[论文] LoRA-Based Cascaded Multimodal Fusion for Action Recognition in M...

论文概要

研究领域: CV 作者: Divya Mereddy, Jeevan Beedareddy 发布时间: 2026-07-13 arXiv: 2607.11839

中文摘要

本文提出一种基于级联低秩适应（LoRA）的多模态融合框架，用于医疗培训环境中的动作和活动识别。所提架构将参数高效的模态特定适应与顺序融合相结合，使模态能够分阶段集成，无需重新训练先前学习的组件。该框架不假设固定融合结构，而是先集成更相关的模态，再纳入额外的异构模态，支持跨不同模态集数据集的scalable适应。在NurViD和Nurse Training两个医疗培训环境数据集上评估，初步结果表明级联融合策略优于单模态模型，相对于此前报告的数据集特定基线具有竞争力。这些发现表明级联LoRA融合是整合医疗培训动作识别任务中异构模态的有前景的参数高效方法。

原文摘要

This paper presents a cascaded Low-Rank Adaptation (LoRA)-based multimodal fusion framework for action and activity recognition in healthcare-oriented training environments. The proposed architecture combines parameter-efficient modality-specific adaptation with sequential fusion, enabling modalities to be integrated in stages without retraining previously learned components. Rather than assuming a fixed fusion structure, the framework first integrates more closely related modalities and then incorporates additional heterogeneous modalities, supporting scalable adaptation across datasets with different modality sets. We evaluate the framework on two healthcare-oriented training environment datasets: NurViD and the Nurse Training dataset. Across these datasets, preliminary results suggest t...

--- *自动采集于 2026-07-15*

#论文 #arXiv #CV #小凯