Face alignment by coarse-to-fine shape searching

Zhu, Shizhan; Li, Cheng; Loy, Chen Change; Tang, Xiaoou

doi:10.1109/cvpr.2015.7299134

Cited by 134 publications

(31 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is evident from the experimental results that the improved PFLD network designed in this paper has a certain degree of improvement in accuracy over the current mainstream methods for recognizing facial landmarks with different test sets. LBF [9] 4.95 11.98 6.32 CFSS [10] 4.73 9.98 5.76 MDM [11] 4.83 10.14 5.88 Two-Stage [12] 4.36 7. In summary, it can be seen that the method in this paper has obvious advantages over the current mainstream facial landmark detection accuracy and is more suitable for the needs of facial landmark detection tasks.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

Research on facial landmark detection algorithm based on improved attention mechanism

Cui

Shi²,

Cui³

et al. 2023

International Conference on Artificial Intelligence, Virtual Reality, and Visualization (AIVRV 2022)

View full text Add to dashboard Cite

In recent years, facial landmark detection has assumed an important role in various fields. However, the current facial landmark detection algorithms are still lacking in recognition accuracy. In order to solve the above problem, this paper uses Ghost bottleneck to replace the original bottleneck on the basis of the original model of PFLD model, and adds and improves the CBAM attention mechanism. The improved PFLD model increases the ability of the model to extract facial landmark and improves the accuracy of the algorithm. The improved model has high accuracy and low parametric number and improves the accuracy of facial landmark detection. It also provides a new idea for facial landmark detection task.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Research on facial landmark detection algorithm based on improved attention mechanism

Cui

Shi²,

Cui³

et al. 2023

International Conference on Artificial Intelligence, Virtual Reality, and Visualization (AIVRV 2022)

View full text Add to dashboard Cite

show abstract

“…Setting AUC FR M 3 CSR [43] FSL (100%) 47.52 5.50 CFSS [42] 49.87 5.05 DenseReg+MDM [44] 52.19 3.67 JMFA [45] 54.85 1.00 LAB [19] 58.85 0.83 3FabRec [6] 54.61 0.17 HybridMatch (ours) SSL (20%) 60.56 0.17 To investigate the effectiveness of our HybridMatch, we compare the proposed method with other fully-supervised models using FR and AUC metrics. We evaluate the methods on the 300-W testset.…”

Section: Methodsmentioning

confidence: 99%

“…We use Inter-ocular norm for 300-W and WFLW datasets, which defines L as the outereye-corner distance for quantitative evaluations as following [6,7]. For AFLW, we define L as the width of the square bounding-box following Zhu et al [42].…”

Section: ) Nmementioning

confidence: 99%

HybridMatch: Semi-Supervised Facial Landmark Detection via Hybrid Heatmap Representations

et al. 2023

View full text Add to dashboard Cite

Facial landmark detection is an essential task in face-processing techniques. Traditional methods however require expensive pixel-level labels. Semi-supervised facial landmark detection has been explored as an alternative but previous approaches only focus on training-oriented issues (e.g., noisy pseudolabels in the semi-supervised learning), neglecting task-oriented issues (i.e., the quantization error in the landmark detection). We argue that semi-supervised landmark detectors should resolve the two technical issues simultaneously. Through a simple experiment, we found that task-and training-oriented solutions may negatively influence each other, thus eliminating their negative interactions is important. To this end, we devise a new heatmap regression framework via hybrid representation, namely HybridMatch. We utilize both 1-D and 2-D heatmap representations. Here, the 1-D and 2-D heatmap help alleviate the task-oriented and the training-oriented issues, respectively. To exploit the advantages of our hybrid representation, we introduce curriculum learning; relying more on the 2-D heatmap at the early training stage and gradually increasing the effects of the 1-D heatmap. By resolving the two issues simultaneously, we can capture more precise landmark points than existing methods with only a few annotated data. Extensive experiments show that HybridMatch achieves state-of-the-art performance on three benchmark datasets, especially showing 26.3% NME improvement over the existing method in the 300-W full set at 5% data ratio. Surprisingly, our method records a comparable performance, 5.04 (challenging set in the 300-W) to the fully-supervised facial landmark detector 5.03. The remarkable performance of HybridMatch shows its potential as a practical alternative to the fully-supervised model.

show abstract

“…Zhu et al [52] 8.16 DRMF [53] 6.70 ESR [11] 5.70 RCPR [43] 5.93 SDM [5] 5.50 GN-DPM [54] 5.69 CFAN [25] 5.53 CFSS [51] 4.63 CFSS Practical [51] 4.72 TCDCN [55] 4.60 Ours 3.11…”

Section: Methods 68 Ptsmentioning

confidence: 99%

“…Our proposed method substantially reduced the mean error rate. The second-best mean error rate in the table is the CFSS [51] method, which has a mean error of 4.87%. Our method is considerably superior with an error rate of only 3.52%.…”

Section: Comparison With Lfpw Datasetmentioning

confidence: 99%

Dilated Skip Convolution for Facial Landmark Detection

Chim

Lee

Park

2019

Sensors

View full text Add to dashboard Cite

Facial landmark detection has gained enormous interest for face-related applications due to its success in facial analysis tasks such as facial recognition, cartoon generation, face tracking and facial expression analysis. Many studies have been proposed and implemented to deal with the challenging problems of localizing facial landmarks from given images, including large appearance variations and partial occlusion. Studies have differed in the way they use the facial appearances and shape information of input images. In our work, we consider facial information within both global and local contexts. We aim to obtain local pixel-level accuracy for local-context information in the first stage and integrate this with knowledge of spatial relationships between each key point in a whole image for global-context information in the second stage. Thus, the pipeline of our architecture consists of two main components: (1) a deep network for local-context subnet that generates detection heatmaps via fully convolutional DenseNets with additional kernel convolution filters and (2) a dilated skip convolution subnet—a combination of dilated convolutions and skip-connections networks—that are in charge of robustly refining the local appearance heatmaps. Through this proposed architecture, we demonstrate that our approach achieves state-of-the-art performance on challenging datasets—including LFPW, HELEN, 300W and AFLW2000-3D—by leveraging fully convolutional DenseNets, skip-connections and dilated convolution architecture without further post-processing.

show abstract

Face alignment by coarse-to-fine shape searching

Cited by 134 publications

References 30 publications

Research on facial landmark detection algorithm based on improved attention mechanism

Research on facial landmark detection algorithm based on improved attention mechanism

HybridMatch: Semi-Supervised Facial Landmark Detection via Hybrid Heatmap Representations

Dilated Skip Convolution for Facial Landmark Detection

Contact Info

Product

Resources

About