Your browser doesn't support javascript.
loading
: 20 | 50 | 100
1 - 3 de 3
1.
Small ; 20(14): e2307756, 2024 Apr.
Article En | MEDLINE | ID: mdl-37987091

Organic photomechanical molecular crystals are promising candidates for photoactuators, which have potential applications as smart materials in various fields. However, it is still challenging to fabricate photomechanical molecular crystals with flexibility because most of the molecular crystals are brittle and the mechanism of flexible crystals remains controversial. Here, a plastically flexible α-cyanostilbene crystal has been synthesized that can undergo solid-state [2+2] cycloaddition reaction under violet or UV irradiation and exhibits excellent photomechanical bending properties. A hook-shaped crystal can lift 0.7 mg object upward by 1.5 cm, which proves its potential for application as photoactuators. When complex with the agarose polymer, the molecules will be in the form of macroscopic crystals, which can drive the composite films to exhibit excellent photomechanical bending performance. Upon irradiation with UV light, the composite film can quickly lift 18.0 mg object upward by 0.3 cm. The results of this work may facilitate the application of macroscale crystals as photoactuators.

2.
Opt Express ; 30(10): 16585-16605, 2022 May 09.
Article En | MEDLINE | ID: mdl-36221498

Most of the existing deep learning methods for hyperspectral image (HSI) classification use pixel-wise or patch-wise classification. In this paper, we propose an image-wise classification method, where the network input is the original hyperspectral cube rather than the spectral curve of each pixel (i.e., pixel-wise) or neighbor region of each pixel (i.e., patch-wise). Specifically, we propose a minimalistic fully convolution network (MFCN) and a semi-supervised loss function, which can perform pixel-level classification for HSI with few labeled samples. The comparison experiments demonstrated the progress of our methods, using three new benchmark HSI datasets (WHU-Hi-LongKou, WHU-Hi-HanChuan and WHU-Hi-HongHu) with wavelength range from 400 to 1000nm. In the comparison experiments, we randomly selected 25 labeled pixels from each class for training, equivalent to only 0.11%, 0.16%, and 0.14% of all labeled pixels for the three datasets, respectively. In addition, through ablation studies and theoretical analysis, we verified and analyzed the effectiveness and superiority of our design choices.

3.
Sensors (Basel) ; 18(2)2018 Feb 22.
Article En | MEDLINE | ID: mdl-29470409

Image captioning with a natural language has been an emerging trend. However, the social image, associated with a set of user-contributed tags, has been rarely investigated for a similar task. The user-contributed tags, which could reflect the user attention, have been neglected in conventional image captioning. Most existing image captioning models cannot be applied directly to social image captioning. In this work, a dual attention model is proposed for social image captioning by combining the visual attention and user attention simultaneously.Visual attention is used to compress a large mount of salient visual information, while user attention is applied to adjust the description of the social images with user-contributed tags. Experiments conducted on the Microsoft (MS) COCO dataset demonstrate the superiority of the proposed method of dual attention.


Attention , Humans , Language , Visual Perception
...