Recognition-Conditioned Reasoning: A Training-Free Multimodal-LLM Pipeline for Fine-Grained Micro-Action Understanding

arXiv:2608.21022v1 Announce Type: new Abstract: Micro-actions are subtle, short, low-amplitude body movements, such as a fidgeting hand or a slight head tilt, that humans perform with little conscious intent yet that reliably leak emotional and psychological state. Understanding them goes beyond assigning a label: a model must also describe which body parts move and reason, faithfully, about why a clip warrants a particular fine-grained category. We present the training-free, prompt-only system that won first place in the fine-grained understanding track (MA-Bench) of the MAC~2026 Micro-Action Challenge, where both fine-tuning and ground-truth supervision are disallowed. Built entirely upon frozen multimodal large language models (MLLMs), the system dynamically routes each of the eight sub-tasks to the MLLM empirically best suited for that task: a discriminative MLLM for closed-ended recognition tasks and a generative MLLM for open-ended description and reasoning tasks. This architecture achieves a statistically significant performance advantage on open-ended tasks, attaining an average score of 2.68 (on a five-point scale) compared to 1.44 for the second-best approach.

Related

• Micro-DualNet: Dual-Path Spatio-Temporal Network for Micro-Action Recognition
• B-MoE: A Body-Part-Aware Mixture-of-Experts 'All Parts Matter' Approach to Micro-Action Recognition
• Fine-Grained Action Recognition with Cross-Attentive Latent Sparse Experts
• Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation

Source: arXiv cs.CV | 2026-08-24