HOI Analysis: Integrating and Decomposing Human-Object Interaction

TL;DR

This paper introduces a novel analytical approach to Human-Object Interaction (HOI) learning, decomposing interactions into human and object components and using transformations to improve detection accuracy.

Contribution

It proposes the HOI Analysis framework and the Integration-Decomposition Network (IDN) to enhance HOI detection by representing interactions through signal decomposition and transformation.

Findings

Achieved state-of-the-art performance on HOI detection benchmarks.

Demonstrated the effectiveness of decomposition and integration in modeling HOI.

Provided a new analytical perspective for HOI learning.

Abstract

Human-Object Interaction (HOI) consists of human, object and implicit interaction/verb. Different from previous methods that directly map pixels to HOI semantics, we propose a novel perspective for HOI learning in an analytical manner. In analogy to Harmonic Analysis, whose goal is to study how to represent the signals with the superposition of basic waves, we propose the HOI Analysis. We argue that coherent HOI can be decomposed into isolated human and object. Meanwhile, isolated human and object can also be integrated into coherent HOI again. Moreover, transformations between human-object pairs with the same HOI can also be easier approached with integration and decomposition. As a result, the implicit verb will be represented in the transformation function space. In light of this, we propose an Integration-Decomposition Network (IDN) to implement the above transformations and achieve state-of-the-art performance on widely-used HOI detection benchmarks. Code is available at https://github.com/DirtyHarryLYL/HAKE-Action-Torch/tree/IDN-(Integrating-Decomposing-Network).