# Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment

arXiv: https://arxiv.org/abs/2512.23413 · HTML: https://mlsanity.com/paper/2512.23413/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 29 Dec 2025.

## Builds on (most cited first, 14 of 14)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Large Language Models for Data Annotation and Synthesis: A Survey](https://mlsanity.com/paper/2402.13446/) (2024)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception](https://mlsanity.com/paper/2404.09624/) (2024)
- [Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New Method](https://mlsanity.com/paper/2303.15166/) (2023)
- [DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization](https://mlsanity.com/paper/2211.10682/) (2022)
- [APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments](https://mlsanity.com/paper/2411.08545/) (2024)
- [Paintings and Drawings Aesthetics Assessment with Rich Attributes for Various Artistic Categories](https://mlsanity.com/paper/2405.02982/) (2024)
- [CreativeSynth: Cross-Art-Attention for Artistic Image Synthesis with Multimodal Diffusion](https://mlsanity.com/paper/2401.14066/) (2024)
- [ArtCrafter: Text-Image Aligning Style Transfer via Embedding Reframing](https://mlsanity.com/paper/2501.02064/) (2025)

## Built on by (most cited first, 2 of 2)

- [Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model](https://mlsanity.com/paper/2601.04033/) (2026)
- [AesCanvas: A Large-Scale Dataset and Benchmark for Aesthetic Critique and Contextual Suitability](https://mlsanity.com/paper/2608.26713/) (2026)

## Abstract (arXiv)

The aesthetic quality assessment task is crucial for developing a human-aligned quantitative evaluation system for AIGC. However, its inherently complex nature, spanning visual perception, cognition, and emotion, poses fundamental challenges. Although aesthetic descriptions offer a viable representation of this complexity, two critical challenges persist: (1) data scarcity and imbalance: existing dataset overly focuses on visual perception and neglects deeper dimensions due to the expensive manual annotation; and (2) model fragmentation: current visual networks isolate aesthetic attributes with multi-branch encoder, while multimodal methods represented by contrastive learning struggle to effectively process long-form textual descriptions. To resolve challenge (1), we first present the Refined Aesthetic Description (RAD) dataset, a large-scale (70k), multi-dimensional structured dataset, generated via an iterative pipeline without heavy annotation costs and easy to scale. To address challenge (2), we propose ArtQuant, an aesthetics assessment framework for artistic images which not only couples isolated aesthetic dimensions through joint description generation, but also better models long-text semantics with the help of LLM decoders. Besides, theoretical analysis confirms this symbiosis: RAD's semantic adequacy (data) and generation paradigm (model) collectively minimize prediction entropy, providing mathematical grounding for the framework. Our approach achieves state-of-the-art performance on several datasets while requiring only 33% of conventional training epochs, narrowing the cognitive gap between artistic images and aesthetic judgment. We will release both code and dataset to support future research.