Visual Persuasion: Inferring Communicative Intents of Images

By Jungseock Joo, Weixin Li, Francis F. Steen, Song-Chun Zhu. 2014

140 citations recorded by the source corpus.

Subfields: Experimental and Cognitive Psychology, Literature and Literary Theory, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Experimental and Cognitive Psychology

In Literature and Literary Theory

In Sociology and Political Science

Citations in the corpus

Recognizing Image Style (2013, background): “For example, there has increasing recent effort in understanding image meaning, aesthetics, interestingness, popularity, and emotion (for example, [10, 12, 14, 16]), and style is an important part of meaning.”
Protest Activity Detection and Perceived Violence Estimation from Social Media Images (2017, background): “Research in media studies and political science has suggested that the visual dimension of human communication can play a significant “persuasive” role in shaping public opinions [21, 43].”
Automated Facial Trait Judgment and Election Outcome Prediction: Social Dimensions of Face (2015, background): “[17] proposed to recognize the hidden communicative intents of social images in the news media and link the sentiments to the public opinion.”
Learning Social Relation Traits from Face Images (2015, background): “Other related problems also include image communicative intents prediction [16] and social role inference [22], usually applied on news and talks shows [31], or meetings to infer dominance [15].”
Understanding the Political Ideology of Legislators from Social Media Images (2019, background): “ addition, recent studies adopt advanced computer vision methods in order to analyze large scale visual content data in political media, to overcome difﬁculty and cost in manual coding-based studies. Joo et al. (2014) trains an automated visual classiﬁer which can identify communicative intent of po”
From Facial Expression Recognition to Interpersonal Relation Prediction (2016, background): “Other related problems also include image communicative intents prediction (Joo et al. 2014) and social role inference (Lan et al.”
Crowdsourcing in Computer Vision (2016, unknown): “While many active selection methods are concerned with binary labeling tasks, Joshi et al. [2010] enable annotators to provide multi-class labels in a way that is efficient both in terms of user time (by breaking down the multi-class questions into questions with binary answers) and system selection”
Photographic home styles in Congress: a computer vision approach (2016, background): “In a recent study by (Joo et al. 2014), for example, the authors find that certain facial expressions and actions convey both positive and negative politically relevant information on a number of dimensions.”
Equal But Not The Same: Understanding the Implicit Relationship Between Persuasive Images and Text (2018, methodology): “SHKA: EQUAL BUT NOT THE SAME Visual rhetoric and advertisements. There has not been extensive work in visual rhetoric, which is especially common in advertisements. In a ﬁrst work on visual rhetoric, [17] devised a method to predict which of two photos of a politician portrays that person in a more ”
Understanding Hand-Object Manipulation with Grasp Types and Object Attributes (2016, background): “In [16] a hierarchical model is built to identify persuasive intent of images based on syntactical attributes, such as “smiling” and “waving hand”.”
Predicting Motivations of Actions by Leveraging Text (2014, background): “ion 4 offers concluding remarks. 1.1 Related Work Motivation in Vision: Perhaps the most related to our paper is work that predicts the persuasive motivation of the photographer who captured an image [14]. However, our paper is different because we seek to infer the motivation of the person inside t”
Exploring Visual Engagement Signals for Representation Learning (2021, background): “This area includes (1) detecting cyberbullying and hate speech [29, 71, 20, 40], (2) identifying emotions [43, 1, 59, 62, 81], (3) understanding rhetoric and intentions [36, 37, 70, 30, 31, 88, 74, 45, 34].”
Persuasive Faces: Generating Faces in Advertisements (2018, background): “[13] learned to predict whether a photograph portrays a politician in a positive or negative light, and [14] trained classiﬁers to predict the outcomes of elections based on the candidates’ faces, but neither of these works creates a generative model.”
Automatic Understanding of Image and Video Advertisements (2017, background): “Most related to our work is the visual persuasion work of [29] which analyzes whether images of politicians portray them in a positive or negative light.”
Integrating Text and Image: Determining Multimodal Document Intent in Instagram Posts (2019, background): “Joo et al. (2014) and Huang and Kovashka (2016) study prediction of intent behind politician por-traits in the news.”