研究人员开发了PartialVisGraph，一个旨在改善有限视场场景下基于骨架的动作识别的新型超图框架。该方法解决了在现实应用（如监控或机器人技术）中常见的关节遮挡或视场外问题导致的性能下降问题。该框架利用可学习的虚拟超边和自适应Transformer来聚合关节特征，同时整合可见性先验，过滤掉来自被遮挡关节的不可靠信息。在基准数据集上的实验表明，在部分可见性条件下，准确率显著提高，最高可达68.8%。 AI
影响 提高了在现实、不受限环境中动作识别模型的鲁棒性。
排序理由 这是一篇详细介绍一种新颖的基于骨架的动作识别框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.00716v1 Announce Type: cross Abstract: Skeleton-based action recognition has achieved remarkable success by exploiting joint coordinates and their topological connections, yet prevailing methods overwhelmingly assume complete and clean skeleton inputs. In real-world de…
Skeleton-based action recognition has achieved remarkable success by exploiting joint coordinates and their topological connections, yet prevailing methods overwhelmingly assume complete and clean skeleton inputs. In real-world deployments, such as egocentric vision, crowded surv…