Learning from Observer Gaze:Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition

TL;DR

This paper introduces a new dataset and model for zero-shot interaction-oriented attention prediction, leveraging human gaze data to improve understanding of complex human-object interactions and enhance interaction recognition models.

Contribution

It presents a novel gaze fixation dataset, a zero-shot attention prediction task, and an interactive attention model that outperforms existing methods and benefits interaction recognition.

Findings

The IG dataset contains 530,000 fixation points across 740 interaction categories.

The IA model surpasses state-of-the-art approaches in ZeroIA and supervised settings.

Incorporating human attention data improves HOI model performance and interpretability.

Abstract

Most existing attention prediction research focuses on salient instances like humans and objects. However, the more complex interaction-oriented attention, arising from the comprehension of interactions between instances by human observers, remains largely unexplored. This is equally crucial for advancing human-machine interaction and human-centered artificial intelligence. To bridge this gap, we first collect a novel gaze fixation dataset named IG, comprising 530,000 fixation points across 740 diverse interaction categories, capturing visual attention during human observers cognitive processes of interactions. Subsequently, we introduce the zero-shot interaction-oriented attention prediction task ZeroIA, which challenges models to predict visual cues for interactions not encountered during training. Thirdly, we present the Interactive Attention model IA, designed to emulate human observers cognitive processes to tackle the ZeroIA problem. Extensive experiments demonstrate that the proposed IA outperforms other state-of-the-art approaches in both ZeroIA and fully supervised settings. Lastly, we endeavor to apply interaction-oriented attention to the interaction recognition task itself. Further experimental results demonstrate the promising potential to enhance the performance and interpretability of existing state-of-the-art HOI models by incorporating real human attention data from IG and attention labels generated by IA.