Search: onr:"swepub:oai:research.chalmers.se:d11cd1cf-4dfa-4060-8ac1-b3e03d6016e5" >
Feature Boosting Ne...
Feature Boosting Network for 3D Pose Estimation
-
- Liu, Jun (author)
- Nanyang Technological University
-
- Ding, Henghui (author)
- Nanyang Technological University
-
- Shahroudy, Amir, 1981 (author)
- Chalmers tekniska högskola,Chalmers University of Technology
-
show more...
-
- Duan, Ling Yu (author)
- Beijing University of Technology
-
- Jiang, Xudong (author)
- Nanyang Technological University
-
Wang, Gang (author)
-
- Kot, Alex C. (author)
- Nanyang Technological University
-
show less...
-
(creator_code:org_t)
- 2020
- 2020
- English.
-
In: IEEE Transactions on Pattern Analysis and Machine Intelligence. - 1939-3539 .- 0162-8828. ; 42:2, s. 494-501
- Related links:
-
https://research.cha...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- In this paper, a feature boosting network is proposed for estimating 3D hand pose and 3D body pose from a single RGB image. In this method, the features learned by the convolutional layers are boosted with a new long short-term dependence-aware (LSTD) module, which enables the intermediate convolutional feature maps to perceive the graphical long short-term dependency among different hand (or body) parts using the designed Graphical ConvLSTM. Learning a set of features that are reliable and discriminatively representative of the pose of a hand (or body) part is difficult due to the ambiguities, texture and illumination variation, and self-occlusion in the real application of 3D pose estimation. To improve the reliability of the features for representing each body part and enhance the LSTD module, we further introduce a context consistency gate (CCG) in this paper, with which the convolutional feature maps are modulated according to their consistency with the context representations. We evaluate the proposed method on challenging benchmark datasets for 3D hand pose estimation and 3D full body pose estimation. Experimental results show the effectiveness of our method that achieves state-of-the-art performance on both of the tasks.
Subject headings
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Robotteknik och automation (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Robotics (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Keyword
- context consistency gate
- 3D pose estimation
- long short-term dependency
- convolutional LSTM
Publication and Content Type
- art (subject category)
- ref (subject category)
Find in a library
To the university's database