Vision-Based Happiness Inference: A Feasibility Case-Study (bibtex)
by Sarsenbayeva, Zhanna, Ferreira, Denzil, van Berkel, Niels, Luo, Chu, Vaisanen, Mikko, Kostakos, Vassilis and Goncalves, Jorge
Abstract:
To humanize interaction between users and computers, one needs the ability to infer the users' mood. One approach is to use a vision-based approach. We quantify the 'preview effect' bias in visual mood assessment. We demonstrate that automated tools which infer user mood from photographs or video may be affected by the presentation methodology used while performing image capture. Specifically, we demonstrate that showing a "preview" of oneself, i.e., a mirror, increases the accuracy of the visual mood inference algorithms present in Google's Mobile Vision API. Our findings show that studies that incorporate visual mood assessment should include "preview" images to reduce bias and increase the reliability of vision-based happiness inference.
Reference:
Z. Sarsenbayeva, D. Ferreira, N. van Berkel, C. Luo, M. Vaisanen, V. Kostakos, J. Goncalves, "Vision-Based Happiness Inference: A Feasibility Case-Study", in Adjunct Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp'17 Adj.), 2017, 494-499.
Bibtex Entry:
@inproceedings{Sarsenbayeva2017VisionHappinessCase,
	Abstract = {To humanize interaction between users and computers, one needs the ability to infer the users' mood. One approach is to use a vision-based approach. We quantify the 'preview effect' bias in visual mood assessment. We demonstrate that automated tools which infer user mood from photographs or video may be affected by the presentation methodology used while performing image capture. Specifically, we demonstrate that showing a "preview" of oneself, i.e., a mirror, increases the accuracy of the visual mood inference algorithms present in Google's Mobile Vision API. Our findings show that studies that incorporate visual mood assessment should include "preview" images to reduce bias and increase the reliability of vision-based happiness inference.},
	Author = {Sarsenbayeva, Zhanna and Ferreira, Denzil and van Berkel, Niels and Luo, Chu and Vaisanen, Mikko and Kostakos, Vassilis and Goncalves, Jorge},
	Booktitle = {Adjunct Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing},
	Date-Modified = {2019-12-26 16:42:28 +0100},
	Doi = {10.1145/3123024.3124438},
	Location = {UbiComp'17 Adj.},
	Pages = {494-499},
	Title = {Vision-Based Happiness Inference: A Feasibility Case-Study},
	Type = {Conference Paper},
	Url = {https://www.nielsvanberkel.com/files/publications/ubicomp2017b.pdf},
	Year = {2017}}
Powered by bibtexbrowser