研究人员推出了一种新颖的两阶段框架DualAlign，旨在通过有效融合多模态数据来改进动作质量评估（AQA）。该方法首先稳定来自RGB、光流和骨骼数据的视觉表示，然后再纳入文本语义，从而解决了跨模态不对齐和标注成本高昂等挑战。为了支持这项研究，创建了一个名为MM--JDM的新数据集，其中包含多样化的多模态输入以及真实的噪声、类别不平衡和标签稀疏性。实验表明，DualAlign在MM--JDM和其他基准测试上的表现显著优于现有方法，并且在模态缺失或标签有限的情况下也表现出鲁棒性。 AI
影响 为动作质量评估中的多模态融合引入了一个新颖的框架和数据集，有望改进体育分析和技能评估。
排序理由 该集群包含一篇详细介绍动作质量评估新框架和数据集的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.07438v1 Announce Type: new Abstract: Action Quality Assessment (AQA) aims to evaluate how well a person performs a movement, which is essential in applications such as sports scoring, skill assessment, and healthcare. However, unimodal approaches often struggle to capt…
Action Quality Assessment (AQA) aims to evaluate how well a person performs a movement, which is essential in applications such as sports scoring, skill assessment, and healthcare. However, unimodal approaches often struggle to capture subtle cues of movement quality in real-worl…