Face alignment by Component Adaptive Mechanism

Wan, Jun; Li, Jing; Chang, Jun; Wu, Yujia; Xiao, Yafu; Li, Xuefei; Zheng, Hao

doi:10.1016/j.neucom.2018.10.068

Cited by 10 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) CCDN is similar to CCL [24] and CAM [53] that firstly partition the optimization space of facial landmark detection into multiple domains of homogeneous descent and then fuse the regression results of relevant domains to further improve the accuracy of facial landmark detection. Compared to CCL and CAM, our method achieves this in an end-to-end way, i.e., by the proposed cross-order cross-semantic deep network.…”

Section: Resultsmentioning

confidence: 99%

Robust facial landmark detection by cross-order cross-semantic deep network

et al. 2021

Self Cite

View full text Add to dashboard Cite

Recently, convolutional neural networks (CNNs)-based facial landmark detection methods have achieved great success. However, most of existing CNN-based facial landmark detection methods have not attempted to activate multiple correlated facial parts and learn different semantic features from them that they can not accurately model the relationships among the local details and can not fully explore more discriminative and fine semantic features, thus they suffer from partial occlusions and large pose variations. To address these problems, we propose a cross-order cross-semantic deep network (CCDN) to boost the semantic features learning for robust facial landmark detection. Specifically, a crossorder two-squeeze multi-excitation (CTM) module is proposed to introduce the cross-order channel correlations for more discriminative representations learning and multiple attention-specific part activation. Moreover, a novel cross-order cross-semantic (COCS) regularizer is designed to drive the network to learn cross-order cross-semantic features from different activation for facial landmark detection. It is interesting to show that by integrating the CTM module and COCS regularizer, the proposed CCDN can effectively activate and learn more Fully documented templates are available in the elsarticle package on CTAN.

show abstract

Section: Resultsmentioning

confidence: 99%

Robust facial landmark detection by cross-order cross-semantic deep network

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Error Failure human 5.6 (-) -PCPR [16] 8.50 (7.49) 20.00 HPM [43] 7.50 (5.88) 13.00 CCR [44] 7.03 (3.53) 10.9 DRDA [45] 6.46 (3.21) 6.00 RAR [38] 6.03 (2.84) 4.14 DAC-CSR(CVPR17) [46] 6.03 (3.07) 4.73 CAM [47] 5.95 (2.67) 3.94 CRD [22] 5.72 (2.44) 3.76 LAB(CVPR18) [10] 5.58 (2.17) 2.76 ODN(CVPR19) [21] 5. 30 ods, which indicates that the proposed HSR method and MCG model can be seamlessly integrated into a multi-order highprecision hourglass network, thus achieving robust and highprecision face alignment for challenging scenarios.…”

Section: Methodsmentioning

confidence: 99%

Robust Face Alignment by Multi-Order High-Precision Hourglass Network

Wan

Lai

Liu

et al. 2021

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Heatmap regression (HR) has become one of the mainstream approaches for face alignment and has obtained promising results under constrained environments. However, when a face image suffers from large pose variations, heavy occlusions and complicated illuminations, the performances of HR methods degrade greatly due to the low resolutions of the generated landmark heatmaps and the exclusion of important high-order information that can be used to learn more discriminative features. To address the alignment problem for faces with extremely large poses and heavy occlusions, this paper proposes a heatmap subpixel regression (HSR) method and a multi-order cross geometry-aware (MCG) model, which are seamlessly integrated into a novel multi-order high-precision hourglass network (MHHN). The HSR method is proposed to achieve high-precision landmark detection by a well-designed subpixel detection loss (SDL) and subpixel detection technology (SDT). At the same time, the MCG model is able to use the proposed multi-order cross information to learn more discriminative representations for enhancing facial geometric constraints and context information. To the best of our knowledge, this is the first study to explore heatmap subpixel regression for robust and high-precision face alignment. The experimental results from challenging benchmark datasets demonstrate that our approach outperforms state-of-theart methods in the literature.

show abstract

“…DeCaFA [19] is an end-to-end deep convolutional cascade architecture for face alignment; it uses fully-convolutional stages to keep full spatial resolution throughout the cascade and significantly outperforms existing approaches on challenging databases. Wang et al [20,21] put forward the idea of combining the face GAN network with the cascaded network to improve the face alignment algorithm, realize the accurate positioning of key points of the face, and solve the problem of facial expression lighting and occlusion for face detection.…”

Section: Related Workmentioning

confidence: 99%

Facial Landmark Detection Using Generative Adversarial Network Combined with Autoencoder for Occlusion

Liu

Zheng

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The performance of the facial landmark detection model will be in trouble when it is under occlusion condition. In this paper, we present an effective framework with the objective of addressing the occlusion problem for facial landmark detection, which includes a generative adversarial network with improved autoencoders (GAN-IAs) and deep regression networks. In this model, GAN-IA can restore the occluded face region by utilizing skip concatenation among feature maps to keep more details. Meanwhile, self-attention mechanism that is effective in modeling long-range dependencies is employed to recover harmonious images for occluded faces. Deep regression networks are used to learn a nonlinear mapping from facial appearance to facial shape. Benefited from the mutual cooperation of GAN-IA and deep regression networks, a robust facial landmark detection model is achieved for the occlusion problem and the performance of the model achieves obviously improvement on challenging datasets.

show abstract

Face alignment by Component Adaptive Mechanism

Cited by 10 publications

References 15 publications

Robust facial landmark detection by cross-order cross-semantic deep network

Robust facial landmark detection by cross-order cross-semantic deep network

Robust Face Alignment by Multi-Order High-Precision Hourglass Network

Facial Landmark Detection Using Generative Adversarial Network Combined with Autoencoder for Occlusion

Contact Info

Product

Resources

About