Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video
This work addresses the challenge of forecasting interactions in egocentric vision, which is crucial for applications like assistive robotics and augmented reality, though it is incremental in improving existing methods.
The paper tackles the problem of anticipating human-object interactions in first-person videos by jointly predicting motor attention (intentional hand movement), interaction hotspots, and future actions, achieving new state-of-the-art results on EGTEA Gaze+ and EPIC-Kitchens datasets.
We address the challenging task of anticipating human-object interaction in first person videos. Most existing methods ignore how the camera wearer interacts with the objects, or simply consider body motion as a separate modality. In contrast, we observe that the international hand movement reveals critical information about the future activity. Motivated by this, we adopt intentional hand movement as a future representation and propose a novel deep network that jointly models and predicts the egocentric hand motion, interaction hotspots and future action. Specifically, we consider the future hand motion as the motor attention, and model this attention using latent variables in our deep model. The predicted motor attention is further used to characterise the discriminative spatial-temporal visual features for predicting actions and interaction hotspots. We present extensive experiments demonstrating the benefit of the proposed joint model. Importantly, our model produces new state-of-the-art results for action anticipation on both EGTEA Gaze+ and the EPIC-Kitchens datasets. Our project page is available at https://aptx4869lm.github.io/ForecastingHOI/