arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.02042cs.CV
收藏

基于姿态的模块化网络人机交互检测

Pose-based Modular Network for Human-Object Interaction Detection

Guangdong University of Technology(广东工业大学);Chinese University of Hong Kong(香港中文大学)

Zhijun Liang, Junfa Liu, Yisheng Guan, Juan Rojas

摘要:

人-物交互检测是场景理解中的一项关键任务。目标是推断场景中的三元组<主语、谓语、宾语>。在这项工作中,我们注意到,人类姿势本身以及相对于目标对象的人类姿势的相对空间信息可以提供信息线索HOI检测。我们贡献了一个基于姿态的模块化网络(PMN),它探讨了绝对姿态特征和相对空间姿态特征,以提高HOI检测,并与现有的网络完全兼容。我们的模块由一个分支组成,该分支首先独立地处理每个关节的相对空间姿态特征。另一个分支通过完全连接的图结构更新绝对姿态特征。然后将处理后的姿势特征馈送到动作分类器中。为了评估我们提出的方法,我们将该模块与最先进的模型VS-GATs相结合,并在两个公共基准测试:V-COCO和HICO-DET上获得了显着的改进,这表明了它的有效性和灵活性。代码可在\url{https://github.com/birlrobotics/PMN}上获得。

英文摘要:

Human-object interaction(HOI) detection is a critical task in scene understanding. The goal is to infer the triplet <subject, predicate, object> in a scene. In this work, we note that the human pose itself as well as the relative spatial information of the human pose with respect to the target object can provide informative cues for HOI detection. We contribute a Pose-based Modular Network (PMN) which explores the absolute pose features and relative spatial pose features to improve HOI detection and is fully compatible with existing networks. Our module consists of a branch that first processes the relative spatial pose features of each joint independently. Another branch updates the absolute pose features via fully connected graph structures. The processed pose features are then fed into an action classifier. To evaluate our proposed method, we combine the module with the state-of-the-art model named VS-GATs and obtain significant improvement on two public benchmarks: V-COCO and HICO-DET, which shows its efficacy and flexibility. Code is available at \url{https://github.com/birlrobotics/PMN}.

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。

↑