arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.00828cs.CV
收藏

从新观点学习人类动作识别的深度模型

Learning a Deep Model for Human Action Recognition from Novel Viewpoints

The University of Western Australia(西澳大学);University of Central Florida(中佛罗里达大学)

Hossein Rahmani, Ajmal Mian, Mubarak Shah

摘要:

从未知的和看不见的(新的)观点识别人类行为是一个具有挑战性的问题。本文从新颖的角度提出了一种用于人体动作识别的鲁棒非线性知识转移模型(R-NKTM)。所提出的R-NKTM是一个深度全连接的神经网络,通过找到连接视图的非线性虚通路,将人类行为的知识从任何未知视图转移到共享的高级虚拟视图。R-NKTM是从适合真实运动捕捉数据的合成3D人体模型的密集轨迹中学习的,并推广到人类动作的真实视频。我们的技术的优势在于,我们为所有动作和所有观点学习单个R-NKTM,用于任何真实人类动作视频的知识转移,而无需重新训练或微调模型。因此,R-NKTM可以有效地扩展以纳入新的操作类。R-NKTM是通过虚拟标签学习的,在任何阶段都不需要了解相机视点。在三个基准交叉视图人体动作数据集上的实验表明,我们的方法优于现有的最先进的。

英文摘要:

Recognizing human actions from unknown and unseen (novel) views is a challenging problem. We propose a Robust Non-Linear Knowledge Transfer Model (R-NKTM) for human action recognition from novel views. The proposed R-NKTM is a deep fully-connected neural network that transfers knowledge of human actions from any unknown view to a shared high-level virtual view by finding a non-linear virtual path that connects the views. The R-NKTM is learned from dense trajectories of synthetic 3D human models fitted to real motion capture data and generalizes to real videos of human actions. The strength of our technique is that we learn a single R-NKTM for all actions and all viewpoints for knowledge transfer of any real human action video without the need for re-training or fine-tuning the model. Thus, R-NKTM can efficiently scale to incorporate new action classes. R-NKTM is learned with dummy labels and does not require knowledge of the camera viewpoint at any stage. Experiments on three benchmark cross-view human action datasets show that our method outperforms existing state-of-the-art.

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。

↑