Reasoning About Human-Object Interactions Through Dual Attention Networks

Citations Over TimeTop 10% of 2019 papers

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 Papers

• → Ecological perception affords an explanation of object permanence(2005)3 cited
• → The role of the action context in object affordance(2018)3 cited
• → The influence of cooperative action intention on object affordance: evidence from the perspective-taking ability of individuals(2021)2 cited
• → Reasoning About Human-Object Interactions Through Dual Attention Networks(2019)3 cited
• → Enabling Affordance-Guided Grasp Synthesis for Robotic Manipulation(2020)