Loading...
Loading...

Go to the content (press return)

Action tube extraction based 3D-CNN for RGB-D action recognition

Author
Xu , Z.; Vilaplana, V.; Morros, J.R.
Type of activity
Presentation of work at congresses
Name of edition
16th International Conference on Content-Based Multimedia Indexing
Date of publication
2018
Presentation's date
2018-11-04
Book of congress proceedings
16th International Conference on Content-Based Multimedia Indexing: 4-6 September, 2018 La Rochelle, France
First page
1
Last page
6
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
DOI
https://doi.org/10.1109/CBMI.2018.8516450 Open in new window
Repository
http://hdl.handle.net/2117/128191 Open in new window
Abstract
In this paper we propose a novel action tube extractor for RGB-D action recognition in trimmed videos. The action tube extractor takes as input a video and outputs an action tube. The method consists of two parts: spatial tube extraction and temporal sampling. The first part is built upon MobileNet-SSD and its role is to define the spatial region where the action takes place. The second part is based on the structural similarity index (SSIM) and is designed to remove frames without obvious motio...
Citation
Xu, Z.; Vilaplana, V.; Morros, J.R. Action tube extraction based 3D-CNN for RGB-D action recognition. A: International Workshop on Content-Based Multimedia Indexing. "16th International Conference on Content-Based Multimedia Indexing: 4-6 September, 2018 La Rochelle, France". Institute of Electrical and Electronics Engineers (IEEE), 2018, p. 1-6.
Keywords
3D-CNN, CNN models, action recognition, action tube extraction extraction, indexing (of information), spatial regions, state-of-the-art methods, structural similarity indices (SSIM), temporal sampling, tubes (components), two-stream
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

Attachments