Rb-PaStaNet: A Few-Shot Human-Object Interaction Detection Based on Rules and Part States
This work addresses the challenge of rare HOI detection for computer vision applications, but it is incremental as it builds on an existing method with added rules.
The paper tackles the problem of detecting rare human-object interaction (HOI) classes by incorporating human-labeled rules into PaStaNet, resulting in Rb-PaStaNet, which shows improvements in rare classes and more significant gains in non-rare classes and overall performance.
Existing Human-Object Interaction (HOI) Detection approaches have achieved great progress on nonrare classes while rare HOI classes are still not well-detected. In this paper, we intend to apply human prior knowledge into the existing work. So we add human-labeled rules to PaStaNet and propose Rb-PaStaNet aimed at improving rare HOI classes detection. Our results show a certain improvement of the rare classes, while the non-rare classes and the overall improvement is more considerable.