Where do emotions come from? Predicting the Emotion Stimuli Map

Kuan Chuan Peng; Amir Sadovnik; Andrew Gallagher; Tsuhan Chen

doi:10.1109/ICIP.2016.7532430

Where do emotions come from? Predicting the Emotion Stimuli Map

Kuan Chuan Peng, Amir Sadovnik, Andrew Gallagher, Tsuhan Chen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

90 Scopus citations

Abstract

Which parts of an image evoke emotions in an observer? To answer this question, we introduce a novel problem in computer vision - predicting an Emotion Stimuli Map (ESM), which describes pixel-wise contribution to evoked emotions. Building a new image database, EmotionROI, as a benchmark for predicting the ESM, we find that the regions selected by saliency and objectness detection do not correctly predict the image regions which evoke emotion. Although objects represent important regions for evoking emotion, parts of the background are also important. Based on this fact, we propose using fully convolutional networks for predicting the ESM. Both qualitative and quantitative experimental results confirm that our method can predict the regions which evoke emotion better than both saliency and objectness detection.

Original language	English
Title of host publication	2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
Publisher	IEEE Computer Society
Pages	614-618
Number of pages	5
ISBN (Electronic)	9781467399616
DOIs	https://doi.org/10.1109/ICIP.2016.7532430
State	Published - Aug 3 2016
Externally published	Yes
Event	23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States Duration: Sep 25 2016 → Sep 28 2016

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2016-August
ISSN (Print)	1522-4880

Conference

Conference	23rd IEEE International Conference on Image Processing, ICIP 2016
Country/Territory	United States
City	Phoenix
Period	09/25/16 → 09/28/16

Keywords

Emotion stimuli map
Fully convolutional networks

Access to Document

10.1109/ICIP.2016.7532430

Cite this

Peng, K. C., Sadovnik, A., Gallagher, A., & Chen, T. (2016). Where do emotions come from? Predicting the Emotion Stimuli Map. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings (pp. 614-618). Article 7532430 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2016-August). IEEE Computer Society. https://doi.org/10.1109/ICIP.2016.7532430

@inproceedings{38a13223f9f74671b372895bae5526bc,

title = "Where do emotions come from? Predicting the Emotion Stimuli Map",

abstract = "Which parts of an image evoke emotions in an observer? To answer this question, we introduce a novel problem in computer vision - predicting an Emotion Stimuli Map (ESM), which describes pixel-wise contribution to evoked emotions. Building a new image database, EmotionROI, as a benchmark for predicting the ESM, we find that the regions selected by saliency and objectness detection do not correctly predict the image regions which evoke emotion. Although objects represent important regions for evoking emotion, parts of the background are also important. Based on this fact, we propose using fully convolutional networks for predicting the ESM. Both qualitative and quantitative experimental results confirm that our method can predict the regions which evoke emotion better than both saliency and objectness detection.",

keywords = "Emotion stimuli map, Fully convolutional networks",

author = "Peng, {Kuan Chuan} and Amir Sadovnik and Andrew Gallagher and Tsuhan Chen",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 23rd IEEE International Conference on Image Processing, ICIP 2016 ; Conference date: 25-09-2016 Through 28-09-2016",

year = "2016",

month = aug,

day = "3",

doi = "10.1109/ICIP.2016.7532430",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "614--618",

booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",

}

Peng, KC, Sadovnik, A, Gallagher, A & Chen, T 2016, Where do emotions come from? Predicting the Emotion Stimuli Map. in 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings., 7532430, Proceedings - International Conference on Image Processing, ICIP, vol. 2016-August, IEEE Computer Society, pp. 614-618, 23rd IEEE International Conference on Image Processing, ICIP 2016, Phoenix, United States, 09/25/16. https://doi.org/10.1109/ICIP.2016.7532430

Where do emotions come from? Predicting the Emotion Stimuli Map. / Peng, Kuan Chuan; Sadovnik, Amir; Gallagher, Andrew et al.
2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. IEEE Computer Society, 2016. p. 614-618 7532430 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2016-August).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Where do emotions come from? Predicting the Emotion Stimuli Map

AU - Peng, Kuan Chuan

AU - Sadovnik, Amir

AU - Gallagher, Andrew

AU - Chen, Tsuhan

PY - 2016/8/3

Y1 - 2016/8/3

N2 - Which parts of an image evoke emotions in an observer? To answer this question, we introduce a novel problem in computer vision - predicting an Emotion Stimuli Map (ESM), which describes pixel-wise contribution to evoked emotions. Building a new image database, EmotionROI, as a benchmark for predicting the ESM, we find that the regions selected by saliency and objectness detection do not correctly predict the image regions which evoke emotion. Although objects represent important regions for evoking emotion, parts of the background are also important. Based on this fact, we propose using fully convolutional networks for predicting the ESM. Both qualitative and quantitative experimental results confirm that our method can predict the regions which evoke emotion better than both saliency and objectness detection.

AB - Which parts of an image evoke emotions in an observer? To answer this question, we introduce a novel problem in computer vision - predicting an Emotion Stimuli Map (ESM), which describes pixel-wise contribution to evoked emotions. Building a new image database, EmotionROI, as a benchmark for predicting the ESM, we find that the regions selected by saliency and objectness detection do not correctly predict the image regions which evoke emotion. Although objects represent important regions for evoking emotion, parts of the background are also important. Based on this fact, we propose using fully convolutional networks for predicting the ESM. Both qualitative and quantitative experimental results confirm that our method can predict the regions which evoke emotion better than both saliency and objectness detection.

KW - Emotion stimuli map

KW - Fully convolutional networks

UR - http://www.scopus.com/inward/record.url?scp=85006791261&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2016.7532430

DO - 10.1109/ICIP.2016.7532430

M3 - Conference contribution

AN - SCOPUS:85006791261

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 614

EP - 618

BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings

PB - IEEE Computer Society

T2 - 23rd IEEE International Conference on Image Processing, ICIP 2016

Y2 - 25 September 2016 through 28 September 2016

ER -

Where do emotions come from? Predicting the Emotion Stimuli Map

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this