Web-Shaped Model for Head Pose Estimation: An Approach for Best Exemplar Selection

Barra, Paola; Barra, Silvio; Bisogni, Carmen; Marsico, Maria De; Nappi, Michele

doi:10.1109/tip.2020.2984373

Cited by 43 publications

(22 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparisons on the Pointing’04 Dataset. The proposed head-pose estimation method is compared with MGD [ 53 ], kCovGa [ 54 ], CovGA [ 54 ], CNN [ 55 ], fuzzy [ 56 ], MSHF [ 57 ], SAE-XGB [ 58 ], Hopenet [ 26 ], FSA-Net [ 27 ], hGLLiM [ 59 ], 3DDFA [ 37 ] and 4C_4S_var4 [ 36 ]. Among them, MGD, kCovGa, CovGA, CNN, fuzzy, MSHF, hGLLiM, and SAE-XGB have been trained on the Pointing’04 dataset following a five-fold cross-validation protocol; Hopenet and FSA-Net have been trained on another dataset called 300W-LP, while 3DDFA, 4C_4S_var4 and our method have not been trained with any head-pose label.…”

Section: Experimental Resultsmentioning

confidence: 99%

“…Recently, Andrea et al [ 35 ] proposed exploiting a quad-tree based representation of facial features and estimate head pose by guiding the subdivision of the locations of a set of landmarks detected over the face image into smaller and smaller quadrants. In [ 36 ], a web-shaped model was proposed to associate each of them to a specific face sector over the detected landmarks. Although this method does not need to train on datasets with head-pose labels, it performs poorly under large poses.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Head Pose Estimation through Keypoints Matching between Reconstructed 3D Face Model and 2D Image

Liu

Huo

et al. 2021

Sensors

View full text Add to dashboard Cite

Mainstream methods treat head pose estimation as a supervised classification/regression problem, whose performance heavily depends on the accuracy of ground-truth labels of training data. However, it is rather difficult to obtain accurate head pose labels in practice, due to the lack of effective equipment and reasonable approaches for head pose labeling. In this paper, we propose a method which does not need to be trained with head pose labels, but matches the keypoints between a reconstructed 3D face model and the 2D input image, for head pose estimation. The proposed head pose estimation method consists of two components: the 3D face reconstruction and the 3D–2D matching keypoints. At the 3D face reconstruction phase, a personalized 3D face model is reconstructed from the input head image using convolutional neural networks, which are jointly optimized by an asymmetric Euclidean loss and a keypoint loss. At the 3D–2D keypoints matching phase, an iterative optimization algorithm is proposed to match the keypoints between the reconstructed 3D face model and the 2D input image efficiently under the constraint of perspective transformation. The proposed method is extensively evaluated on five widely used head pose estimation datasets, including Pointing’04, BIWI, AFLW2000, Multi-PIE, and Pandora. The experimental results demonstrate that the proposed method achieves excellent cross-dataset performance and surpasses most of the existing state-of-the-art approaches, with average MAEs of 4.78∘ on Pointing’04, 6.83∘ on BIWI, 7.05∘ on AFLW2000, 5.47∘ on Multi-PIE, and 5.06∘ on Pandora, although the model of the proposed method is not trained on any of these five datasets.

show abstract

Section: Experimental Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Head Pose Estimation through Keypoints Matching between Reconstructed 3D Face Model and 2D Image

Liu

Huo

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…As the proposed approach deals with the normalization of faces of arbitrary poses, the head pose estimation may also be considered as part of related work. A recent approach proposed by Barra et al [12] first detects the facial landmarks, and applies the web-shaped model to associate each landmark to a specific face sector. The obtained information is used to build a feature vector to infer the head pose.…”

Section: Related Workmentioning

confidence: 99%

Dual-View Normalization for Face Recognition

Hsu

Tang

2020

IEEE Access

View full text Add to dashboard Cite

Face normalization refers to a family of approaches that rotate a non-frontal face to the frontal pose for better handling of face recognition. While a great majority of face normalization methods focus on frontal pose only, we proposed a framework for dual-view normalization that generates a frontal pose and an additional yaw-45 • pose to an input face of an arbitrary pose. The proposed Dual-View Normalization (DVN) framework is designed to learn the transformation from a source set to two normal sets. The source set contains faces collected in the wild and covers a wide scope of variables. One normal set contains face images taken under controlled conditions and all faces are in frontal pose and balanced in illumination. The other normal set contains faces also taken under controlled conditions and balanced in illumination, but in 45 • pose. The DVN framework is composed of one face encoder, two layers of generators, and two sets of discriminators. The encoder is made of a state-of-the-art face recognition network, which is not updated during training, and it acts as a facial feature extractor. The Layer-1 generators are trained on both the source and normal sets, aiming at learning the transformation from the source set to both normal sets. The trained generators can transform an arbitrary face into a pair of normalized faces, one in frontal pose and the other in 45 • pose. The Layer-2 generators are trained to enhance the identity preservation of the faces made by the Layer-1 generators by minimizing the cross-pose identity loss. The discriminators are trained to ensure the photo-realistic quality of the dual-view normalized face images generated by the generators. The loss functions employed in the generators and the discriminators are designed to achieve satisfactory dual-view normalization outcomes and identity preservation. We verify the DVN framework on benchmark databases and compare with other state-of-the-art approaches for tackling face recognition.

show abstract

“…This method significantly improves the performance of the dataset where subjects are in movement. Recently, [30] relies on a cascade of two models and applies a web-shaped model over the detected landmarks to associate each landmark with a specific target area. This method detects the target at a reasonable distance and resolution to capture the best frame in the video.…”

Section: A Human Pose Estimationmentioning

confidence: 99%

Deep High-Resolution Network With Double Attention Residual Blocks for Human Pose Estimation

et al. 2020

View full text Add to dashboard Cite

Web-Shaped Model for Head Pose Estimation: An Approach for Best Exemplar Selection

Cited by 43 publications

References 42 publications

Head Pose Estimation through Keypoints Matching between Reconstructed 3D Face Model and 2D Image

Head Pose Estimation through Keypoints Matching between Reconstructed 3D Face Model and 2D Image

Dual-View Normalization for Face Recognition

Deep High-Resolution Network With Double Attention Residual Blocks for Human Pose Estimation

Contact Info

Product

Resources

About