scholarly journals “Excavating AI” Re-excavated: Debunking a Fallacious Account of the JAFFE Dataset

2021 ◽  
Author(s):  
Michael J Lyons
Keyword(s):  
Machine Learning ◽  
Facial Expression ◽  
Human Computer Interaction ◽  
Present Article ◽  
Face Perception ◽  
Affective Computing ◽  
The Creation ◽  
Computer Interaction ◽  
Training Sets

Twenty-five years ago, my colleagues Miyuki Kamachi and Jiro Gyoba and I designed and photographed JAFFE, a set of facial expression images intended for use in a study of face perception. In 2019, without seeking permission or informing us, Kate Crawford and Trevor Paglen exhibited JAFFE in two widely publicized art shows. In addition, they published a nonfactual account of the images in the essay “Excavating AI: The Politics of Images in Machine Learning Training Sets.” The present article recounts the creation of the JAFFE dataset and unravels each of Crawford and Paglen’s fallacious statements. I also discuss JAFFE more broadly in connection with research on facial expression, affective computing, and human-computer interaction.

scholarly journals Feature extraction and classification methods of facial expression: a survey

2021 ◽  
Vol 2 (1) ◽  
pp. 26-32
Author(s):  
Moe Moe Htay
Keyword(s):  
Feature Extraction ◽  
Facial Expression ◽  
Human Computer Interaction ◽  
Affective Computing ◽  
Recognition System ◽  
Expression Recognition ◽  
Care Assessment ◽  
Main Components ◽  
Fatigue Detection ◽  
Computer Interaction

Facial Expression is a significant role in affective computing and one of the non-verbal communication for human computer interaction. Automatic recognition of human affects has become more challenging and interesting problem in recent years. Facial Expression is the significant features to recognize the human emotion in human daily life. Facial Expression Recognition System (FERS) can be developed for the application of human affect analysis, health care assessment, distance learning, driver fatigue detection and human computer interaction. Basically, there are three main components to recognize the human facial expression. They are face or face’s components detection, feature extraction of face image, classification of expression. The study proposed the methods of feature extraction and classification for FER.

Multimodel Expressions

2006 ◽  
pp. 110-131
Author(s):  
Lesley Axelrod ◽  
Kate Hone
Keyword(s):  
Human Computer Interaction ◽  
Affective Computing ◽  
Emotional Design ◽  
Ethical Considerations ◽  
Emotional Recognition ◽  
Innovative Technologies ◽  
User Centred Design ◽  
Recognition Algorithms ◽  
Multimedia Technologies ◽  
Computer Interaction

In a culture which places increasing emphasis on happiness and wellbeing, multimedia technologies include emotional design to improve commercial edge. This chapter explores affective computing and illustrates how innovative technologies are capable of emotional recognition and display. Research in this domain has emphasised solving the technical difficulties involved, through the design of ever more complex recognition algorithms. But fundamental questions about the use of such technology remain neglected. Can it really improve human-computer interaction? For which types of application is it suitable? How is it best implemented? What ethical considerations are there? We review this field and discuss the need for user-centred design. We describe and give evidence from a study that explores some of the user issues in affective computing.

scholarly journals The uulmMAC Database—A Multimodal Affective Corpus for Affective Computing in Human-Computer Interaction

Sensors ◽  
2020 ◽  
Vol 20 (8) ◽  
pp. 2308 ◽  
Author(s):  
Dilana Hazer-Rau ◽  
Sascha Meudt ◽  
Andreas Daucher ◽  
Jennifer Spohrs ◽  
Holger Hoffmann ◽  
...  
Keyword(s):  
Human Computer Interaction ◽  
Affective Computing ◽  
Signal Quality ◽  
Multimodal Data ◽  
Machine Learning Applications ◽  
The Stability ◽  
The University ◽  
Physiological Reactions ◽  
Multimodal Data Analysis ◽  
Computer Interaction

In this paper, we present a multimodal dataset for affective computing research acquired in a human-computer interaction (HCI) setting. An experimental mobile and interactive scenario was designed and implemented based on a gamified generic paradigm for the induction of dialog-based HCI relevant emotional and cognitive load states. It consists of six experimental sequences, inducing Interest, Overload, Normal, Easy, Underload, and Frustration. Each sequence is followed by subjective feedbacks to validate the induction, a respiration baseline to level off the physiological reactions, and a summary of results. Further, prior to the experiment, three questionnaires related to emotion regulation (ERQ), emotional control (TEIQue-SF), and personality traits (TIPI) were collected from each subject to evaluate the stability of the induction paradigm. Based on this HCI scenario, the University of Ulm Multimodal Affective Corpus (uulmMAC), consisting of two homogenous samples of 60 participants and 100 recording sessions was generated. We recorded 16 sensor modalities including 4 × video, 3 × audio, and 7 × biophysiological, depth, and pose streams. Further, additional labels and annotations were also collected. After recording, all data were post-processed and checked for technical and signal quality, resulting in the final uulmMAC dataset of 57 subjects and 95 recording sessions. The evaluation of the reported subjective feedbacks shows significant differences between the sequences, well consistent with the induced states, and the analysis of the questionnaires shows stable results. In summary, our uulmMAC database is a valuable contribution for the field of affective computing and multimodal data analysis: Acquired in a mobile interactive scenario close to real HCI, it consists of a large number of subjects and allows transtemporal investigations. Validated via subjective feedbacks and checked for quality issues, it can be used for affective computing and machine learning applications.

scholarly journals Psychological Aspects in lifelike synthetic agents: Towards to the Personality Markup Language (A Brief Survey)

RENOTE ◽  
2009 ◽  
Vol 7 (3) ◽  
pp. 390-400
Author(s):  
Maria Augusta Silveira Netto Nunes
Keyword(s):  
Human Computer Interaction ◽  
Affective Computing ◽  
Psychological Aspects ◽  
Markup Language ◽  
Starting Point ◽  
Synthetic Agents ◽  
Computer Interaction

This paper describes how human psychological aspects have been used in lifelike synthetic agents in order to provide believability during the human-computer interaction. We describe a brief survey of applications where Affective Computing Scientists have applied psychological aspects, like Emotion and Personality. Based on those aspects we describe the effort done by Affective Computing scientists in order to create a Markup Language to express and standardize Emotions. Because they have not yet concentrated their effort on Personality, here, we propose a starting point to create a Markup Language to express Personality.

scholarly journals User-driven sampling strategies in image exploitation

2014 ◽  
Vol 15 (1) ◽  
pp. 64-74 ◽  
Author(s):  
Neal Harvey ◽  
Reid Porter
Keyword(s):  
Machine Learning ◽  
Human Computer Interaction ◽  
Visual Analytics ◽  
Complex Data ◽  
Sampling Strategies ◽  
Interactive Machine Learning ◽  
Significant Performance ◽  
Analysis Application ◽  
Performance Gains ◽  
Computer Interaction

Both visual analytics and interactive machine learning try to leverage the complementary strengths of humans and machines to solve complex data exploitation tasks. These fields overlap most significantly when training is involved: the visualization or machine learning tool improves over time by exploiting observations of the human–computer interaction. This article focuses on one aspect of the human–computer interaction that we call user-driven sampling strategies. Unlike relevance feedback and active learning sampling strategies, where the computer selects which data to label at each iteration, we investigate situations where the user selects which data are to be labeled at each iteration. User-driven sampling strategies can emerge in many visual analytics applications, but they have not been fully developed in machine learning. User-driven sampling strategies suggest new theoretical and practical research questions for both visualization science and machine learning. In this article, we identify and quantify the potential benefits of these strategies in a practical image analysis application. We find user-driven sampling strategies can sometimes provide significant performance gains by steering tools toward local minima that have lower error than tools trained with all of the data. In preliminary experiments, we find these performance gains are particularly pronounced when the user is experienced with the tool and application domain.

Sign in / Sign up

Export Citation Format

Share Document