Extrapolating continuous color emotions through deep learning

Ram, V. N. V. Sri; Schaposnik, Laura P.; Konstantinou, Nikos; Volkan, Eliz; Παπαδάτου-Παστού, Μαριέττα; Manav, Banu; Jonauskaitė, Domicėlė; Möhr, Christine

doi:10.1103/physrevresearch.2.033350

Cited by 7 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We received ethics approval from the Research Ethics Commission of the University of Lausanne (C_SSP_032020_00003). Forty‐six per cent of this dataset has been published before, answering different research questions (Jonauskaite, Abdel‐Khalek, et al., 2019; Jonauskaite, Abu‐Akel, et al., 2020; Jonauskaite, Parraga, et al., 2020; Jonauskaite, Wicker, et al., 2019; Ram et al., 2020; Uusküla et al., 2023). For the current study, we made efforts to recruit older participants so we could analyse the data from an adult lifespan perspective.…”

Section: Methodsmentioning

confidence: 99%

A comparative analysis of colour–emotion associations in 16–88‐year‐old adults from 31 countries

Jonauskaite,

Epicoco,

Al‐rasheed

et al. 2023

British J of Psychology

Self Cite

View full text Add to dashboard Cite

As people age, they tend to spend more time indoors, and the colours in their surroundings may significantly impact their mood and overall well‐being. However, there is a lack of empirical evidence to provide informed guidance on colour choices, irrespective of age group. To work towards informed choices, we investigated whether the associations between colours and emotions observed in younger individuals also apply to older adults. We recruited 7393 participants, aged between 16 and 88 years and coming from 31 countries. Each participant associated 12 colour terms with 20 emotion concepts and rated the intensity of each associated emotion. Different age groups exhibited highly similar patterns of colour–emotion associations (average similarity coefficient of .97), with subtle yet meaningful age‐related differences. Adolescents associated the greatest number but the least positively biased emotions with colours. Older participants associated a smaller number but more intense and more positive emotions with all colour terms, displaying a positivity effect. Age also predicted arousal and power biases, varying by colour. Findings suggest parallels in colour–emotion associations between younger and older adults, with subtle but significant age‐related variations. Future studies should next assess whether colour–emotion associations reflect what people actually feel when exposed to colour.

show abstract

Section: Methodsmentioning

confidence: 99%

A comparative analysis of colour–emotion associations in 16–88‐year‐old adults from 31 countries

Jonauskaite,

Epicoco,

Al‐rasheed

et al. 2023

British J of Psychology

Self Cite

View full text Add to dashboard Cite

show abstract

“…It was determined that red was the most noticed and preferred logo color after combining the gaze and preference data. In a sense, it demonstrated that the subjects' attention and significance were unified, and it also indicated that red, a prevalent accent color in traditional Chinese culture, evoked the most intense emotions and influenced people's evaluation of cultural aesthetics [50]. Unlike the Western cultural environment where red is seen as dangerous and as a warning, the people of the East see red as a color of celebration.…”

Section: Discussionmentioning

confidence: 91%

Design Element Preferences in Public Facilities: An Eye Tracking Study

Liu

Zhi-cheng

2023

Land

View full text Add to dashboard Cite

As a highly used form of architecture, public facilities are closely related to people’s daily lives. The aesthetic level of their design greatly affects the quality of people’s lives and interactions, as well as the appearance of the whole area. However, research on their design elements has not received enough attention, and few quantitative studies on the design of public facilities simultaneously focus on multiple influencing factors such as color and material. Therefore, this study uses eye-tracking technology and audience aesthetic preference evaluation to explore the appropriate combination of color and materials in sign design. This study found that, in the design of public facilities and in terms of aesthetic preference, firstly, color has more influence on subjective preference and objective gaze behavior than material. Secondly, men prefer technological and changeable colors and materials, and women prefer soft and uniform materials. Finally, visitors spend more time gazing at their preferred signs, which means that visitors’ top-down gaze behavior and bottom-up psychological perception are highly unified. Regarding material perception, visitors’ subjective preferences are influenced by the physical or cultural properties of the material itself. This study’s results will provide suggestions for future urban and landscape architecture design in terms of color and material aesthetics, and the research methodology can be applied to more scenarios in environmental spaces.

show abstract

“…The field of affective computation has roots going back more than three decades (Minsky, 1986;Picard, 1995). However, it is only in the last decade that it has been possible to advance in a deeper comprehension and formulation about emotional inference based on digital images (Chen, Zhang, & Allebach, 2015;Kim, Lee, & Provost, 2013;Ram et al, 2020;Yao et al, 2020;Zhao et al, 2014); what we today know as affective computing. This has been achieved thanks to major advances in computational techniques based on deep learning architectures, which have aided in advancing automatic comprehension of emotions.…”

Section: Recognizing Emotions: Affective Computationmentioning

confidence: 99%

Detection of Emotions in Artworks Using a Convolutional Neural Network Trained on Non-Artistic Images: A Methodology to Reduce the Cross-Depiction Problem

González-Martín

Carrasco

Wielandt

2023

Empirical Studies of the Arts

View full text Add to dashboard Cite

This research is framed within the study of automatic recognition of emotions in artworks, proposing a methodology to improve performance in detecting emotions when a network is trained with an image type different from the entry type, which is known as the cross-depiction problem. To achieve this, we used the QuickShift algorithm, which simplifies images’ resources, and applied it to the Open Affective Standardized Image (OASIS) dataset as well as the WikiArt Emotion dataset. Both datasets are also unified under a binary emotional system. Subsequently, a model was trained based on a convolutional neural network using OASIS as a learning base, in order to then be applied on the WikiArt Emotion dataset. The results show an improvement in the general prediction performance when applying QuickShift (73% overall). However, we can observe that artistic style influences the results, with minimalist art being incompatible with the methodology proposed.

show abstract

Extrapolating continuous color emotions through deep learning

Cited by 7 publications

References 22 publications

A comparative analysis of colour–emotion associations in 16–88‐year‐old adults from 31 countries

A comparative analysis of colour–emotion associations in 16–88‐year‐old adults from 31 countries

Design Element Preferences in Public Facilities: An Eye Tracking Study

Detection of Emotions in Artworks Using a Convolutional Neural Network Trained on Non-Artistic Images: A Methodology to Reduce the Cross-Depiction Problem

Contact Info

Product

Resources

About