Face detection has been well studied for many years and one of remaining challenges is to detect small, blurred and partially occluded faces in uncontrolled environment. This paper proposes a novel contextassisted single shot face detector, named PyramidBox to handle the hard face detection problem. Observing the importance of the context, we improve the utilization of contextual information in the following three aspects. First, we design a novel context anchor to supervise high-level contextual feature learning by a semi-supervised method, which we call it PyramidAnchors. Second, we propose the Low-level Feature Pyramid Network to combine adequate high-level context semantic feature and Low-level facial feature together, which also allows the PyramidBox to predict faces of all scales in a single shot. Third, we introduce a contextsensitive structure to increase the capacity of prediction network to improve the final accuracy of output. In addition, we use the method of Data-anchor-sampling to augment the training samples across different scales, which increases the diversity of training data for smaller faces. By exploiting the value of context, PyramidBox achieves superior performance among the state-of-the-art over the two common face detection benchmarks, FDDB and WIDER FACE. Our code is available in Pad-dlePaddle: https://github.com/PaddlePaddle/models/tree/develop/ fluid/face_detection.
Batteries
based on Zn and other two-valent metals can be nearly
ideal charge storage devices because of their high energy density
combined with reliability, earth-abundance, and low flammability.
Searching for high-performance positive electrodes with good rate
capability and adequate cycle life is currently a hot topic and a
great challenge for developing zinc batteries. Here, a binder-free
3D porous graphene aerogel-supported α-MnO2 cathode
(G-MnO2) is synthesized via a facile and scalable hydrogel
method. The hybrid cathode of α-MnO2 nanotube attached
on highly conductive interconnected graphene frameworks enables rechargeable
Zn/G-MnO2 batteries with a high capacity of 321 mAhg–1 at 0.2C (1C = 240 mAhg–1), good
rate capability, and ultralong cycle life (91% capacity retention
over 300 cycles at a high current rate 3C). These findings open the
pathway to a large family of low-cost high-performance Zn-batteries
and potentially other two-valent metals for a wide range of applications.
Industrial wastewater containing dyes have led to global water scarcity and been severely damaging to human health. The demand for the exploration of practical and cost-effective dyes removal treatment is...
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.