.png){kind=icon}
.png){kind=icon}
Return
Interaction Confidence Attention for Human-Object Interaction Detection
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-025-02445-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In human-object interaction (HOI) detection task, ensuring that interactive pairs receive higher attention weights while reducing the weight of non-interaction pairs is imperative for enhancing HOI detection accuracy. Guiding attention learning is also a key aspect of existing transformer-based algorithms. To tackle this challenge, this study proposes a novel approach termed Interaction Confidence Score Learning Attention (ICSLA), which introduces weakening and augmentation operations into the original attention weight calculation and feature extraction processes. In ICSLA, feature learning is coupled with confidence score learning, simultaneously. Leveraging ICSLA, a new and universal decoder is devised, establishing a transformer-based one-stage HOI detection architecture. Experimental results demonstrate the effectiveness of the proposed method in improving HOI detection accuracy, offering valuable insights for further optimization of attention mechanisms.
Keywords:
Human-object interaction detection
Interaction confidence score learning attention
Weakening operation
Augmentation operation
Journal
IF:
9.3
Papers:
3.9K
Citations:
2.8W