{"url":"/dataset/aesbench","name":"AesBench","full_name":null,"description_markdown":"**AesBench** is an expert benchmark designed to comprehensively evaluate the aesthetic perception capacities of **Multimodal Large Language Models (MLLMs)** when it comes to **image aesthetics perception**. Let me break it down for you:\r\n\r\n1. **Purpose and Challenge**:\r\n   - MLLMs, which combine language and vision, are rapidly advancing.\r\n   - However, their performance in **aesthetic perception** (assessing the beauty or visual appeal of images) remains uncertain.\r\n   - The lack of a specific benchmark for evaluating MLLMs in this domain hinders their further development.\r\n\r\n2. **What Is AesBench?**:\r\n   - AesBench addresses this challenge by providing a comprehensive benchmark.\r\n   - It evaluates MLLMs' aesthetic perception abilities through **dual facets**:\r\n     - **Expert-labeled Aesthetics Perception Database (EAPD)**: This database contains diverse image contents with high-quality annotations from professional aesthetic experts.\r\n     - **Integrative Criteria**: AesBench proposes criteria to measure MLLMs' aesthetic perception abilities from four perspectives:\r\n       - **Perception (AesP)**: How well MLLMs perceive aesthetics.\r\n       - **Empathy (AesE)**: Their ability to empathize with aesthetic preferences.\r\n       - **Assessment (AesA)**: How accurately they assess aesthetics.\r\n       - **Interpretation (AesI)**: Their understanding of aesthetic features.\r\n\r\n3. **Findings**:\r\n   - Extensive experiments reveal that current MLLMs possess only **rudimentary aesthetic perception ability**.\r\n   - There remains a significant gap between MLLMs and human aesthetic perception.\r\n\r\nIn summary, AesBench provides a valuable tool for assessing how well MLLMs understand and appreciate the beauty of images. 📸🌟\r\n\r\n(1) [2401.08276] AesBench: An Expert Benchmark for Multimodal Large .... https://arxiv.org/abs/2401.08276.\r\n(2) GitHub - yipoh/AesBench: An expert benchmark aiming to comprehensively .... https://github.com/yipoh/AesBench.\r\n(3) AesBench/README.md at main · yipoh/AesBench · GitHub. https://github.com/yipoh/AesBench/blob/main/README.md.\r\n(4) undefined. https://doi.org/10.48550/arXiv.2401.08276.","description_withheld":null,"homepage":"https://github.com/yipoh/AesBench","introduced_date":"2024-01-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/aesbench-an-expert-benchmark-for-multimodal","title":"AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception","first_author":"Yipo Huang","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["AesBench"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}