PulseAugur
实时 08:37:30
English(EN) KGS-GCN: Kinematics-Driven Gaussian Splatting and Probabilistic Topology for Skeleton-Based Action Recognition

GCN-DevLSTM 通过李群路径发展增强了基于骨架的动作识别

研究人员推出了一种新颖的视频骨架动作识别架构 GCN-DevLSTM。该模型通过引入 G-Dev 层来增强现有的图卷积神经网络 (GCN),该层利用李群结构的路径发展来更好地捕捉时间动态。GCN-DevLSTM 模块能有效总结局部时间信息,同时保留高频细节,从而在 NTU-60NTU-120 等基准数据集上取得了改进的性能。 AI

影响 引入了一种改进骨架动作识别中时间建模的新方法,可能推动视频分析的发展。

排序理由 该集群包含一篇详细介绍计算机视觉任务新模型架构的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

GCN-DevLSTM 通过李群路径发展增强了基于骨架的动作识别

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Yuhan Chen, Yicui Shi, Guofa Li, Liping Zhang, Jie Li, Jiaxin Gao, Wenbo Chu ·

    KGS-GCN:基于运动学和概率拓扑的骨骼动作识别

    arXiv:2603.16943v2 Announce Type: replace-cross Abstract: Skeleton-based action recognition is widely applied in sensor-based systems, including human-computer interaction and intelligent surveillance. However, typical sensors produce sparse and discrete joint coordinates, often …

  2. arXiv cs.CV TIER_1 English(EN) · Lei Jiang, Weixin Yang, Xin Zhang, Hao Ni ·

    GCN-DevLSTM:基于骨骼的动作识别的路径开发

    arXiv:2403.15212v3 Announce Type: replace Abstract: Skeleton-based action recognition (SAR) in videos is an important but challenging task in computer vision. The recent state-of-the-art (SOTA) models for SAR are primarily based on graph convolutional neural networks (GCNs), whic…