As the optical lenses for cameras always have limited depth of field, the captured images with the same scene are not all in focus. Multifocus image fusion is an efficient technology that can synthesize an all-in-focus image using several partially focused images. Previous methods have accomplished the fusion task in spatial or transform domains. However, fusion rules are always a problem in most methods. In this letter, from the aspect of focus region detection, we propose a novel multifocus image fusion method based on a fully convolutional network (FCN) learned from synthesized multifocus images. The primary novelty of this method is that the pixel-wise focus regions are detected through a learning FCN, and the entire image, not just the image patches, are exploited to train the FCN. First, we synthesize 4500 pairs of multifocus images by repeatedly using a gaussian filter for each image from PASCAL VOC 2012, to train the FCN. After that, a pair of source images is fed into the trained FCN, and two score maps indicating the focus property are generated. Next, an inversed score map is averaged with another score map to produce an aggregative score map, which take full advantage of focus probabilities in two score maps. We implement the fully connected conditional random field (CRF) on the aggregative score map to accomplish and refine a binary decision map for the fusion task. Finally, we exploit the weighted strategy based on the refined decision map to produce the fused image. To demonstrate the performance of the proposed method, we compare its fused results with several start-of-the-art methods not only on a gray data set but also on a color data set. Experimental results show that the proposed method can achieve superior fusion performance in both human visual quality and objective assessment.
We study the problem of knowledge tracing (KT) where the goal is to trace the students' knowledge mastery over time so as to make predictions on their future performance. Owing to the good representation capacity of deep neural networks (DNNs), recent advances on KT have increasingly concentrated on exploring DNNs to improve the performance of KT. However, we empirically reveal that the DNNs based KT models may run the risk of overfitting, especially on small datasets, leading to limited generalization. In this paper, by leveraging the current advances in adversarial training (AT), we propose an efficient AT based KT method (ATKT) to enhance KT model's generalization and thus push the limit of KT. Specifically, we first construct adversarial perturbations and add them on the original interaction embeddings as adversarial examples. The original and adversarial examples are further used to jointly train the KT model, forcing it is not only to be robust to the adversarial examples, but also to enhance the generalization over the original ones. To better implement AT, we then present an efficient attentive-LSTM model as KT backbone, where the key is a proposed knowledge hidden state attention module that adaptively aggregates information from previous knowledge hidden states while simultaneously highlighting the importance of current knowledge hidden state to make a more accurate prediction. Extensive experiments on four public benchmark datasets demonstrate that our ATKT achieves new state-of-the-art performance. Code is available at: https://github.com/xiaopengguo/ATKT.
CCS CONCEPTS• Applied computing → Computer-assisted instruction; Learning management systems.
Ultraviolet (UV) photodetector is a kind of important optoelectronic device which can be widely used in scientific and engineering fields including astronomical research, environmental monitoring, forest-fire prevention, medical analysis, and missile approach warning etc. The development of UV detector is hindered by the acquirement of stable p-type materials, which makes it difficult to realize large array, low-power consumption UV focal plane array (FPA) detector. Here, we provide a novel structure (Al/Poly(9,9-di-n-octylfuorenyl-2,7-diyl)(PFO)/ZnO/ITO) to demonstrate the UV photovoltaic (PV) response. A rather smooth surface (RMS roughness: 0.28 nm) may be reached by solution process, which sheds light on the development of large-array, light-weight and low-cost UV FPA detectors.
Cadmium sulfide quantum dots (CdS QDs) are widely used in solar cells, light emitting diodes, photocatalysis and biological imaging because of their unique optical and electrical properties. However, there are some drawbacks in existing preparation techniques of CdS QDs, such as protection of inert gas, lengthy reaction time, high reaction temperature, poor crystallinity and non-uniform particle size distribution. In this study, we prepared CdS QDs by liquid phase synthesis under ambient room temperature and atmospheric pressure using sodium alkyl sulfonate, CdCl 2 and Na 2 S as capping agent, cadmium and sulfur sources respectively. The technique offers facile preparation, efficient reaction, low-cost, and controllable particle size. The as-prepared CdS QDs exhibited good crystallinity, excellent monodispersity and uniform particle size. The responsivity of CdS QDs based photodetector was greater than 0.3 μA/W, which makes them suitable for use as UV detector.
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.