Aspect ratio and spatial layout are two of the principal factors determining
the aesthetic value of a photograph. But, incorporating these into the
traditional convolution-based frameworks for the task of image aesthetics
assessment is problematic. The aspect ratio of the photographs gets distorted
while they are resized/cropped to a fixed dimension to facilitate training
batch sampling. On the other hand, the convolutional filters process
information locally and are limited in their ability to model the global
spatial layout of a photograph. In this work, we present a two-stage framework
based on graph neural networks and address both these problems jointly. First,
we propose a feature-graph representation in which the input image is modelled
as a graph, maintaining its original aspect ratio and resolution. Second, we
propose a graph neural network architecture that takes this feature-graph and
captures the semantic relationship between the different regions of the input
image using visual attention. Our experiments show that the proposed framework
advances the state-of-the-art results in aesthetic score regression on the
Aesthetic Visual Analysis (AVA) benchmark.

本文提出了一种基于图神经网络的两阶段框架，通过图形神经网络捕捉视觉注意力，使得美学视觉分析中原始的长宽比和空间布局等特征得以保留，进一步提高了美学得分回归的精度。

使用图注意力网络进行图像美感评估

Image Aesthetics Assessment Using Graph Attention Network

We address the flutter instability of a flexible plate immersed in an axial
flow. This instability is similar to flag flutter and results from the
competition between destabilising pressure forces and stabilising bending
stiffness. In previous experimental studies, the plates have always appeared
much more stable than the predictions of two-dimensional models. This
discrepancy is discussed and clarified in this paper by examining
experimentally and theoretically the effect of the plate aspect ratio on the
instability threshold. We show that the two-dimensional limit cannot be
achieved experimentally because hysteretical behaviour and three-dimensional
effects appear for plates of large aspect ratio. The nature of the instability
bifurcation (sub- or supercritical) is also discussed in the light of recent
numerical results.

本研究论文探究了在轴向流动中，柔性板的颤振不稳定性，着重从实验和理论两方面阐述了板的宽高比对颤振不稳定性状态的影响，并讨论了颤振分叉的本质和二维限制的实验矛盾。