Search

In the era of deep learning, it's important to obtain enough qualified data for model training. For the labor-intensive and time-consuming characteristics of data collection and annotation, date augmentation has been widely employed in deep learning methods to mitigate over-fitting. It has been proven to be one of the most effective ways to ensure the performance of deep models. In the field of computer vision, the principal goal of data augmentation usually is enlarging both the scale and diversity of the dataset, and maintaining the quality of both the image and the annotation data simultaneously. Data augmentation methods at the raw input data level are intuitive to obtain semantic meaningful images. In this paper, we provide a brief survey on some data augmentation studies conducted at image level and briefly categorize the studies into two main classes: those based on image editing and those based on image generation. We also make an analysis of the semantic-preserving considerations within data augmentation techniques. [ABSTRACT FROM AUTHOR]

Celsian was synthesized in situ and was used to sinter silicon carbide. The low temperature pressureless liquid sintering process for BAS/SiC complex phase ceramics was studied, and ceramic materials with high density were prepared. The effect of sintering temperature and content of BAS on density, structure and mechanical properties of the ceramics were investigated. The densification and microstructures of BAS/SiC ceramics were observed by scanning electron microscope. The crystalline phase of the composite ceramics was identified by X-ray powder diffraction. The results show that celsian is synthesized at the temperature of 1800 ℃, and BAS/SiC ceramics are prepared with density of 3.2 g/cm3. BAS is precipitated in hexagonal structure, and SiC particles are distributed uniformly in the composite ceramic. The flexural strength and fracture toughness of composite ceramics are decreased due to grains growth while the sintering temperature is above 1800 ℃. When the mass content of BAS reaches 30%, the typical flexural strength, elastic modulus and fracture toughness of the pressureless sintered BAS/SiC ceramics are 413 MPa, 210 GPa and 5.03 MPa?m1/2 at room temperature.

This paper proposes a quasi-dense matching approach to the automatic acquisition of camera parameters, which is required for recovering 3-D information from 2-D images. An affine transformation-based optimization model and a new matching cost function are used to acquire quasi-dense correspondences with high accuracy in each pair of views. These correspondences can be effectively detected and tracked at the sub-pixel level in multiviews with our neighboring view selection strategy. A two-layer iteration algorithm is proposed to optimize 3-D quasi-dense points and camera parameters. In the inner layer, different optimization strategies based on local photometric consistency and a global objective function are employed to optimize the 3-D quasi-dense points and camera parameters, respectively. In the outer layer, quasi-dense correspondences are resampled to guide a new estimation and optimization process of the camera parameters. We demonstrate the effectiveness of our algorithm with several experiments. [ABSTRACT FROM PUBLISHER]

Abstract: A facile method to decorate the polymeric hollow spheres with ZnS nanoparticles has been presented. In this method, the precursors, Zn(Ac)2⋅H2O and CH3CSNH2, were first adsorbed by the polymer substrate in supercritical CO2–ethanol solution at 35 °C. Followed by heating the mixture at 100 °C for 2 h, ZnS/polymer composites were obtained. The as-produced ZnS/polymer composites were characterized by means of IR spectra, X-ray diffraction, transmission electron microscopy, high-resolution transmission electron microscopy. It was demonstrated that crystalline ZnS nanoparticles with size of 3–5 nm were uniformly decorated on the polymer spheres under suitable conditions. The resultant ZnS/polymer composites exhibited high efficiency for degrading eosin B, methyl orange and methylene blue under UV light irradiation. [Copyright &y& Elsevier]

Human activity localization aims at recognizing contents and detecting locations of activities in video sequences. With an increasing number of untrimmed video data, traditional activity localization methods always suffer from two major limitations. First, detailed annotations are needed in most existing methods, i.e., bounding-box annotations in every frame, which are both expensive and time consuming. Second, the search space is too large for 3D activity localization, which requires generating a large number of proposals. In this paper, we propose a unified deep Q-network with weak reward and weak loss (DWRLQN) to address the two problems. Certain weak knowledge and weak constraints involving the temporal dynamics of human activity are incorporated into a deep reinforcement learning framework under sparse spatial supervision, where we assume that only a portion of frames are annotated in each video sequence. Experiments on UCF-Sports, UCF-101 and sub-JHMDB demonstrate that our proposed model achieves promising performance by only utilizing a very small number of proposals. More importantly, our DWRLQN trained with partial annotations and weak information even outperforms fully supervised methods.