ActFER: 通过主动工具增强的视觉推理实现代理面部表情识别
ActFER: Agentic Facial Expression Recognition via Active Tool-Augmented Visual Reasoning
AI总结：
ActFER通过主动视觉证据获取和多模态推理提升面部表情识别，采用UC-GRPO算法优化局部检查和情绪感知，实验显示其在AU预测准确率上显著优于传统方法。
摘要：
近期多模态大语言模型（MLLMs）的进步为面部表情识别（FER）创造了新机会，使其从单纯的标签预测转向基于推理的情感理解。然而，现有基于MLLMs的FER方法仍采用被动范式：依赖外部准备的面部输入，并在固定视觉证据上进行单次推理，缺乏主动面部感知能力。为解决这一限制，我们提出了ActFER，一种代理框架，将FER重新定义为主动视觉证据获取后接多模态推理。具体而言，ActFER动态调用面部检测和对齐工具，选择性地聚焦于信息丰富的局部区域，并通过视觉链式思维对面部动作单元（AUs）和情绪进行推理。为实现此类行为，我们进一步开发了Utility-Calibrated GRPO（UC-GRPO），一种针对代理FER定制的强化学习算法。UC-GRPO使用基于AU的多级可验证奖励来密集化监督，查询条件对比性效用估计以实现样本感知的动态信用分配用于局部检查，并通过情绪感知的EMA校准来减少噪声效用估计同时捕捉情绪层面的检查倾向。该算法使ActFER能够学习何时局部检查是有益的以及如何对获取的证据进行推理。全面实验表明，使用UC-GRPO训练的ActFER在AU预测准确率上显著优于传统方法。
英文摘要：
Recent advances in Multimodal Large Language Models (MLLMs) have created new opportunities for facial expression recognition (FER), moving it beyond pure label prediction toward reasoning-based affect understanding. However, existing MLLM-based FER methods still follow a passive paradigm: they rely on externally prepared facial inputs and perform single-pass reasoning over fixed visual evidence, without the capability for active facial perception. To address this limitation, we propose ActFER, an agentic framework that reformulates FER as active visual evidence acquisition followed by multimodal reasoning. Specifically, ActFER dynamically invokes tools for face detection and alignment, selectively zooms into informative local regions, and reasons over facial Action Units (AUs) and emotions through a visual Chain-of-Thought. To realize such behavior, we further develop Utility-Calibrated GRPO (UC-GRPO), a reinforcement learning algorithm tailored to agentic FER. UC-GRPO uses AU-grounded multi-level verifiable rewards to densify supervision, query-conditional contrastive utility estimation to enable sample-aware dynamic credit assignment for local inspection, and emotion-aware EMA calibration to reduce noisy utility estimates while capturing emotion-wise inspection tendencies. This algorithm enables ActFER to learn both when local inspection is beneficial and how to reason over the acquired evidence. Comprehensive experiments show that ActFER trained with UC-GRPO consistently outperforms passive MLLM-based FER baselines and substantially improves AU prediction accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
