Institution
Wuhan University
Education•Wuhan, China•
About: Wuhan University is a education organization based out in Wuhan, China. It is known for research contribution in the topics: Population & Feature extraction. The organization has 92849 authors who have published 92882 publications receiving 1691049 citations. The organization is also known as: WHU & Wuhan College.
Papers published on a yearly basis
Papers
More filters
••
TL;DR: In this article, the authors present a review of the recent developments in this field, and focus on two categories of PNIPAAm-based copolymer micelles as smart drug delivery systems.
635 citations
••
01 Jun 2019TL;DR: The core idea of RoI Transformer is to apply spatial transformations on RoIs and learn the transformation parameters under the supervision of oriented bounding box (OBB) annotations.
Abstract: Object detection in aerial images is an active yet challenging task in computer vision because of the bird’s-eye view perspective, the highly complex backgrounds, and the variant appearances of objects. Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects. This leads to the common misalignment between the final object classification confidence and localization accuracy. In this paper, we propose a RoI Transformer to address these problems. The core idea of RoI Transformer is to apply spatial transformations on RoIs and learn the transformation parameters under the supervision of oriented bounding box (OBB) annotations. RoI Transformer is with lightweight and can be easily embedded into detectors for oriented object detection. Simply apply the RoI Transformer to light head RCNN has achieved state-of-the-art performances on two common and challenging aerial datasets, i.e., DOTA and HRSC2016, with a neglectable reduction to detection speed. Our RoI Transformer exceeds the deformable Position Sensitive RoI pooling when oriented bounding-box annotations are available. Extensive experiments have also validated the flexibility and effectiveness of our RoI Transformer.
634 citations
••
TL;DR: In this article, a type of polymer electrolyte fuel cells (PEFC) employing a hydroxide ion-conductive polymer, quaternary ammonium polysulphone, as alkaline electrolyte and nonprecious metals, chromium-decorated nickel and silver, as the catalyst for the negative and positive electrodes, respectively.
Abstract: In recent decades, fuel cell technology has been undergoing revolutionary developments, with fundamental progress being the replacement of electrolyte solutions with polymer electrolytes, making the device more compact in size and higher in power density. Nowadays, acidic polymer electrolytes, typically Nafion, are widely used. Despite great success, fuel cells based on acidic polyelectrolyte still depend heavily on noble metal catalysts, predominantly platinum (Pt), thus increasing the cost and hampering the widespread application of fuel cells. Here, we report a type of polymer electrolyte fuel cells (PEFC) employing a hydroxide ion-conductive polymer, quaternary ammonium polysulphone, as alkaline electrolyte and nonprecious metals, chromium-decorated nickel and silver, as the catalyst for the negative and positive electrodes, respectively. In addition to the development of a high-performance alkaline polymer electrolyte particularly suitable for fuel cells, key progress has been achieved in catalyst tailoring: The surface electronic structure of nickel has been tuned to suppress selectively the surface oxidative passivation with retained activity toward hydrogen oxidation. This report of a H2–O2 PEFC completely free from noble metal catalysts in both the positive and negative electrodes represents an important advancement in the research and development of fuel cells.
634 citations
••
TL;DR: An amorphous phosphorus/carbon (a-P/C) composite was synthesized using simple mechanical ball milling of red phosphorus and conductive carbon powders, showing great promise as a high capacity and high rate anode material for sodium ion batteries.
Abstract: Turning on your P/C: An amorphous phosphorus/carbon (a-P/C) composite was synthesized using simple mechanical ball milling of red phosphorus and conductive carbon powders. This material gave an extraordinarily high sodium ion storage capacity of 1764 mA h g(-1) (see graph) with a very high rate capability, showing great promise as a high capacity and high rate anode material for sodium ion batteries.
633 citations
••
TL;DR: Li et al. as discussed by the authors proposed a COVID-19 Lung Infection Segmentation Deep Network ( Inf-Net) to automatically identify infected regions from chest CT slices, where a parallel partial decoder is used to aggregate the high-level features and generate a global map.
Abstract: Coronavirus Disease 2019 (COVID-19) spread globally in early 2020, causing the world to face an existential health crisis. Automated detection of lung infections from computed tomography (CT) images offers a great potential to augment the traditional healthcare strategy for tackling COVID-19. However, segmenting infected regions from CT slices faces several challenges, including high variation in infection characteristics, and low intensity contrast between infections and normal tissues. Further, collecting a large amount of data is impractical within a short time period, inhibiting the training of a deep model. To address these challenges, a novel COVID-19 Lung Infection Segmentation Deep Network ( Inf-Net ) is proposed to automatically identify infected regions from chest CT slices. In our Inf-Net , a parallel partial decoder is used to aggregate the high-level features and generate a global map. Then, the implicit reverse attention and explicit edge-attention are utilized to model the boundaries and enhance the representations. Moreover, to alleviate the shortage of labeled data, we present a semi-supervised segmentation framework based on a randomly selected propagation strategy, which only requires a few labeled images and leverages primarily unlabeled data. Our semi-supervised framework can improve the learning ability and achieve a higher performance. Extensive experiments on our COVID-SemiSeg and real CT volumes demonstrate that the proposed Inf-Net outperforms most cutting-edge segmentation models and advances the state-of-the-art performance.
633 citations
Authors
Showing all 93441 results
Name | H-index | Papers | Citations |
---|---|---|---|
Jing Wang | 184 | 4046 | 202769 |
Jiaguo Yu | 178 | 730 | 113300 |
Lei Jiang | 170 | 2244 | 135205 |
Gang Chen | 167 | 3372 | 149819 |
Omar M. Yaghi | 165 | 459 | 163918 |
Xiang Zhang | 154 | 1733 | 117576 |
Yi Yang | 143 | 2456 | 92268 |
Thomas P. Russell | 141 | 1012 | 80055 |
Jun Chen | 136 | 1856 | 77368 |
Lei Zhang | 135 | 2240 | 99365 |
Chuan He | 130 | 584 | 66438 |
Han Zhang | 130 | 970 | 58863 |
Lei Zhang | 130 | 2312 | 86950 |
Zhen Li | 127 | 1712 | 71351 |
Chao Zhang | 127 | 3119 | 84711 |