Projects per year
Abstract
This paper presents a new method for 3D action recognition
with skeleton sequences (i.e., 3D trajectories of human
skeleton joints). The proposed method first transforms each
skeleton sequence into three clips each consisting of several
frames for spatial temporal feature learning using deep
neural networks. Each clip is generated from one channel
of the cylindrical coordinates of the skeleton sequence.
Each frame of the generated clips represents the temporal
information of the entire skeleton sequence, and incorporates
one particular spatial relationship between the joints.
The entire clips include multiple frames with different spatial
relationships, which provide useful spatial structural information
of the human skeleton. We propose to use deep
convolutional neural networks to learn long-term temporal
information of the skeleton sequence from the frames of the
generated clips, and then use a Multi-Task Learning Network
(MTLN) to jointly process all frames of the generated
clips in parallel to incorporate spatial structural information
for action recognition. Experimental results clearly
show the effectiveness of the proposed new representation
and feature learning method for 3D action recognition.
with skeleton sequences (i.e., 3D trajectories of human
skeleton joints). The proposed method first transforms each
skeleton sequence into three clips each consisting of several
frames for spatial temporal feature learning using deep
neural networks. Each clip is generated from one channel
of the cylindrical coordinates of the skeleton sequence.
Each frame of the generated clips represents the temporal
information of the entire skeleton sequence, and incorporates
one particular spatial relationship between the joints.
The entire clips include multiple frames with different spatial
relationships, which provide useful spatial structural information
of the human skeleton. We propose to use deep
convolutional neural networks to learn long-term temporal
information of the skeleton sequence from the frames of the
generated clips, and then use a Multi-Task Learning Network
(MTLN) to jointly process all frames of the generated
clips in parallel to incorporate spatial structural information
for action recognition. Experimental results clearly
show the effectiveness of the proposed new representation
and feature learning method for 3D action recognition.
| Original language | English |
|---|---|
| Title of host publication | Proceedings |
| Subtitle of host publication | 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 |
| Place of Publication | United States |
| Publisher | IEEE, Institute of Electrical and Electronics Engineers |
| Pages | 4570-4579 |
| Number of pages | 10 |
| ISBN (Electronic) | 9781538604571 |
| ISBN (Print) | 9781538604571 |
| Publication status | Published - 6 Nov 2017 |
| Event | 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 - Honolulu, United States Duration: 21 Jul 2017 → 26 Jul 2017 |
Publication series
| Name | Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 |
|---|---|
| Volume | 2017-January |
Conference
| Conference | 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 |
|---|---|
| Country/Territory | United States |
| City | Honolulu |
| Period | 21/07/17 → 26/07/17 |
Fingerprint
Dive into the research topics of 'A new representation of skeleton sequences for 3D action recognition'. Together they form a unique fingerprint.-
Advanced Computer Vision Techniques for Marine Ecology
Bennamoun, M., Boussaid, F., Kendrick, G. & Fisher, R.
ARC Australian Research Council
1/01/15 → 31/12/21
Project: Research
-
Advanced 3D Computer Vision Algorithms for 'Find and Grasp' Future Robots
ARC Australian Research Council
1/01/15 → 31/12/20
Project: Research
-
Revocable 2D/3D Shape Based Multimodal Hand Biometrics for Personal Identification & Verification
Sohel, F.
ARC Australian Research Council
1/01/12 → 29/06/17
Project: Research