Action Recognition With Gradient Boundary Convolutional Network
Keywords
Action recognition; Convolutional network; Gradient boundary
Abstract
Deep learning features for video action recognition are usually learned from RGB/gray images, image gradients, and optical flows. The single modality of the input data can describe one characteristic of the human action such as appearance structure or motion information. In this paper, we propose a high efficient gradient boundary convolutional network (ConvNet) to simultaneously learn spatio-temporal feature from the single modality data of gradient boundaries. The gradient boundaries represent both local spacial structure and motion information of action video. The gradient boundaries also have less background noise compared to RGB/gray images and image gradients. Extensive experiments are conducted on two popular and challenging action benchmarks, the UCF101 and the HMDB51 action datasets. The proposed deep gradient boundary feature achieves competitive performances on both benchmarks.
Publication Date
2-20-2018
Publication Title
Proceedings - International Conference on Image Processing, ICIP
Volume
2017-September
Number of Pages
1047-1051
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICIP.2017.8296441
Copyright Status
Unknown
Socpus ID
85045315693 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85045315693
STARS Citation
Chen, Huafeng; Chen, Jun; Chen, Chen; and Hu, Ruimin, "Action Recognition With Gradient Boundary Convolutional Network" (2018). Scopus Export 2015-2019. 8863.
https://stars.library.ucf.edu/scopus2015/8863