FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single Image

Yang, Tsun-Yi; Chen, Yi-Ting; Lin, Yen‐Yu; Chuang, Yung-Yu

doi:10.1109/cvpr.2019.00118

Cited by 265 publications

(245 citation statements)

References 39 publications

Supporting

Mentioning

244

Contrasting

Unclassified

Order By: Relevance

“…Facial information recovery aims to use high-level information to perform estimations and has gained great success in recent years. Yang et al [2] proposed a method for head estimation from a single image without landmark or depth information. On the basis of regression and feature aggregation, they learned a fine-grained structure mapping, and their results outperformed many state-of-the-art methods in terms of efficiency.…”

Section: Related Workmentioning

confidence: 99%

“…Multiview data were required in Refs. [2,4] as input, such as multiview images or cameras, which cannot be used for direct video tracking. The results in Refs.…”

Section: Related Workmentioning

confidence: 99%

“…We compare our approach with two state-of-the-art methods, i.e., Hopenet [26] and FSA [2] , which only take RGB images or videos as input to generate recognition results in realtime. Hopenet proposes an elegant and robust way to determine pose by training a multiloss CNN and predict intrinsic Euler angles directly from image intensities rather than landmark-to-pose methods.…”

Section: Evaluation Criterionmentioning

confidence: 99%

See 2 more Smart Citations

Real-time facial pose estimation and tracking by coarse-to-fine iterative optimization

Yang

Jia

Yuan

et al. 2020

Tinshhua Sci. Technol.

View full text Add to dashboard Cite

We present a novel and efficient method for real-time multiple facial poses estimation and tracking in a single frame or video. First, we combine two standard convolutional neural network models for face detection and mean shape learning to generate initial estimations of alignment and pose. Then, we design a bi-objective optimization strategy to iteratively refine the obtained estimations. This strategy achieves faster speed and more accurate outputs. Finally, we further apply algebraic filtering processing, including Gaussian filter for background removal and extended Kalman filter for target prediction, to maintain real-time tracking superiority. Only general RGB photos or videos are required, which are captured by a commodity monocular camera without any priori or label. We demonstrate the advantages of our approach by comparing it with the most recent work in terms of performance and accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Multiview data were required in Refs. [2,4] as input, such as multiview images or cameras, which cannot be used for direct video tracking. The results in Refs.…”

Section: Related Workmentioning

confidence: 99%

Section: Evaluation Criterionmentioning

confidence: 99%

See 1 more Smart Citation

Real-time facial pose estimation and tracking by coarse-to-fine iterative optimization

Yang

Jia

Yuan

et al. 2020

Tinshhua Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…It showed that it can directly predict head rotation and highly outperform landmark-to-pose methods using state-of-the-art landmark detection methods. FSA-Net [47] provides attention for pose estimation and even proved to be a slight improvement over Hopenet [46].…”

Section: Gaze Estimationmentioning

confidence: 99%

“…The method to unite appearances was based on the kernel method of object tracking [46,47]. Consider that frame t i is the image frame at time t i .…”

Section: Uniting the Appearances Into A Sequencementioning

confidence: 99%

A Computer-Vision Based Application for Student Behavior Monitoring in Classroom

et al. 2019

View full text Add to dashboard Cite

Automated learning analytics is becoming an essential topic in the educational area, which needs effective systems to monitor the learning process and provides feedback to the teacher. Recent advances in visual sensors and computer vision methods enable automated monitoring of behavior and affective states of learners at different levels, from university to pre-school. The objective of this research was to build an automatic system that allowed the faculties to capture and make a summary of student behaviors in the classroom as a part of data acquisition for the decision making process. The system records the entire session and identifies when the students pay attention in the classroom, and then reports to the facilities. Our design and experiments show that our system is more flexible and more accurate than previously published work.

show abstract

Multi‐angle head pose classification with masks based on color texture analysis and stack generalization

Dong

Shi

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

Head pose classification is an important part of the preprocessing process of face recognition, which can independently solve application problems related to multi-angle. But, due to the impact of the COVID-19 coronavirus pandemic, more and more people wear masks to protect themselves, which covering most areas of the face. This greatly affects the performance of head pose classification. Therefore, this article proposes a method to classify the head pose with wearing a mask. This method focuses on the information that is helpful for head pose classification. First, the H-channel image of the HSV color space is extracted through the conversion of the color space.Then use the line portrait to extract the contour lines of the face, and train the convolutional neural networks to extract features in combination with the grayscale image.Finally, stacked generalization technology is used to fuse the output of the three classifiers to obtain the final classification result. The results on the MAFA dataset show that compared with the current advanced algorithm, the accuracy of our method is 94.14% on the front, 86.58% on the more side, and 90.93% on the side, which has better performance.

show abstract

FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single Image

Cited by 265 publications

References 39 publications

Real-time facial pose estimation and tracking by coarse-to-fine iterative optimization

Real-time facial pose estimation and tracking by coarse-to-fine iterative optimization

A Computer-Vision Based Application for Student Behavior Monitoring in Classroom

Multi‐angle head pose classification with masks based on color texture analysis and stack generalization

Contact Info

Product

Resources

About