arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.09283cs.CV
收藏

用于连续细粒度动作分割的耦合生成对抗网络

Coupled Generative Adversarial Network for Continuous Fine-grained Action Segmentation

Queensland University of Technology(昆士兰科技大学)

Harshala Gammulle, Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes

摘要:

我们提出了一种新的条件GAN(cGAN)模型连续细粒度的人体动作分割,利用多模态数据和学习场景上下文信息。所提出的方法利用两个GANs:称为动作GAN和辅助GAN,其中动作GAN被训练为在当前RGB帧上操作,而辅助GAN利用补充信息,例如深度或光流。两个GANs的目标都是生成类似的“动作代码”,即当前动作的矢量表示。为了促进这一过程的上下文提取器,结合数据和最近的输出,从两种模式被用来提取上下文信息,以帮助识别。其结果是一个经常性的GAN架构,学习任务特定的损失函数从多个功能模态。对所提出的模型的变体进行了广泛的评估,以显示在所提出的网络中利用不同信息流(如上下文和辅助信息)的重要性;并表明我们的模型能够在三个广泛使用的数据集上表现优于最先进的方法:50沙拉,MERL购物和佐治亚理工学院以自我为中心的活动,包括静态和动态相机设置。

英文摘要:

We propose a novel conditional GAN (cGAN) model for continuous fine-grained human action segmentation, that utilises multi-modal data and learned scene context information. The proposed approach utilises two GANs: termed Action GAN and Auxiliary GAN, where the Action GAN is trained to operate over the current RGB frame while the Auxiliary GAN utilises supplementary information such as depth or optical flow. The goal of both GANs is to generate similar `action codes', a vector representation of the current action. To facilitate this process a context extractor that incorporates data and recent outputs from both modes is used to extract context information to aid recognition. The result is a recurrent GAN architecture which learns a task specific loss function from multiple feature modalities. Extensive evaluations on variants of the proposed model to show the importance of utilising different information streams such as context and auxiliary information in the proposed network; and show that our model is capable of outperforming state-of-the-art methods for three widely used datasets: 50 Salads, MERL Shopping and Georgia Tech Egocentric Activities, comprising both static and dynamic camera settings.

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。

↑