一种用于静态图像零样本面部表情识别的视觉问答策略评估
An Evaluation of a Visual Question Answering Strategy for Zero-shot Facial Expression Recognition in Still Images
AI总结：
本研究评估本地执行的VLMs并采用视觉问答策略，以解决零样本面部表情识别泛化性能差的问题，在AffectNet、FERPlus和RAF-DB基准上与现有模型对比，发现部分VLMs表现优异，为提升FER泛化能力提供了新方向。
摘要：
面部表情识别（FER）是计算机视觉和人机交互领域的关键研究方向。尽管深度学习近期取得了进展，但挑战依然存在，尤其是在泛化到新场景方面。事实上，零样本FER显著降低了最先进FER模型的性能。为解决这一问题，社区近期开始探索将Large Language Models的知识整合到视觉任务中。在本研究中，我们评估了广泛收集的本地执行的Visual Language Models（VLMs），通过采用视觉问答策略来避免缺乏特定任务知识的问题。我们将提出的pipeline与最先进的FER模型（包含整合和排除VLMs的情况）进行了比较，评估了知名的FER基准：AffectNet、FERPlus和RAF-DB。结果显示，部分VLMs在零样本FER场景中表现出色，表明需要进一步探索以提升FER的泛化能力。
英文摘要：
Facial expression recognition (FER) is a key research area in computer vision and human-computer interaction. Despite recent advances in deep learning, challenges persist, especially in generalizing to new scenarios. In fact, zero-shot FER significantly reduces the performance of state-of-the-art FER models. To address this problem, the community has recently started to explore the integration of knowledge from Large Language Models for visual tasks. In this work, we evaluate a broad collection of locally executed Visual Language Models (VLMs), avoiding the lack of task-specific knowledge by adopting a Visual Question Answering strategy. We compare the proposed pipeline with state-of-the-art FER models, both integrating and excluding VLMs, evaluating well-known FER benchmarks: AffectNet, FERPlus, and RAF-DB. The results show excellent performance for some VLMs in zero-shot FER scenarios, indicating the need for further exploration to improve FER generalization.
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。
