Aesthetics and Emotions in Images

Joshi, Dhiraj; Datta, Ritendra; Fedorovskaya, Elena A.; Luong, Quang-Tuan; Wang, James; Li, Jia; Luo, Jiebo

doi:10.1109/msp.2011.941851

Cited by 360 publications

(173 citation statements)

References 83 publications

Supporting

Mentioning

163

Contrasting

Order By: Relevance

“…Current computational models for quantifying aesthetics are based on low level features of design elements [28,99,197,198]. We believe that both outcomes of this work, the inferred color semantics and the application of the LDA-dual model to color semantics can leverage the current models of quantifying aesthetics.…”

Section: Quantifying Aestheticsmentioning

confidence: 90%

“…Our motivation in this work is to model visual balance. Learning visual balance from the work of professionals in design and photography may help to enable the automatic design applications in layout creation [109,110,112,151,[221][222][223][224][225][226][227][228][229][230][231][232][233][234], content retargeting [235][236][237][238][239], cropping [220,238,240,241], photo composition [238,242]and quantifying aesthetics of layouts [22,28,48,198,[243][244][245]. Nevertheless, there is no rigorous model to describe visual balance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Quantifying Aesthetics of Visual Design Applied to Automatic Design

Jahanian

2016

Springer Theses

View full text Add to dashboard Cite

Section: Quantifying Aestheticsmentioning

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Quantifying Aesthetics of Visual Design Applied to Automatic Design

Jahanian

2016

Springer Theses

View full text Add to dashboard Cite

“…The former provides ratings of emotion (in terms of pleasure, arousal and dominance) for 369 images, while the latter provides 520 images associated to negative sentiment, 89 neutral and 121 positive images. Another related direction is given by works on aesthetics: surveys are provided in [22,46]. However, none of these datasets deal with social media.…”

Section: Sentiment Analysis In Social Imagesmentioning

confidence: 99%

A multimodal feature learning approach for sentiment analysis of social network multimedia

Baecchi

Uricchio

Bertini

et al. 2015

Multimed Tools Appl

View full text Add to dashboard Cite

In this paper we investigate the use of a multimodal feature learning approach, using neural network based models such as Skip-gram and Denoising Autoencoders, to address sentiment analysis of micro-blogging content, such as Twitter short messages, that are composed by a short text and, possibly, an image. The approach used in this work is motivated by the recent advances in: i) training language models based on neural networks that have proved to be extremely efficient when dealing with web-scale text corpora, and have shown very good performances when dealing with syntactic and semantic word similarities; ii) unsupervised learning, with neural networks, of robust visual features, that are recoverable from partial observations that may be due to occlusions or noisy and heavily modified images. We propose a novel architecture that incorporates these neural networks, testing it on several standard Twitter datasets, and showing that the approach is efficient and obtains good classification results.

show abstract

“…For example, firstly, it may be used to enhance depth perception in photographs (Marshall, Burbeck, Ariely, Rolland, & Martin, 1996;Pentland, 1987;Watt, Akeley, Ernst, & Banks, 2005). Secondly, it has been shown to contribute to the aesthetic appreciation of photographs (Datta, Joshi, Li, & Wang, 2006), and to make images appear more natural and realistic (Joshi et al, 2011). Thirdly, DOF is believed to be closely related to visual attention-the focal point of the image can be highlighted by blurring the remainder, thus drawing viewers' attention to specific positions in the photograph (Cole et al, 2006;Steve, Caitlin, & James, 2010).…”

Section: Introductionmentioning

confidence: 99%

Human Discrimination of Depth of Field in Stereoscopic and Nonstereoscopic Photographs

2014

View full text Add to dashboard Cite

Abstract. Depth of field (DOF) is defined as the distance range within which objects are perceived as sharp. Previous research has focused on blur discrimination in artificial stimuli and natural photographs. The discrimination of DOF, however, has received less attention. Since DOF introduces blur which is related to distance in depth, many levels of blur are simultaneously present. As a consequence, it is unclear whether discrimination thresholds for blur are appropriate for predicting discrimination thresholds for DOF. We therefore measured discrimination thresholds for DOF using a two-alternative forced-choice task. Ten participants were asked to observe two images and to select the one with the larger DOF. We manipulated the scale of the scene-that is, the actual depth in the scene. We conducted the experiment under stereoscopic and nonstereoscopic viewing conditions. We found that the threshold for a large DOF (39.1 mm) was higher than for a small DOF (10.1 mm), and the thresholds decreased when scale of scene increased. We also found that there was no significant difference between stereoscopic and nonstereoscopic conditions. We compared our results with thresholds predicted from the literature. We concluded that using blur discrimination thresholds to discriminate DOF may lead to erroneous conclusions because the depth in the scene significantly affects people's DOF discrimination ability.

show abstract

Aesthetics and Emotions in Images

Cited by 360 publications

References 83 publications

Quantifying Aesthetics of Visual Design Applied to Automatic Design

Quantifying Aesthetics of Visual Design Applied to Automatic Design

A multimodal feature learning approach for sentiment analysis of social network multimedia

Human Discrimination of Depth of Field in Stereoscopic and Nonstereoscopic Photographs

Contact Info

Product

Resources

About