Learning Deep Representation for Face Alignment with Auxiliary Attributes

Zhang, Zhanpeng; Luo, Ping; Loy, Chen Change; Tang, Xiaoou

doi:10.1109/tpami.2015.2469286

Cited by 405 publications

(309 citation statements)

References 50 publications

Supporting

Mentioning

308

Contrasting

Unclassified

Order By: Relevance

“…The CDSM reports [24], the third by SDM [23] and the bottom by TCDCN [28]. RLBF, SDM and TCDCN fail to handle profile or nearly profile faces, but FHM works well for all poses.…”

Section: B Experimental Resultsmentioning

confidence: 99%

Fast Landmark Localization With 3D Component Reconstruction and CNN for Cross-Pose Recognition

Hsu

Hsieh

Chan

2018

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Abstract-Two approaches are proposed for cross-pose face recognition, one is based on the 3D reconstruction of facial components and the other is based on the deep Convolutional Neural Network (CNN). Unlike most 3D approaches that consider holistic faces, the proposed approach considers 3D facial components. It segments a 2D gallery face into components, reconstructs the 3D surface for each component, and recognizes a probe face by component features. The segmentation is based on the landmarks located by a hierarchical algorithm that combines the Faster R-CNN for face detection and the Reduced Tree Structured Model for landmark localization. The core part of the CNN-based approach is a revised VGG network. We study the performances with different settings on the training set, including the synthesized data from 3D reconstruction, the real-life data from an in-the-wild database, and both types of data combined. We investigate the performances of the network when it is employed as a classifier or designed as a feature extractor. The two recognition approaches and the fast landmark localization are evaluated in extensive experiments, and compared to stateof-the-art methods to demonstrate their efficacy.

show abstract

“…The CDSM reports [24], the third by SDM [23] and the bottom by TCDCN [28]. RLBF, SDM and TCDCN fail to handle profile or nearly profile faces, but FHM works well for all poses.…”

Section: B Experimental Resultsmentioning

confidence: 99%

Fast Landmark Localization With 3D Component Reconstruction and CNN for Cross-Pose Recognition

Hsu

Hsieh

Chan

2018

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…In our experiments, we compared our methods with 12 state-of-the-art face alignment methods including FPLL (Zhu and Ramanan 2012), DRMF (Asthana et al 2013), RCPR (Burgos-Artizzu et al 2013), SDM (Xiong and la Torre 2013), GN-DPM (Tzimiropoulos and Pantic 2014), ESR (Cao et al 2012), LBF (Ren et al 2014), ERT (Kazemi and Sullivan 2014), CFSS (Zhu et al 2015), CFAN (Zhang et al 2014), BPCPR (Sun et al 2015) and TCDCN (Zhang et al 2016). Table 1 tabulates comparisons of the averaged errors of our method to those state-of-the-art methods, where the results were directly cropped from the original papers.…”

Section: Comparisons With State-of-the-art Methodsmentioning

confidence: 99%

Multiscale recurrent regression networks for face alignment

Wang

Sun

et al. 2017

Appl Inform

View full text Add to dashboard Cite

“…Our proposed method is also reminiscent of previously proposed deep learning methods for face alignment [43,55,47,61,63,62]. Sun et al [47] and Zhou et al [63] propose to use independent Convolutional Neural Networks (CNN) to perform coarse-to-fine shape searching.…”

Section: Related Workmentioning

confidence: 98%

Mnemonic Descent Method: A Recurrent Process Applied for End-to-End Face Alignment

Trigeorgis

Snape

Nicolaou

et al. 2016

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

320

278

View full text Add to dashboard Cite

Cascaded regression has recently become the method of choice for solving non-linear least squares problems such as deformable image alignment. Given a sizeable training set, cascaded regression learns a set of generic rules that are sequentially applied to minimise the least squares problem. Despite the success of cascaded regression for problems such as face alignment and head pose estimation, there are several shortcomings arising in the strategies proposed thus far. Specifically, (a) the regressors are learnt independently, (b) the descent directions may cancel one another out and (c) handcrafted features (e.g., HoGs, SIFT etc.) are mainly used to drive the cascade, which may be sub-optimal for the task at hand. In this paper, we propose a combined and jointly trained convolutional recurrent neural network architecture that allows the training of an end-to-end to system that attempts to alleviate the aforementioned drawbacks. The recurrent module facilitates the joint optimisation of the regressors by assuming the cascades form a nonlinear dynamical system, in effect fully utilising the information between all cascade levels by introducing a memory unit that shares information across all levels. The convolutional module allows the network to extract features that are specialised for the task at hand and are experimentally shown to outperform hand-crafted features. We show that the application of the proposed architecture for the problem of face alignment results in a strong improvement over the current state-of-the-art.

show abstract

Learning Deep Representation for Face Alignment with Auxiliary Attributes

Cited by 405 publications

References 50 publications

Fast Landmark Localization With 3D Component Reconstruction and CNN for Cross-Pose Recognition

Fast Landmark Localization With 3D Component Reconstruction and CNN for Cross-Pose Recognition

Multiscale recurrent regression networks for face alignment

Mnemonic Descent Method: A Recurrent Process Applied for End-to-End Face Alignment

Contact Info

Product

Resources

About