Who is Mistaken?
By Benjamin Eysenbach, Carl Vondrick, Antonio Torralba. 2016
18 citations recorded by the source corpus.
Recognizing when people have false beliefs is crucial for understanding their actions. We introduce the novel problem of identifying when people in abstract scenes have incorrect beliefs. We present a dataset of scenes, each visually depicting an 8-frame story in which a character has a mistaken belief. We then create a representation of characters' beliefs for two tasks in human action understanding: predicting who is mistaken, and when they are mistaken. Experiments suggest that our method for identifying mistaken characters performs better on these tasks than simple baselines. Diagnostics on our model suggest it learns important cues for recognizing mistaken beliefs, such as gaze. We believe models of people's beliefs will have many applications in action understanding, robotics, and healthcare.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Social Psychology, Philosophy
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- T. Griffiths
- Devi Parikh
- Deshraj Yadav
- Prithvijit Chattopadhyay
- Viraj Prabhu
- Alison Gopnik
- Arjun Chandrasekaran
- Aida Nematzadeh
In Computer Vision and Pattern Recognition
- Prithvijit Chattopadhyay
- Deshraj Yadav
- Viraj Prabhu
- Arjun Chandrasekaran
- Aida Nematzadeh
- Kaylee Burns
- Devi Parikh
- T. Griffiths
In Social Psychology
In Philosophy
- Devi Parikh
- T. Griffiths
- Alison Gopnik
- Deshraj Yadav
- Arjun Chandrasekaran
- Viraj Prabhu
- Prithvijit Chattopadhyay
Citations in the corpus
- Evaluating Theory of Mind in Question Answering (2018, background): “Eysenbach et al. (2016) created a dataset of scene-description pairs where each scene is a set of visual frames and some frames include people with mistaken beliefs.”
- It Takes Two to Tango: Towards Theory of AI's Mind (2017, background): “However, AI research has traditionally placed much of the burden on the AI to play its part in the team: to be more accurate [32, 56, 65, 57, 39], more human-like [4, 36, 48, 23, 3, 54, 50, 10, 13], understand our intentions [49, 67, 68], beliefs [22], tendencies [18], contexts [55], and mental stat”
- Obj2Text: Generating Visually Descriptive Language from Object Layouts (2017, unknown): “The works of Vedantam et al. (2015b); Eysenbach et al. (2016) proposed methods to learn common-sense knowledge from clipart scenes, while the method of Yatskar et al. (2016), similar to our work, leverages object annotations for natural images.”