Inferring Affective Experience From the Big Picture Metaphor: A Two-Dimensional Visual Breadth Model

Song Tong, Jingyi Duan, Xuefeng Liang, Takatsune Kumada, Kaiping Peng, Ryoichi Nakashima; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 5880-5888

Abstract


This study explores the psychological significance of the commonly used visual metaphor 'seeing the big picture' and examines whether and how it leads to positive experiences in real-life situations. To elucidate this phenomenon, a two-dimensional model of visual breadth is proposed, then respectively operationalized by two computer vision approaches. Our approaches are evaluated on a collected data set with 29,216 photos. The results revealed that physical and contextual breadth are two essential visual structures that compose a 'big picture'. Furthermore, these two visual breadths interactively shape people's affective experiences. This study provides insight into the psychological implications of the 'big picture' metaphor and sheds light on its practical potential for computer vision approaches and affective computing in the wild.

Related Material


[pdf]
[bibtex]
@InProceedings{Tong_2023_CVPR, author = {Tong, Song and Duan, Jingyi and Liang, Xuefeng and Kumada, Takatsune and Peng, Kaiping and Nakashima, Ryoichi}, title = {Inferring Affective Experience From the Big Picture Metaphor: A Two-Dimensional Visual Breadth Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {5880-5888} }