Relational Future Captioning Model for Explaining Likely Collisions in Daily Tasks
This addresses the need for domestic service robots to explain collision risks before performing tasks, benefiting elderly or disabled people, but it appears incremental as it builds on existing transformer-based methods.
The paper tackles the problem of generating captions about future events, specifically collision risks for domestic service robots, by proposing the Relational Future Captioning Model (RFCM), which outperforms a baseline method on two datasets.
Domestic service robots that support daily tasks are a promising solution for elderly or disabled people. It is crucial for domestic service robots to explain the collision risk before they perform actions. In this paper, our aim is to generate a caption about a future event. We propose the Relational Future Captioning Model (RFCM), a crossmodal language generation model for the future captioning task. The RFCM has the Relational Self-Attention Encoder to extract the relationships between events more effectively than the conventional self-attention in transformers. We conducted comparison experiments, and the results show the RFCM outperforms a baseline method on two datasets.