- Face-research-list - University of Stirling Mailing Lists

Looking for 3D famous faces
by Caspar M. Schwiedrzik 30 Oct '18

30 Oct '18

Hi! I am looking for a database of 3D models of famous faces. I found Eric Baird's database at http://www.relativitybook.com/CoolStuff/facebank.html, but was hoping for additional celebrities. If anyone has a database and is willing to share, or could point me to a database, it would be very much appreciated. Thanks! Caspar

1 0

CBAR@FG 2019 CFP: 6th International Workshop on Context Based Affect Recognition @ FG 2019
by zakia hammal 21 Oct '18

21 Oct '18

Apologies for cross-posting *********************************************************************************** CBAR 2019: CALL FOR PAPERS 6th International Workshop on CONTEXT BASED AFFECT RECOGNITION https://cbar2019.blogspot.com/ Submission Deadline: December 14th, 2018 *********************************************************************************** The 6th International Workshop on Context Based Affect Recognition (CBAR 2019) will be held in conjunction with FG 2019 in May 2019 in Lille France – http://fg2019.org/ For details concerning the workshop program, paper submission, and guidelines please visit our workshop website at: https://cbar2019.blogspot.com/ Best regards, Zakia Hammal Zakia Hammal, PhD The Robotics Institute, Carnegie Mellon University http://www.ri.cmu.edu/ http://ri.cmu.edu/personal-pages/ZakiaHammal/

1 0

CFP: TAC | Special Issue on Automated Perception of Human Affect from Longitudinal Behavioral Data
by Pablo Barros 18 Oct '18

18 Oct '18

CALL FOR PAPERS IEEE Transactions on Affective Computing Special Issue on Automated Perception of Human Affect from Longitudinal Behavioral Data Website: https://www2.informatik.uni-hamburg.de/wtm/omgchallenges/tacSpecialIssue201… I. Aim and Scope Research trends within artificial intelligence and cognitive sciences are still heavily based on computational models that attempt to imitate human perception in various behavior categorization tasks. However, most of the research in the field focuses on instantaneous categorization and interpretation of human affect, such as the inference of six basic emotions from face images, and/or affective dimensions (valence-arousal), stress and engagement from multi-modal (e.g., video, audio, and autonomic physiology) data. This diverges from the developmental aspect of emotional behavior perception and learning, where human behavior and expressions of affect evolve and change over time. Moreover, these changes are present not only in the temporal domain but also within different populations and more importantly, within each individual. This calls for a new perspective when designing computational models for analysis and interpretation of human affective behaviors: the computational models that can timely and efficiently adapt to different contexts and individuals over time, and also incorporate existing neurophysiological and psychological findings (prior knowledge). Thus, the long-term goal is to create life-long personalized learning and inference systems for analysis and perception of human affective behaviors. Such systems would benefit from long-term contextual information (including demographic and social aspects) as well as individual characteristics. This, in turn, would allow building intelligent agents (such as mobile and robot technologies) capable of adapting their behavior in a continuous and on-line manner to the target contexts and individuals. This special issue aims at contributions from computational neuroscience and psychology, artificial intelligence, machine learning, and affective computing, challenging and expanding current research on interpretation and estimation of human affective behavior from longitudinal behavioral data, i.e., single or multiple modalities captured over extended periods of time allowing efficient profiling of target behaviors and their inference in terms of affect and other socio-cognitive dimensions. We invite contributions focusing on both the theoretical and modeling perspective, as well as applications ranging from human-human, human-computer and human-robot interactions. II. Potential Topics Given computational models, the capability to perceive and understand emotion behavior is an important and popular research topic. That is why recent special issues on the IEEE Journal on Transactions on Affective Computing covered topics from emotion behavior analysis “in-the-wild” to personality analysis. However, most of the research published by these specific calls treat emotion behavior as an instantaneous event, relating mostly to emotion recognition, and thus neglect the development of complex emotion behavior models. Our special issue will foster the development of the field by focusing excellent research on emotion models for long-term behavior analysis. The topics of interest for this special issue include, but are not limited to: - New theories and findings on continuous emotion recognition - Multi- and Cross-modal emotion perception and interpretation - Lifelong affect analysis, perception, and interpretation - Novel neural network models for affective processing - New neuroscientific and psychological findings on continuous emotion representation - Embodied artificial agents for empathy and emotion appraisal - Machine learning for affect-driven interventions - Socially intelligent human-robot interaction - Personalized systems for human affect recognition III. Submission Prospective authors are invited to submit their manuscripts electronically, adhering to the IEEE Transactions on Affective Computing guidelines ( https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=5165369) Please submit your papers through the online system ( https://mc.manuscriptcentral.com/taffc-cs) and be sure to select the special issue: Special Issue/Section on Automated Perception of Human Affect from Longitudinal Behavioral Data. IV. IMPORTANT DATES: Submissions Deadline: 15th of January 2019 Deadline for reviews and response to authors: 06th of April 2019 Camera-ready deadline: 05th of August 2019 V. Guest Editors Pablo Barros, University of Hamburg, Germany Stefan Wermter, University of Hamburg, Germany Ognjen (Oggi) Rudovic, Massachusetts Institute of Technology, United States of America Hatice Gunes, University of Cambridge, United Kingdom -------------------------- -- Dr. Pablo Barros Postdoctoral Research Associate - Crossmodal Learning Project (CML) Knowledge Technology Department of Informatics University of Hamburg Vogt-Koelln-Str. 30 22527 Hamburg, Germany Phone: +49 40 42883 2535 Fax: +49 40 42883 2515 barros at informatik.uni-hamburg.dehttp://www.pablobarros.nethttps://www.inf.uni-hamburg.de/en/inst/ab/wtm/people/barros.htmlhttps://www.inf.uni-hamburg.de/en/inst/ab/wtm/

1 0

Society for Affective Science conference - Abstract portal now open!
by Rachael Jack 15 Oct '18

15 Oct '18

Dear colleagues, The Society for Affective Science is pleased to announce a Call for Abstracts for the SAS 2019 Conference at the Westin Boston Waterfront Hotel in Boston, MA, on March 21-23, 2019. Abstract Submission Formats In addition to invited sessions, we invite attendees to submit abstracts for posters and flash talk sessions. We welcome abstract submissions that describe new research within the domain of affective science. In line with our goal to facilitate interdisciplinary advances, we welcome submissions from affective scientists in any discipline (e.g., anthropology, business, computer science, cultural studies, economics, education, geography, history, integrative medicine, law, linguistics, literature, neuroscience, philosophy, political science, psychiatry, psychology, public health, sociology, theatre), working on a broad range of topics using a variety of measures. Authors at all career stages – trainees, junior faculty, and senior faculty – are encouraged to submit an abstract according to two presentation formats on any topic within the domain of affective science as follows: 1. A poster 2. A flash talk Deadline for Receipt of Abstracts Abstracts must be submitted by Friday, November 9, 2018, at 11:59 p.m. Baker Island Time (BIT; UTC-12) to be considered for inclusion in the program. Please review the abstract submission instructions carefully. Click here<https://t.e2ma.net/click/4fw8pd/824poyb/sqgu0q> to submit your abstract. All presenters must register and pay to attend the meeting. Notification of acceptance or rejection of abstracts will be emailed to the corresponding author by Friday, January 11, 2019. Selection Process All abstracts will be evaluated for scholarly merit by an interdisciplinary group of SAS Program Committee members using blind peer review. Abstracts are also selected at this time for Poster Spotlight presentations and consideration for poster and flash talk awards. Posters and flash talk award nominees will be evaluated during the conference by SAS faculty members. Reviewers do not review abstracts, posters, or flash talks on which they have a known conflict of interest. Awards will be announced at the conference during the closing ceremony. Program Highlights This year's invited program includes new and exciting interdisciplinary conversations in affective science. An opening session "Trajectories, Transitions, and Turning Points," features Phoebe Ellsworth, Valeria Gazzola, and Bob Levenson describing experiences, events, and findings that were key transitions points in their research programs and careers. The presidential symposium will be devoted to research on culture, ethnicity, and emotion. This year's program will also feature a symposium on emotion and health jointly sponsored by SAS and the American Psychosomatic Society called "The Vital Role of Affective Science in Medicine." We will also continue to showcase other exciting formats, such as TED-style talks, salons, methods and speed networking events, flash talks, poster spotlights, and interactive poster sessions. Come see other invited speakers, including Marc Brackett, Cynthia Breazeal, Alan Fiske, Richard Lane, Jenn Lerner, Tali Sharot, and invited flash-talk speakers who will present groundbreaking research representing a wide range of affective science! There are also four exciting pre-conferences that will be held March 21. Please see the conference website<https://t.e2ma.net/click/4fw8pd/824poyb/8ihu0q> for more information. You can register for SAS 2019 starting in November. We're looking forward to seeing you in Boston for what promises to be another great SAS meeting! Relevant Links Check out our new look!<https://t.e2ma.net/click/4fw8pd/824poyb/obiu0q> We are extremely excited about the new Society website! It's been redesigned from the bottom up with clarity and effectiveness foremost in our minds. We hope affective scientists everywhere will find the site easy to navigate and use. Note that our members-only section will open soon. www.facebook.com/affectScience<https://www.facebook.com/affectScience/> twitter.com/affectScience<https://twitter.com/affectScience> Dr. Rachael E. Jack, Ph.D. Reader Institute of Neuroscience & Psychology School of Psychology University of Glasgow +44 (0) 141 5087 www.psy.gla.ac.uk/schools/psychology/staff/rachaeljack/

1 0

ESRC AI Studentship University of Nottingham
by Alan Johnston 15 Oct '18

15 Oct '18

Multi-view Representations for Pose Invariant Face Recognition in Man and Machine ESRC DTP Artificial Intelligence Studentship School of Psychology and School of Computer Science, Nottingham University This is a unique opportunity for a fully-funded ESRC Doctoral Studentship for applicants from the UK, EU or Overseas with a background in psychology, neuroscience, cognitive science, computer science or a related STEM discipline. The successful candidate will be located within the School of Psychology. The start date of this studentship may be 1st February 2019 or 1st October 2019 and will depend on the required award length (see ‘Award Lengths’ section below). Pose-Invariant Face Recognition (PIFR) remains a significant stumbling block to realizing the full potential of face recognition as a passive biometric technology. This fundamental human ability poses a significant challenge for computer vision systems due to the immense within-class appearance variations caused by pose change, e.g., self-occlusion and coupled illumination or expression variations. Despite extensive efforts to solve the problem of pose-invariant face recognition it remains a significant barrier to developments in Artificial Intelligence. PIFR is achieved effortlessly by the human visual system but at present we do not understand the human system well enough to provide plausible solutions to the clear technological challenges. The aim of the studentship will be to enhance our understanding of how human observers achieve pose invariant recognition of faces in order to inform AI strategies. We will particularly focus on multi- view or pose-aware strategies and compare these against object-based models or pose-agnostic approaches. The work will involve both extensive psychophysical experimentation with human participants and computational experiments exploring computer models of pose-invariant dynamic face recognition. The project will be jointly supervised by Prof Alan Johnston (Psychology) and Dr Michel Valstar (Computer Science). Award Lengths The length of award offered will depend on the extent to which the candidate has met the ESRC’s core research methods training requirements. These are: *  Quantitative methods, *  Qualitative methods, *  Philosophy of Research and *  Research Design. The extent to which you have met this criteria will be assessed during the application process. For those who have met all of the training, a +3 year award will be made, for those who have met some of the training, a 3.5 year award will be made, with a requirement that core training is completed within the first 12 months. If no core methods research has been undertaken by the candidate, then a +4 award will be made, which will include 180 credits research methods training before progressing to the PhD. Owing to these requirements, +3 awards could start in February, but +4 awards would need to start at the beginning of the next academic year. +3.5 awards would depend on the type of training required and we will be able to advise candidates further prior to application if required. You can read more about award lengths here: www.nottingham.ac.uk/esrc-dtc/mgs/dtp-training-<http://www.nottingham.ac.uk/esrc-dtc/mgs/dtp-training-> at-nottingham.aspx Application Process To be considered for this PhD, please complete the ESRC AI Studentship application form available online here with a covering letter and a CV as well as two references and then email this to christopher.atkinson(a)nottingham.ac.uk<mailto:christopher.atkinson@nottingham.ac.uk>. Application deadline: Friday 9th November 2018 Midlands Graduate School ESRC DTP The Midlands Graduate School is an accredited Economic and Social Research Council (ESRC) Doctoral Training Partnership (DTP). One of 14 such partnerships in the UK, the Midlands Graduate School is a collaboration between the University of Warwick, Aston University, University of Birmingham, University of Leicester, Loughborough University and the University of Nottingham. Our ESRC studentships cover fees and maintenance stipend and extensive support for research training, as well as research activity support grants. For this priority area candidates ordinarily resident in an EU member state will be eligible for a full award as will candidates from overseas. Informal enquiries about the research prior to application can be directed to: alan.johnston(a)nottingham.ac.uk<mailto:alan.johnston@nottingham.ac.uk>. This message and any attachment are intended solely for the addressee and may contain confidential information. If you have received this message in error, please contact the sender and delete the email and attachment. Any views or opinions expressed by the author of this email do not necessarily reflect the views of the University of Nottingham. Email communications with the University of Nottingham may be monitored where permitted by law.

1 0

PhD position in Neuroscience of Auditory (Speech) Perception, TU Dresden, Germany
by Katharina von Kriegstein 10 Oct '18

10 Oct '18

We are seeking an enthusiastic PhD student with a particular interest in neuroscience of auditory (speech) perception. The PhD position is part of the Chair of Cognitive and Clinical Neuroscience led by Prof. Dr. Katharina von Kriegstein at the TU Dresden, Germany. The position is funded by the ERC-project SENSOCOM (http://cordis.europa.eu/project/rcn/199655_en.html) The aim of the SENSOCOM project is to investigate the role of auditory and visual subcortical sensory structures in analysing human communication signals and to specify how their dysfunction contributes to human communication disorders such as developmental dyslexia. For examples of our work on these topics see von Kriegstein et al., 2008 Current Biology, Diaz et al., 2012 PNAS, Müller-Axt et al., 2017 Current Biology. TU Dresden is one of eleven German Universities of Excellence and offers an interdisciplinary scientific environment. The Neuroimaging Centre at the TU Dresden (http://www.nic-tud.de) has cutting-edge infrastructure with 3-Tesla MRI, MRI compatible headphones and eye-tracking, several EEG systems, a neurostimulation unit including neuronavigation, TMS and tDCS devices. The PhD position is available at the next possible date. Subject to personal qualification, employees are remunerated according to salary group E 13 TV-L 50%. There will be the opportunity to participate in the TU Dresden graduate academy (https://tu-dresden.de/ga?set_language=en) For more information on the post please see the official advertisement: https://tinyurl.com/ybwe47bc For more information on our research group see: https://tu-dresden.de/mn/psychologie/kknw --- Katharina von Kriegstein Professor of Cognitive and Clinical Neuroscience Technische Universität Dresden Bamberger Str. 7, 01187 Dresden, Germany Phone +49 (0) 351-463-43145 https://tu-dresden.de/mn/psychologie/kknw https://twitter.com/kvonkriegstein

1 0

Call for abstracts deadline extended to 8th Oct 2018: special session on human health monitoring based on computer vision, IEEE International Conference on Automatic Face and Gesture Recognition (FG’19), Lille, France, May 14-18, 2019.
by Abhijit Das 27 Sep '18

27 Sep '18

Dear colleagues, We are inviting abstract submissions for a special session on “Human Health Monitoring Based on Computer Vision”, as part of the 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG’19, http://fg2019.org/) Lille, France, May 14-18, 2019. Details on the special session follow below. Title, abstract, list of authors, as well as the name of the corresponding author, should be emailed directly to Abhijit Das (abhijitdas2048(a)gmail.com) We hope to receive abstracts before October 8th 2018. Full paper submission December 9th 2018. Feel free to contact Abhijit Das if you have any further questions. Kindly circulate this email to others who might be interested. We look forward to your contributions! François Brémond (INRIA, France) Antitza Dantcheva (INRIA, France) Abhijit Das (INRIA, France) Xilin Chen (CAS, China) Hu Han (CAS, China) -------------------------------------------------------------------------------------------- *Call for abstract for FG 2018 special session * *on* *Human Health Monitoring Based on Computer Vision* --------------------------------------------------------------- Human Health Monitoring Based on Computer Vision has gained rapid scientific growth in the last years, with many research articles and complete systems based on a set of features, extracted from face and gesture. Researchers from the computer, as well as from medical science have granted significant attention, with goals ranging from patient analysis and monitoring to diagnostics. (e.g., for dementia, depression, healthcare, physiological measurement [5, 6]). Despite the progress, there are various open, unexplored, and unidentified challenges. Such as the robustness of these techniques in the real-world scenario, collecting large dataset for research, heterogeneity of the acquiring environment and the artefacts. Moreover, healthcare represents an area of broad economic (e.g., https://www.prnewswire.com/news-releases/healthcare-automation-market-to-re…) social, and scientific impact. Therefore, it is imperative to foster efforts coming from computer vision, machine learning, and the medical domain, as well as multidisciplinary efforts. Towards this, we propose a special session, with a focus on multidisciplinary efforts. We aim to document recent advancements in automated healthcare, as well as enable and discuss progress.. Therefore, the goal of this special session is to bring together researchers and practitioners working in this area of computer vision and medical science, and to address a wide range of theoretical and practical issues related to real-life healthcare systems. Topics of interest include, but are not limited to: · Health monitoring based on face analysis, · Health monitoring based on gesture analysis, · Health monitoring based corporeal-based visual features, · Depression analysis based on visual features, · Face analytics for human behaviour understanding, · Anxiety diagnosis based on face and gesture · Physiological measurement employing face analytics, · Databases on health monitoring, e.g., depression analysis, · Augmentative and alternative communication, · Human-robot interaction, · Home healthcare, · Technology for cognition, · Automatic emotional hearing and understanding, · Visual attention and visual saliency, · Assistive living, · Privacy preserving systems, · Quality of life technologies, · Mobile and wearable systems, · Applications for the visually impaired, · Sign language recognition and applications for hearing impaired, · Applications for the ageing society, · Personalized monitoring, · Egocentric and first-person vision, · Applications to improve the health and wellbeing of children and the elderly, etc. In addition, we plan to organise a special issue in a journal with the extended version of accepted special session papers.

1 0

CFP: The OMG-Empathy Prediction Challenge
by Pablo Barros 26 Sep '18

26 Sep '18

CALL FOR PARTICIPATION The One-Minute Gradual-Empathy Prediction (OMG-Empathy) Competition held in partnership with the IEEE International Conference on Automatic Face and Gesture Recognition 2019 in Lille, France. https://www2.informatik.uni-hamburg.de/wtm/omgchallenges/omg_empathy.html I. Aim and Scope The ability to perceive, understand and respond to social interactions in a human-like manner is one of the most desired capabilities in artificial agents, particularly social robots. These skills are highly complex and require a focus on several different aspects of research, including affective understanding. An agent which is able to recognize, understand and, most importantly, adapt to different human affective behaviors can increase its own social capabilities by being able to interact and communicate in a natural way. Emotional expression perception and categorization are extremely popular in the affective computing community. However, the inclusion of emotions in the decision-making process of an agent is not considered in most of the research in this field. To treat emotion expressions as the final goal, although necessary, reduces the usability of such solutions in more complex scenarios. To create a general affective model to be used as a modulator for learning different cognitive tasks, such as modeling intrinsic motivation, creativity, dialog processing, grounded learning, and human-level communication, only emotion perception cannot be the pivotal focus. The integration of perception with intrinsic concepts of emotional understanding, such as a dynamic and evolving mood and affective memory, is required to model the necessary complexity of an interaction and realize adaptability in an agent's social behavior. Such models are most necessary for the development of real-world social systems, which would communicate and interact with humans in a natural way on a day-to-day basis. This could become the next goal for research on Human-Robot Interaction (HRI) and could be an essential part of the next generation of social robots. For this challenge, we designed, collected and annotated a novel corpus based on human-human interaction. This novel corpus builds on top of the experience we gathered while organizing the OMG-Emotion Recognition Challenge, making use of state-of-the-art frameworks for data collection and annotation. The One-Minute Gradual Empathy datasets (OMG-Empathy) contain multi-modal recordings of different individuals discussing predefined topics. One of them, the actor, shares a story about themselves while the other, the listener, reacts to it emotionally. We annotated each interaction based on the listener's own assessment of how they felt while the interaction was taking place. We encourage the participants to propose state-of-the-art solutions not only based on deep, recurrent and self-organizing neural networks but also traditional methods for feature representation and data processing. We also enforce that the use of contextual information, as well as personalized solutions for empathy assessment, will be extremely important for the development of competitive solutions. II. Competition Tracks We let available for the challenge a pre-defined set of training, validation and testing samples. We separate our samples based on each story: 4 stories for training, 1 for validation and 3 for testing. Each story sample is composed of 10 videos with interactions, one for each listener. Although using the same training, validation and testing data split, we propose two tracks which will measure different aspects of the self-assessed empathy: The Personalized Empathy track, where each team must predict the empathy of a specific person. We will evaluate the ability of proposed models to learn the empathic behavior of each of the subjects over a newly perceived story. We encourage the teams to develop models which take into consideration the individual behavior of each subject in the training data. The Generalized Empathy track, where the teams must predict the general behavior of all the participants over each story. We will measure the performance of the proposed models to learn a general empathic measure for each of the stories individually. We encourage the proposed models to take into consideration the aggregated behavior of all the participants for each story and to generalize this behavior in a newly perceived story. The training and validation samples will be given to the participants at the beginning of the challenge together with all the associated labels. The test set will be given to the participants without the associated labels. The team`s predictions on the test set will be used to calculate the final metrics of the challenge. III. How to Participate To participate to the challenge, please send us an email to barros @ informatik.uni-hamburg.de with the title "OMG-Empathy Team Registration". This e-mail must contain the following information: Team Name Team Members Affiliation Participating tracks We split the corpus into three subsets: training, validation and testing. The participants will receive the training and validation sets, together with the associated annotations once they subscribe to the challenge. The subscription will be done via e-mail. Each participant team must consist of 1 to 5 participants and must agree to use the data only for scientific purposes. Each team can choose to take part in one or both the tracks. After the training period is over, the testing set will be released without the associated annotations. Each team must submit, via e-mail, their final predictions as a .csv file for each video on the test set. Together with the final submission, each team must send a short 2-4 pages paper describing their solution published on Arxiv and the link for a github page to their solution. If a team fails to submit any of these items, their submission will be invalidated. Each team can submit 3 complete submissions for each track. IV. Important Dates 25th of September 2018 - Opening of the Challenge - Team registrations begin 1st of October 2018 - Training/validation data and annotation available 1st of December 2018 - Test data release 3rd of December 2018 - Final submission (Results and code) 5th of December 2018 - Final submission (Paper) 7th of December 2018 - Announcement of the winners V. Organization Pablo Barros, University of Hamburg, Germany Nikhil Churamani, University of Cambridge, United Kingdom Angelica Lim, Simon Fraser University, Canada Stefan Wermter, Hamburg University, Germany -- Dr.rer.nat. Pablo Barros Postdoctoral Research Associate - Crossmodal Learning Project (CML) Knowledge Technology Department of Informatics University of Hamburg Vogt-Koelln-Str. 30 22527 Hamburg, Germany Phone: +49 40 42883 2535 Fax: +49 40 42883 2515 barros at informatik.uni-hamburg.de https://www.inf.uni-hamburg.de/en/inst/ab/wtm/people/barros.html https://www.inf.uni-hamburg.de/en/inst/ab/wtm/

1 0

Call for abstracts: special session on human health monitoring based on computer vision, IEEE International Conference on Automatic Face and Gesture Recognition (FG’19), Lille, France, May 14-18, 2019.
by ABHIJIT DAS 21 Sep '18

21 Sep '18

Dear colleagues, We are inviting abstract submissions for a special session on “Human Health Monitoring Based on Computer Vision”, as part of the 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG’19, http://fg2019.org/) Lille, France, May 14-18, 2019. Details on the special session follow below. Title, abstract, list of authors, as well as the name of the corresponding author, should be emailed directly to Abhijit Das (abhijitdas2048(a)gmail.com) We hope to receive abstracts before Thursday, September 27th. Feel free to contact Abhijit Das if you have any further questions. Kindly circulate this email to others who might be interested. We look forward to your contributions! François Brémond (INRIA, France) Antitza Dantcheva (INRIA, France) Abhijit Das (INRIA, France) Xilin Chen (CAS, China) Hu Han (CAS, China) -------------------------------------------------------------------------------------------- *Call for abstract for FG 2018 special session * *on* *Human Health Monitoring Based on Computer Vision* --------------------------------------------------------------- Human Health Monitoring Based on Computer Vision has gained rapid scientific growth in the last years, with many research articles and complete systems based on a set of features, extracted from face and gesture. Researchers from the computer, as well as from medical science have granted significant attention, with goals ranging from patient analysis and monitoring to diagnostics. (e.g., for dementia, depression, healthcare, physiological measurement [5, 6]). Despite the progress, there are various open, unexplored, and unidentified challenges. Such as the robustness of these techniques in the real-world scenario, collecting large dataset for research, heterogeneity of the acquiring environment and the artefacts. Moreover, healthcare represents an area of broad economic (e.g., https://www.prnewswire.com/news-releases/healthcare-automation-market-to-re…) social, and scientific impact. Therefore, it is imperative to foster efforts coming from computer vision, machine learning, and the medical domain, as well as multidisciplinary efforts. Towards this, we propose a special session, with a focus on multidisciplinary efforts. We aim to document recent advancements in automated healthcare, as well as enable and discuss progress.. Therefore, the goal of this special session is to bring together researchers and practitioners working in this area of computer vision and medical science, and to address a wide range of theoretical and practical issues related to real-life healthcare systems. Topics of interest include, but are not limited to: · Health monitoring based on face analysis, · Health monitoring based on gesture analysis, · Health monitoring based corporeal-based visual features, · Depression analysis based on visual features, · Face analytics for human behaviour understanding, · Anxiety diagnosis based on face and gesture · Physiological measurement employing face analytics, · Databases on health monitoring, e.g., depression analysis, · Augmentative and alternative communication, · Human-robot interaction, · Home healthcare, · Technology for cognition, · Automatic emotional hearing and understanding, · Visual attention and visual saliency, · Assistive living, · Privacy preserving systems, · Quality of life technologies, · Mobile and wearable systems, · Applications for the visually impaired, · Sign language recognition and applications for hearing impaired, · Applications for the ageing society, · Personalized monitoring, · Egocentric and first-person vision, · Applications to improve the health and wellbeing of children and the elderly, etc. In addition, we plan to organise a special issue in a journal with the extended version of accepted special session papers.

1 0

Resources for Gestures and Emotion Recognition
by Pablo Barros 10 Aug '18

10 Aug '18

Dear all, We are very happy to announce the release of resource material related to our research on affective computing and gestures recognition. This resource contains research on hand gesture and emotion processing (auditory, visual and crossmodal) recognition and processing, organized as three datasets (NCD, GRIT, and OMG-Emotion), source code for proposed neural network solutions, pre-trained models, and ready-to-run demos. The NAO Camera hand posture Database (NCD) was designed and recorded using the camera of a NAO robot and contains four different hand postures. A total of 2000 images were recorded. In each image, the hand was is present in different positions, not always in the centralized, and sometimes with occlusion of some fingers. The Gesture Commands for Robot InTeraction (GRIT) dataset contains recordings of six different subjects performing eight command gestures for Human-Robot Interaction (HRI): Abort, Circle, Hello, No, Stop, Turn Right, Turn Left, and Warn. We recorded a total of 543 sequences with a varying number of frames in each one. The One-Minute Gradual Emotion Corpus (OMG-Emotion) is composed of Youtube videos which are about a minute in length and are annotated taking into consideration a continuous emotional behavior. The videos were selected using a crawler technique that uses specific keywords based on long-term emotional behaviors such as "monologues", "auditions", "dialogues" and "emotional scenes". After the videos were selected, we created an algorithm to identify weather the video had at least two different modalities which contribute for the emotional categorization: facial expressions, language context, and a reasonably noiseless environment. We selected a total of 420 videos, totaling around 10 hours of data. Together with the datasets, we provide the source code for different proposed neural models. These models are based on novel deep and self-organizing neural networks which deploy different mechanisms inspired by neuropsychological concepts. All of our models are formally described in different high-impact peer-reviewed publications. We also provide a ready-to-run demo for visual emotion recognition based on our proposed models. These resources are accessible through our GitHub link: https://github.com/knowledgetechnologyuhh/EmotionRecognitionBarros . We hope that with these resources we can contribute to the areas of affective computing and gesture recognition and foster the development of innovative solutions. -- Dr.rer.nat. Pablo Barros Postdoctoral Research Associate - Crossmodal Learning Project (CML) Knowledge Technology Department of Informatics University of Hamburg Vogt-Koelln-Str. 30 22527 Hamburg, Germany Phone: +49 40 42883 2535 Fax: +49 40 42883 2515 barros at informatik.uni-hamburg.de https://www.inf.uni-hamburg.de/en/inst/ab/wtm/people/barros.html https://www.inf.uni-hamburg.de/en/inst/ab/wtm/

1 0