2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition 2018
DOI: 10.1109/cvpr.2018.00047
|View full text |Cite
|
Sign up to set email alerts
|

Style Aggregated Network for Facial Landmark Detection

Abstract: Recent advances in facial landmark detection achieve success by learning discriminative features from rich deformation of face shapes and poses. Besides the variance of faces themselves, the intrinsic variance of image styles, e.g., grayscale vs. color images, light vs. dark, intense vs. dull, and so on, has constantly been overlooked. This issue becomes inevitable as increasing web images are collected from various sources for training neural networks. In this work, we propose a style-aggregated approach to d… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
227
0
1

Year Published

2018
2018
2022
2022

Publication Types

Select...
5
2

Relationship

1
6

Authors

Journals

citations
Cited by 293 publications
(228 citation statements)
references
References 59 publications
(143 reference statements)
0
227
0
1
Order By: Relevance
“…CPM+SBR [5] employs landmark registration to regularize training. SAN [4] uses adversarial networks to convert images from different styles to an aggregated style, upon which regression is performed. This aggregated style space thus serve as an intermediate representation that is more convenient for training.…”
Section: Related Workmentioning
confidence: 99%
“…CPM+SBR [5] employs landmark registration to regularize training. SAN [4] uses adversarial networks to convert images from different styles to an aggregated style, upon which regression is performed. This aggregated style space thus serve as an intermediate representation that is more convenient for training.…”
Section: Related Workmentioning
confidence: 99%
“…The classic model-based methods ASMs [27], AAMs [7,17,23,32], CLMs [19,33], ESR [3], SDM [41], CFSS [46], and deep convolutional neural wetwork methods, e.g. TCDCN [45], FAN [1], DSRN [26], RFLD [25], SAN [8], LAB [38] have obtained increasingly excellent performance in static images under different poses, light conditions, expressions, etc. However, few works in the literature of face alignment pay attention to the motion blur.…”
Section: Related Work 21 Facial Landmark Detectionmentioning
confidence: 99%
“…This experiment is conducted to demonstrate that our algorithm is capable to handle artificial motion blur, and accurately detect facial landmarks. We re-implemented several typical state-of-the-art algorithms for comparison, including RFLD [25], SAN [8] and LAB [38]. For a fair comparison, we made great efforts to reproduce the comparable results reported in their papers.…”
Section: Evaluation On Blurred-300vwmentioning
confidence: 99%
See 2 more Smart Citations