Body-part Attention Probability for Measuring Gaze During Impression Word Evaluation
[Abstract]
We investigate how to probabilistically describe the distribution of gaze with respect to body parts when an observer evaluates impression words for an individual in an image.
In the field of cognitive science, analytical studies have reported how observers view a person in an image and form impressions about him or her.
However, a probabilistic representation of their gaze distributions has not yet been discussed.
Here, we represent the gaze distribution as a conditional probability according to each body part.
To do this, we measured the gaze distribution of observers performing a task that consists of assessing an impression word. We then evaluated whether these distributions change with respect to the impression word and body part specified in the task.
Experimental results show that the divergences between the conditional probabilities of gaze distributions are large when the impression words or body parts of the task are changed.
[Publications]
- 木下 顕, 井上 路子, 西山 正志, 岩井 儀雄,
身体への印象単語を判別する際に計測された視線位置分布の確率表現,
精密工学会誌, vol. 86, no. 12, pp. 989 - 996, December 2020.
- Ken Kinoshita, Michiko Inoue, Masashi Nishiyama, Yoshio Iwai,
Body-part Attention Probability for Measuring Gaze During Impression Word Evaluation,
Proceedings of 23rd International Conference on Human-Computer Interaction (HCII), CCIS 1420, pp. 105 - 112, July 2021.
[Short movie]