Series Photo Selection via Multi-view Graph Learning

TL;DR

This paper introduces a multi-view graph neural network approach for series photo selection, leveraging multiple image features and adaptive attention to improve aesthetic quality assessment.

Contribution

It proposes a novel multi-view graph neural network with adaptive self-attention for more accurate photo selection from series, considering diverse image features.

Findings

Achieves the highest success rates among compared methods.

Effectively models relationships between multi-view features.

Demonstrates improved photo selection accuracy.

Abstract

Series photo selection (SPS) is an important branch of the image aesthetics quality assessment, which focuses on finding the best one from a series of nearly identical photos. While a great progress has been observed, most of the existing SPS approaches concentrate solely on extracting features from the original image, neglecting that multiple views, e.g, saturation level, color histogram and depth of field of the image, will be of benefit to successfully reflecting the subtle aesthetic changes. Taken multi-view into consideration, we leverage a graph neural network to construct the relationships between multi-view features. Besides, multiple views are aggregated with an adaptive-weight self-attention module to verify the significance of each view. Finally, a siamese network is proposed to select the best one from a series of nearly identical photos. Experimental results demonstrate that our model accomplish the highest success rates compared with competitive methods.