Reasoning about Human-Object Interactions through Dual Attention Networks

Computer Vision


Published on



Computer Vision

Objects are entities we act upon, where the functionality of an object is determined by how we interact with it. In this work we propose a Dual Attention Network model which reasons about human-object interactions. The dual-attentional framework weights the important features for objects and actions respectively. As a result, the recognition of objects and actions mutually benefit each other. The proposed model shows competitive classification performance on the human-object interaction dataset Something-Something. Besides, it can perform weak spatiotemporal localization and affordance segmentation, despite being trained only with video-level labels. The model not only finds when an action is happening and which object is being manipulated, but also identifies which part of the object is being interacted with.

Please cite our work using the BibTeX below.

    author={Xiao, Tete and Fan, Quanfu and Gutfreund, Dan and Monfort, Mathew and Oliva, Aude and Zhou, Bolei},
    title={Reasoning About Human-Object Interactions Through Dual Attention Networks},
Close Modal