Learning Image-Text Associations

Web information fusion can be defined as the problem of collating and tracking information related to specific topics on the World Wide Web. Whereas most existing work on Web information fusion has focused on text-based multidocument summarization, this paper concerns the topic of image and text association, a cornerstone of cross-media Web information fusion. Specifically, we present two learning methods for discovering the underlying associations between images and texts based on small training data sets. The first method based on vague transformation measures the information similarity between the visual features and the textual features through a set of predefined domain-specific information categories. Another method uses a neural network to learn direct mapping between the visual and textual features by automatically and incrementally summarizing the associated features into a set of information templates. Despite their distinct approaches, our experimental results on a terrorist domain document set show that both methods are capable of learning associations between images and texts from a small training data set.     

Friendly spectrum jamming against MIMO eavesdropping

Wireless Networks - Friendly spectrum jamming is a flexible scheme to establish secure communications among heterogeneous wireless devices without the need of encryption. Previous works have...     

A Survey on Long-Tailed Visual Recognition

The heavy reliance on data is one of the major reasons that currently limit the development of deep learning. Data quality directly dominates the effect of deep learning models, and the long-tailed distribution is one of the factors affecting data quality. The long-tailed phenomenon is prevalent due to the prevalence of power law in nature. In this case, the performance of deep learning models is often dominated by the head classes while the learning of the tail classes is severely underdeveloped. In order to learn adequately for all classes, many researchers have studied and preliminarily addressed the long-tailed problem. In this survey, we focus on the problems caused by long-tailed data distribution, sort out the representative long-tailed visual recognition datasets and summarize some mainstream long-tailed studies. Specifically, we summarize these studies into ten categories from the perspective of representation learning, and outline the highlights and limitations of each category. Besides, we have studied four quantitative metrics for evaluating the imbalance, and suggest using the Gini coefficient to evaluate the long-tailedness of a dataset. Based on the Gini coefficient, we quantitatively study 20 widely-used and large-scale visual datasets proposed in the last decade, and find that the long-tailed phenomenon is widespread and has not been fully studied. Finally, we provide several future directions for the development of long-tailed learning to provide more ideas for readers.

     

In-situ synthesis of TiO2 nanostructures on Ti foil for enhanced and stable photocatalytic performance

TiO_2 nanostructures with strong interfacial adhesion and diverse morphologies have been in-situ grown on Ti foil substrate through a multiple-step method based on conventional plasma electrolytic oxidation(PEO) technology, hydrothermal reaction and ion exchange process. The PEO process is critical to the formation of TiO_2 seeding layer for the nucleation of Na_2Ti_3O_7 and H_2Ti_3O_7 mediates that are strongly attached to the Ti foil. An ion exchange reaction can finally lead to the formation of H_2Ti_3O_7 nanostructures with diverse morphologies and the calcination process can turn the H_2Ti_3O_7 nanostructures into TiO_2 nanostructures with enhanced crystallinity. The morphology of the TiO_2 nanostructures including nanoparticles(NP), nanowhiskers(NWK), nanowires(NW) and nanosheets(NS) can be easily tailored by controlling the NaOH concentration and reaction time during hydrothermal process. The morphology, composition and optical properties of TiO_2 photocatalysts were analyzed using scanning electron microscope(SEM), X-ray diffraction(XRD), photoluminescence(PL) spectroscopy and UV–vis absorption spectrum. Photocatalytic tests indicate that the TiO_2 nanosheets calcined at 500?C show good crystallization and the best capability of decomposing organic pollutants. The decoration of Ag cocatalyst can further improve the photocatalytic performance of the TiO_2 nanosheets as a result of the enhanced charger separation efficiency. Cyclic photocatalytic test using TiO_2 nanostructures grown on Ti foil substrate demonstrates the superior stability in the photodegradation of organic pollutant, suggesting the promising potential of in-situ growth technology for industrial application.     

Erratum to: High-purity helical carbon nanotubes by trace-waterassisted chemical vapor deposition: Large-scale synthesis and growth mechanism

Nano Research - The first author, Fanbin Meng, and the second author, Ying Wang, contributed equally to this work was unfortunately forgotten to write on the first pages of the main text and the...