Face parsing has recently attracted increasing interest due to its numerous application potentials, such as facial make up and facial image generation. In this paper, we make contributions on face parsing task from two aspects. First, we develop a high-efficiency framework for pixel-level face parsing annotating and construct a new large-scale Landmark guided face Parsing dataset (LaPa). It consists of more than 22,000 facial images with abundant variations in expression, pose and occlusion, and each image of LaPa is provided with an 11-category pixel-level label map and 106-point landmarks. The dataset is publicly accessible to the community for boosting the advance of face parsing.1 Second, a simple yet effective Boundary-Attention Semantic Segmentation (BASS) method is proposed for face parsing, which contains a three-branch network with elaborately developed loss functions to fully exploit the boundary information. Extensive experiments on our LaPa benchmark and the public Helen dataset show the superiority of our proposed method.
Facial landmark localization is a very crucial step in numerous face related applications, such as face recognition, facial pose estimation, face image synthesis, etc. However, previous competitions on facial landmark localization (i.e., the 300-W, 300-VW and Menpo challenges) aim to predict 68-point landmarks, which are incompetent to depict the structure of facial components. In order to overcome this problem, we construct a challenging dataset, named JDlandmark. Each image is manually annotated with 106point landmarks. This dataset covers large variations on pose and expression, which brings a lot of difficulties to predict accurate landmarks. We hold a 106-point facial landmark localization competition 1 on this dataset in conjunction with IEEE International Conference on Multimedia and Expo (ICME) 2019. The purpose of this competition is to discover effective and robust facial landmark localization approaches.
With the increasing application of explosive welding structures in many engineering fields, interface bonding state detection has become more and more significant to avoid catastrophic accidents. However, the complexity of the interface bonding state makes this task challenging. In this paper, a new method based on ensemble empirical mode decomposition (EEMD) and sensitive intrinsic mode function (IMF) time entropy is proposed for this task. As a self-adaptive non-stationary signal analysis method, EEMD can decompose a complicated signal into a set of IMFs with truly physical meaning, which is beneficial to allocate the structural vibration response signal containing a wealth of bonding state information to certain IMFs. Then, the time entropies of these IMFs are calculated to quantitatively assess the bonding state of the explosive welding structure. However, the IMF time entropies have different sensitivities to the bonding state. Therefore, the most sensitive IMF time entropy is selected based on a distance evaluation technique to detect the bonding state of explosive welding structures. The proposed method is applied to bonding state detection of explosive welding pipes in three cases, and the results demonstrate its effectiveness.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.