Paper Info
Title
Discriminative Multi-View Dynamic Image Fusion for Cross-View 3-D Action Recognition
Abstract
Dramatic imaging viewpoint variation is the critical challenge toward action recognition for depth video. To address this, one feasible way is to enhance view-tolerance of visual feature, while still maintaining strong discriminative capacity. Multi-view dynamic image (MVDI) is the most recently proposed 3-D action representation manner that is able to compactly encode human motion information and 3-D visual clue well. However, it is still view-sensitive. To leverage its performance, a discriminative MVDI fusion method is proposed by us via multi-instance learning (MIL). Specifically, the dynamic images (DIs) from different observation viewpoints are regarded as the instances for 3-D action characterization. After being encoded using Fisher vector (FV), they are then aggregated by sum-pooling to yield the representative 3-D action signature. Our insight is that viewpoint aggregation helps to enhance view-tolerance. And, FV can map the raw DI feature to the higher dimensional feature space to promote the discriminative power. Meanwhile, a discriminative viewpoint instance discovery method is also proposed to discard the viewpoint instances unfavorable for action characterization. The wide-range experiments on five data sets demonstrate that our proposition can significantly enhance the performance of cross-view 3-D action recognition. And, it is also applicable to cross-view 3-D object recognition. The source code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/3huo/ActionView</uri> .
Year
DOI
Venue
2022
10.1109/TNNLS.2021.3070179
IEEE Transactions on Neural Networks and Learning Systems
Keywords
DocType
Volume
Cross-view 3-D action recognition,discriminative viewpoint instance discovery,Fisher vector (FV),multi-view dynamic image (MVDI),viewpoint aggregation
Journal
33
Issue
ISSN
Citations 
10
2162-237X
0
PageRank 
References 
Authors
0.34
50
7
Name
Order
Citations
PageRank
Wang Yancheng122.06
Yang Xiao223726.58
Junyi Lu300.34
Bo Tan431320.58
Zhiguo Cao531444.17
Zhenjun Zhang600.34
Joey Tianyi Zhou735438.60