finally, the experimental results conducted on HMDB-51 and UCF-101 datasets show that the proposed method outperforms the state-of-the-art.
Year
DOI
Venue
2017
10.1007/s11042-016-3768-5
Multimedia Tools Appl.
Keywords
Field
DocType
Human action recognition,Convolutional neural networks (CNN),Stratified pooling (SP),Support vector machines (SVM)
Dimensionality reduction,Pattern recognition,Convolutional neural network,Computer science,Action recognition,Pooling,Support vector machine,Artificial intelligence,Principal component analysis,Machine learning,Multiclass classification
Journal
Volume
Issue
ISSN
76
11
1380-7501
Citations 
PageRank 
References 
10
0.52
35
Authors
5
Name
Order
Citations
PageRank
Sheng Yu1171.27
Yun Cheng2232.15
Song-zhi Su3618.53
Guo-Rong Cai45811.42
Shaozi Li540354.27