论文标题
基于姿势的模块化网络，用于人类对象相互作用检测
Pose-based Modular Network for Human-Object Interaction Detection
论文作者
论文摘要
人类对象相互作用（HOI）检测是场景理解中的关键任务。目标是在场景中推断三胞胎<主题，谓词，对象>。在这项工作中，我们注意到，人类姿势以及人类姿势相对于目标对象的相对空间信息可以为HOI检测提供信息的线索。我们为基于姿势的模块化网络（PMN）贡献，该网络探讨了绝对姿势特征和相对空间姿势特征以改善HOI检测，并且与现有网络完全兼容。我们的模块由一个分支组成，该分支首先处理每个关节的相对空间姿势特征。另一个分支通过完全连接的图形结构更新了绝对姿势特征。然后将处理的姿势特征馈入动作分类器。为了评估我们提出的方法，我们将模块与名为VS-Gats的最新模型相结合，并在两个公共基准上获得了显着改进：V-Coco和Hico-Det，该基准显示其功效和灵活性。代码可在\ url {https://github.com/birlrobotics/pmn}中获得。
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}.
