INformer: Inertial-Based Fusion Transformer for Camera Shake Deblurring.

Inertial measurement units (IMU) in the capturing device can record the motion information of the device, with gyroscopes measuring angular velocity and accelerometers measuring acceleration. However, conventional deblurring methods seldom incorporate IMU data, and existing approaches that utilize IMU information often face challenges in fully leveraging this valuable data, resulting in noise issues from the sensors. To address these issues, in this paper, we propose a multi-stage deblurring network named INformer, which combines inertial information with the Transformer architecture.

SRGAT: Single Image Super-Resolution With Graph Attention Network.

Deep neural networks have demonstrated remarkable reconstruction for single-image super-resolution (SISR). However, most existing CNN-based SISR methods directly learn the relation between low-resolution (LR) and high-resolution (HR) images, neglecting to explore the recurrence of internal patches, hence hindering the representational power of CNNs. In this paper, we propose a novel single image Super-Resolution network based on Graph ATtention network (SRGAT) to make full use of the internal patch-recurrence in a natural image.

Regional innovation distribution and its dynamic evolution: Policy impact and spillover effect-Based on the perspective of innovation motivation.

This study aims to explore the direct effect and spillover effect of innovation policy in the distribution and dynamic evolution of the regional innovation from the perspective of innovation motivation using the spatial econometric model. Substantive innovation and strategic innovation in one region could affect innovation in another region. In addition, the direct effect and spatial spillover effect of innovation policy could significantly affect innovation; however, they exert a higher impact on substantive innovation.

A note on estimating the bent line quantile regression model.

This paper considers a new estimating method for the bent line quantile regression model. By a simple linearization technique, the proposed method can simultaneously obtain the estimates of the regression coefficients and the change-point location. Moreover, it can be readily implemented by current software.