Summary of Explicit Modelling Of Theory Of Mind For Belief Prediction in Nonverbal Social Interactions, by Matteo Bortoletto et al.
Explicit Modelling of Theory of Mind for Belief Prediction in Nonverbal Social Interactions
by Matteo Bortoletto, Constantin Ruhdorfer, Lei Shi, Andreas Bulling
First submitted to arxiv on: 9 Jul 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed MToMnet neural network is a Theory of Mind (ToM) model that predicts beliefs and their dynamics during human social interactions using multimodal input. This paper fills the gap in existing belief modelling methods by incorporating explicit ToM modelling and integrating multiple modalities, including scene videos, object locations, human gaze, and body language. The MToMnet variants fuse latent representations or re-rank classification scores to improve prediction accuracy. Evaluations on two real-world datasets demonstrate that MToMnet outperforms existing methods while requiring fewer parameters. This breakthrough opens up opportunities for artificial intelligent systems that can effectively collaborate with humans. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary We developed a special neural network called MToMnet that helps us understand what people believe and how those beliefs change during conversations or interactions. Right now, computers are not very good at understanding these things, but this new model does better! It uses lots of information like videos, pictures, and body language to figure out what people are thinking. We tested it on two big datasets and it did way better than other computer models while using fewer “brain cells” (computer parts). This is an important step towards creating computers that can work well with humans. |
Keywords
» Artificial intelligence » Classification » Neural network
