A$^3$: Towards Advertising Aesthetic Assessment

TL;DR

The paper introduces A^3, a comprehensive framework for advertising aesthetic assessment based on a new theory-driven paradigm, a large annotated dataset, and a multimodal language model, aiming to improve evaluation's scalability, interpretability, and effectiveness.

Contribution

It proposes the A^3-Law paradigm, constructs a large annotated dataset, and develops A^3-Align, a multimodal model that aligns with the paradigm for better advertising image evaluation.

Findings

A^3-Align outperforms existing models in aligning with A^3-Law.

The framework generalizes well to advertisement selection and critique.

The dataset contains 120K instruction-response pairs with rich annotations.

Abstract

Advertising images significantly impact commercial conversion rates and brand equity, yet current evaluation methods rely on subjective judgments, lacking scalability, standardized criteria, and interpretability. To address these challenges, we present A^3 (Advertising Aesthetic Assessment), a comprehensive framework encompassing four components: a paradigm (A^3-Law), a dataset (A^3-Dataset), a multimodal large language model (A^3-Align), and a benchmark (A^3-Bench). Central to A^3 is a theory-driven paradigm, A^3-Law, comprising three hierarchical stages: (1) Perceptual Attention, evaluating perceptual image signals for their ability to attract attention; (2) Formal Interest, assessing formal composition of image color and spatial layout in evoking interest; and (3) Desire Impact, measuring desire evocation from images and their persuasive impact. Building on A^3-Law, we construct A^3-Dataset with 120K instruction-response pairs from 30K advertising images, each richly annotated with multi-dimensional labels and Chain-of-Thought (CoT) rationales. We further develop A^3-Align, trained under A^3-Law with CoT-guided learning on A^3-Dataset. Extensive experiments on A^3-Bench demonstrate that A^3-Align achieves superior alignment with A^3-Law compared to existing models, and this alignment generalizes well to quality advertisement selection and prescriptive advertisement critique, indicating its potential for broader deployment. Dataset, code, and models can be found at: https://github.com/euleryuan/A3-Align.