Recent years have witnessed rapid progress in detecting and recognizing
individual object instances. To understand the situation in a scene, however,
computers need to recognize how humans interact with surrounding objects. In
this paper, we tackle the challenging task of detecting human-object
interactions (HOI). Our core idea is that the appearance of a person or an
object instance contains informative cues on which relevant parts of an image
to attend to for facilitating interaction prediction. To exploit these cues, we
propose an instance-centric attention module that learns to dynamically
highlight regions in an image conditioned on the appearance of each instance.
Such an attention-based network allows us to selectively aggregate features
relevant for recognizing HOIs. We validate the efficacy of the proposed network
on the Verb in COCO and HICO-DET datasets and show that our approach compares
favorably with the state-of-the-arts.

本文提出了一种利用实例注意力重点聚合一张图像中与人 - 物交互相关的特征，实现人 - 物交互检测任务的方法，并在 COCO 和 HICO-DET 数据集上验证了其有效性，结果明显优于现有技术。