Reasoning About Human-Object Interactions Through Dual Attention Networks

Tete Xiao, Quanfu Fan, Dan Gutfreund, Mathew Monfort, Aude Oliva, Bolei Zhou; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 3919-3928

Abstract


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.

Related Material


[pdf]
[bibtex]
@InProceedings{Xiao_2019_ICCV,
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},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}