Feng, Zhenhua, Kittler, Josef, Christmas, William et al. (2 more authors) (2017) Dynamic attention-controlled cascaded shape regression exploiting training data augmentation and fuzzy-set sample weighting. In: Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 21-26 Jul 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE , USA , pp. 3681-3686.
Abstract
We present a new Cascaded Shape Regression (CSR) architecture, namely Dynamic Attention-Controlled CSR (DAC-CSR), for robust facial landmark detection on unconstrained faces. Our DAC-CSR divides facial landmark detection into three cascaded sub-tasks: face bounding box refinement, general CSR and attention-controlled CSR. The first two stages refine initial face bounding boxes and output intermediate facial landmarks. Then, an online dynamic model selection method is used to choose appropriate domain-specific CSRs for further landmark refinement. The key innovation of our DAC-CSR is the fault-tolerant mechanism, using fuzzy set sample weighting, for attentioncontrolled domain-specific model training. Moreover, we advocate data augmentation with a simple but effective 2D profile face generator, and context-aware feature extraction for better facial feature representation. Experimental results obtained on challenging datasets demonstrate the merits of our DAC-CSR over the state-of-the-art methods.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2017, The Author(s). |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Depositing User: | Pure (York) |
Date Deposited: | 05 Nov 2019 09:40 |
Last Modified: | 16 Oct 2024 11:05 |
Published Version: | https://doi.org/10.1109/CVPR.2017.392 |
Status: | Published |
Publisher: | IEEE |
Series Name: | IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
Identification Number: | 10.1109/CVPR.2017.392 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:153124 |
Download
Filename: Feng_Dynamic_Attention_Controlled_Cascaded_CVPR_2017_paper.pdf
Description: Feng_Dynamic_Attention-Controlled_Cascaded_CVPR_2017_paper
Licence: CC-BY 2.5