Lune

CVPR2026Top-tier venue

MA-Bench: Towards Fine-grained Micro-Action Understanding

Kun Li, Jihao Gu, Fei Wang, Zhiliang Wu, Hehe Fan, Dan Guo

Abstract

With the rapid development of Multimodal Large Language Models (MLLMs), their potential in Micro-Action understanding, a vital role in human emotion analysis, remains unexplored due to the absence of specialized benchmarks. To tackle this issue, we present MA-Bench, a benchmark comprising 1,000 videos and a three-tier evaluation architecture that progressively examines micro-action perception, relational comprehension, and interpretive reasoning. MA-Bench contains 12,000 structured question-answer pairs, enabling systematic assessment of both recognition accuracy and action interpretation. The results of 23 representative MLLMs reveal that there are significant challenges in capturing motion granularity and fine-grained body-part dynamics. To address these challenges, we further construct MA-Bench-Train, a large-scale training corpus with 20.5K videos annotated with structured micro-action captions for fine-tuning MLLMs. The results of Qwen3-VL-8B fine-tuned on MA-Bench-Train show clear performance improvements across micro-action reasoning and explanation tasks. Our work aims to establish a foundation benchmark for advancing MLLMs in understanding subtle micro-action and human-related behaviors. Project Page: https://MA-Bench.github.io

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • NExT-GPT: Any-to-Any Multimodal LLM cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
  • VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical ProblemsShuhang Chen, Hangjie Yuan, Yunqiu Xu, Pengwei Liu et al.ACL 2026 · 9 citations

Builds on20

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. NExT-GPT: Any-to-Any Multimodal LLMShengqiong Wu, Hao Fei, Leigang Qu, Wei Ji et al.ICML 2024 · 786 citations
  3. Video-R1: Reinforcing Video Reasoning in MLLMsKaituo Feng, Kaixiong Gong, Bohao Li, Zonghao Guo et al.NeurIPS 2025 · 528 citations
  4. Video-LLaVA: Learning United Visual Representation by Alignment Before ProjectionBin Lin, Yang Ye, Bin Zhu, Jiaxi Cui et al.EMNLP 2024 · 231 citations
  5. VideoChat-Flash: Hierarchical Compression for Long-Context Video ModelingXinhao Li, Yi Wang, Jiashuo Yu, Xiangyu Zeng et al.ICLR 2026 · 172 citations

Related papers

  1. HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized BenchmarksTing Zhou, Daoyuan Chen, Qirui Jiao, Bolin Ding et al.CVPR 2026
  2. AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language ModelsZheng Lian, Haoyu Chen, Lan Chen, Haiyang Sun et al.ICML 2025
  3. MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language ModelsFan Zhang, Zebang Cheng, Chong Deng, Haoxuan Li et al.ICLR 2026 · 23 citations
  4. MVBench: A Comprehensive Multi-modal Video Understanding BenchmarkKunchang Li, Yali Wang, Yinan He, Yizhuo Li et al.CVPR 2024
  5. Beyond Emotion Recognition: A Multi-Turn Multimodal Emotion Understanding and Reasoning BenchmarkJinpeng Hu, Hongchang Shi, Chongyuan Dai, Zhuo Li et al.ACM MM 2025 · 7 citations
Dusk over the sea between two cliffs drawn in fine vertical lines