A broadband transparent and flexible silver (Ag) mesh is presented experimentally for the first time for both efficient electromagnetic interference (EMI) shielding in the X band and high-quality free-space optical (FSO) communication. High transmission is achieved in a broad wavelength range of 0.4-2.0 µm. The transmittance of the Ag mesh relative to the substrate is around 92% and the sheet resistance is as low as 7.12 Ω/sq. The Ag mesh/polyethylene (PE) achieves a high average EMI shielding effectiveness (SE) of 28.8 dB in the X band with an overall transmittance of 80.9% at 550 nm. High-quality FSO communication with small power penalty is attributed to the high optical transmittance and the low haze at 1550 nm, superior to those of the Ag NW networks. With a polydimethylsiloxane (PDMS) coating, the average EMI SE is still up to 26.2 dB and the overall transmittance is increased to 84.5% at 550 nm due to antireflection. The FSO communication does not change much due to the nearly unchanged optical property at 1550 nm. Both the EMI shielding performance and the FSO communication function maintain after 2-hour chemical corrosions as well as after 1000 bending cycles and twisting. Our PDMS/Ag mesh/PE sandwiched film can be self-cleaned, suitable for outdoor applications.
Image captioning aims to generate a corresponding description of an image. In recent years, neural encoder-decoder models have been the dominant approaches, in which the Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) are used to translate an image into a natural language description. Among these approaches, the visual attention mechanisms are widely used to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. However, most conventional visual attention mechanisms are based on high-level image features, ignoring the effects of other image features, and giving insufficient consideration to the relative positions between image features. In this work, we propose a Position-Aware Transformer model with image-feature attention and position-aware attention mechanisms for the above problems. The image-feature attention firstly extracts multi-level features by using Feature Pyramid Network (FPN), then utilizes the scaled-dot-product to fuse these features, which enables our model to detect objects of different scales in the image more effectively without increasing parameters. In the position-aware attention mechanism, the relative positions between image features are obtained at first, afterwards the relative positions are incorporated into the original image features to generate captions more accurately. Experiments are carried out on the MSCOCO dataset and our approach achieves competitive BLEU-4, METEOR, ROUGE-L, CIDEr scores compared with some state-of-the-art approaches, demonstrating the effectiveness of our approach.
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.