Search

Your search keyword '"Wang, Xiaofen"' showing total 92 results
Start Over Author "Wang, Xiaofen" Publisher elsevier bv
92 results on '"Wang, Xiaofen"'

18. Single image de-raining via clique recursive feedback mechanism

Author

Wang Xiaofen, Zhongyuan Wang, Jun Chen, Chao Liang, Zhen Han, Kui Jiang, and Weijian Ruan

Subjects
Clique, 0209 industrial biotechnology, Computer science, business.industry, Cognitive Neuroscience, Deep learning, Scale (descriptive set theory), 02 engineering and technology, Computer Science Applications, 020901 industrial engineering & automation, Artificial Intelligence, Feature (computer vision), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, Representation (mathematics), business, Algorithm, Block (data storage)
Abstract

Deep learning methods have achieved significant progress in single image rain removal in recent years. However, the remaining rain streak phenomenon still exists in previous ways, provided that they did not adequately consider the interaction of features flowing among the network. To utilize the feature interaction of the network, we propose a new rain removal network based on the clique recursive feedback mechanism. Mainly, considering the interaction of the feature between different convolution layers, we construct a residual clique block (RCB) to infer the local information, allowing the network to rectify the model parameters in RCB alternately. Besides, a multi-path dilated convolutional unit is embedded into a scale clique block (SCB) to cover more scale components. In SCB, we consider the complementary correlation of different scales, and the multi-scale features are updated alternately, which is essential for excellent feature representation. Along with the clique recursive feedback mechanism, the information flowing among RCB and SCB is thus maximized during propagation. Experiments on synthetic and real-world images have shown the superiority of the proposed method over state-of-the-art methods.

Published
2020

44. The effects of fermentation and adsorption using lactic acid bacteria culture broth on the feed quality of rice straw

Author

Ren Ji-wei, Wang Xiaofen, Liu Xiao-ping, Cui Zongjun, Abdelfattah Z.M. Salem, Yuan XuFeng, Liu JingJing, and Zhao Hong-yan

Subjects
animal structures, lactic acid bacteria culture broth, Agriculture (General), Forage, Plant Science, Biochemistry, S1-972, chemistry.chemical_compound, Food Animals, Botany, Dry matter, Palatability, Food science, fermentation, Ecology, biology, food and beverages, Straw, biology.organism_classification, Lactic acid, Neutral Detergent Fiber, chemistry, adsorption, rice straw, Animal Science and Zoology, Fermentation, Agronomy and Crop Science, Bacteria, Food Science
Abstract

To improve the nutritional value and the palatability of air-dried rice straw, culture broth of the lactic acid bacteria community SFC-2 was used to examine the effects of two different treatments, fermentation and adsorption. Air-dried and chopped rice straw was treated with either fermentation for 30 d after adding 1.5 L nutrient solution (50 mL inocula L−1, 1.2×1012 CFU mL−1 inocula) kg−1 straw dry matter, or spraying a large amount of culture broth (1.5 L kg−1 straw dry matter, 1.5×1011 CFU mL−1 culture broth) on the straw and allowing it to adsorb for 30 min. The feed quality and aerobic stability of the resulting forage were examined. Both treatments improved the feed quality of rice straw, and adsorption was better than fermentation for preserving nutrients and improving digestibility, as evidenced by higher dry matter (DM) and crude protein (CP) concentrations, lower neutral detergent fiber (NDF), acid detergent fiber (ADF) and NH3-N concentrations, as well as higher lactic acid production and in vitro digestibility of DM (IVDMD). The aerobic stability of the adsorbed straw and the fermented straw was 392 and 480 h, respectively. After being exposed to air, chemical components and microbial community of the fermented straw were more stable than the adsorbed straw.

Published
2015

Catalog

Books, media, physical & digital resources
See catalog results