Learn More
Deep ConvNets have shown its good performance in image classification tasks. However it still remains as a problem in deep video representation for action recognition. The problem comes from two aspects: on one hand, current video ConvNets are relatively shallow compared with image ConvNets, which limits its capability of capturing the complex video action(More)
The power conversion efficiency (PCE) of single-wall carbon nanotube (SCNT)/n-type crystalline silicon heterojunction photovoltaic devices is significantly improved by Au doping. It is found that the overall PCE was significantly increased to threefold. The efficiency enhancement of photovoltaic devices is mainly the improved electrical conductivity of SCNT(More)
  • Xiaobo Wang, Han Feng, +9 authors Wenbin Zeng
  • 2017
Owing to the central role of apoptosis in many human diseases and the wide-spread application of apoptosis-based therapeutics, molecular imaging of apoptosis in clinical practice is of great interest for clinicians, and holds great promises. Based on the well-defined biochemical changes for apoptosis, a rich assortment of probes and approaches have been(More)
Several recent researches have shown that image features produced by Convolutional Neural Networks (CNNs) provide the state-of-the-art performance for image classification and retrieval. Moreover, some researchers have found that the features extracted from the deep convolutional layers of CNNs perform better than that from the fully-connected layers.(More)
  • 1