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

The OMG-Emotion Recognition Challenge
by Pablo Barros 14 Mar '18

14 Mar '18

CALL FOR PARTICIPATION The One-Minute Gradual-Emotion Recognition (OMG-Emotion) held in partnership with the WCCI/IJCNN 2018 in Rio de Janeiro, Brazil. https://www2.informatik.uni-hamburg.de/wtm/OMG-EmotionChallenge/ I. Aim and Scope Our One-Minute-Gradual Emotion Dataset (OMG-Emotion Dataset) is composed of 420 relatively long emotion videos with an average length of 1 minute, collected from a variety of Youtube channels. The videos were selected automatically based on specific search terms related to the term ``monologue''. Using monologue videos allowed for different emotional behaviors to be presented in one context and that changes gradually over time. Videos were separated into clips based on utterances, and each utterance was annotated by at least five independent subjects using the Amazon Mechanical Turk tool. To maintain the contextual information for each video, each annotator watched the clips of a video in sequence and had to annotate each video using an arousal/valence scale and a categorical emotion based on the universal emotions from Ekman. The participants are encouraged to use crossmodal information in their models, as the videos were labeled by humans without distinction of any modality. II. How to Participate To participate, please send us an email to barros(a)informatik.uni-hamburg.de with the title "OMG-Emotion Recognition Team Registration". This e-mail must contain the following information: Team Name Team Members Affiliation Each team can have a maximum of 5 participants. You will receive from us the access to the dataset and all the important information about how to train and evaluate your models. For the final submission, each team will have to send us a .csv file containing the final arousal/valence values for each of the utterances on the test dataset. We also request a link to a GitHub repository where your solution must be stored, and a link to an ArXiv paper with 4-6 pages describing your model and results. The best papers will be invited to submit their detailed research to a journal yet to be specified. Also, the best participating teams will hold an oral presentation about their solution during the WCCI/IJCNN 2018 conference. III. Important Dates Publishing of training and validation data with annotations: March 14, 2018. Publishing of the test data, and an opening of the online submission: April 11, 2018. Closing of the submission portal: April 13, 2018. Announcement of the winner through the submission portal: April 18, 2018. IV. Organization Pablo Barros, University of Hamburg, Germany Egor Lakomkin, University of Hamburg, Germany Henrique Siqueira, Hamburg University, Germany Alexander Sutherland, Hamburg University, Germany Stefan Wermter, Hamburg University, Germany --------------------------

1 0

Stirling/ESRC face database update
by Peter Hancock 09 Mar '18

09 Mar '18

Database update: Our face database at http://pics.stir.ac.uk/ESRC/index.htm has been updated. There are now 64 male and 71 female identities in most of the image types. I'm still updating a few, such as the stereo images and the conformed 3D models. The unedited 3D models are mostly of higher quality than previously. While there are still relatively few identities, the variety of imagery provided for each person is still the widest that I know of. Peter Peter Hancock Professor, Deputy Head of Psychology, Faculty of Natural Sciences University of Stirling FK9 4LA, UK phone 01786 467675 fax 01786 467641 http://stir.ac.uk/190 http://orcid.org/0000-0001-6025-7068 http://www.researcherid.com/rid/A-4633-2009 Psychology at Stirling: 100% 4* Impact, REF2014 Come and study Face Perception at the University of Stirling! Our unique MSc in the Psychology of Faces is open for applications. For more information see http://www.stir.ac.uk/postgraduate/programme-information/prospectus/psychol… [highly cited 2016]

1 0

Database of faces across lifespan
by Marlene Behrmann 03 Mar '18

03 Mar '18

I am wondering whether anyone knows (or has) a database of faces with the same individual's face shown at multiple times across the lifespan - even just childhood and adulthood (and if there is a third point, this would be even better). Many thanks, Marlene Behrmann -- Marlene Behrmann, Ph.D George A. and Helen Dunham Cowan Professor of Cognitive Neuroscience Center for the Neural Basis of Cognition and Department of Psychology Carnegie Mellon University, Pittsburgh, USA (412) 268-2790 behrmann(a)cmu.edu

2 1

Re: [Face-research-list] Database of faces across lifespan (Marlene Behrmann)
by %Edwin Burns (Dr) 02 Mar '18

02 Mar '18

If you wanted unfamiliar faces for use with an American audience, then there are many soccer players who have childhood and adult images available online. Edwin. ________________________________________ From: Face-research-list [face-research-list-bounces(a)lists.stir.ac.uk] on behalf of face-research-list-request(a)lists.stir.ac.uk [face-research-list-request(a)lists.stir.ac.uk] Sent: Friday, 2 March, 2018 8:00:01 PM To: face-research-list(a)lists.stir.ac.uk Subject: Face-research-list Digest, Vol 84, Issue 2 Send Face-research-list mailing list submissions to face-research-list(a)lists.stir.ac.uk To subscribe or unsubscribe via the World Wide Web, visit http://lists.stir.ac.uk/cgi-bin/mailman/listinfo/face-research-list or, via email, send a message with subject or body 'help' to face-research-list-request(a)lists.stir.ac.uk You can reach the person managing the list at face-research-list-owner(a)lists.stir.ac.uk When replying, please edit your Subject line so it is more specific than "Re: Contents of Face-research-list digest..." Today's Topics: 1. Re: Database of faces across lifespan (Marlene Behrmann) (Jodie Davies-Thompson) ---------------------------------------------------------------------- Message: 1 Date: Thu, 1 Mar 2018 12:29:18 +0000 From: Jodie Davies-Thompson <davies.jodie(a)gmail.com> To: face-research-list(a)lists.stir.ac.uk Subject: Re: [Face-research-list] Database of faces across lifespan (Marlene Behrmann) Message-ID: <9866AE96-15ED-4BD2-8CFC-A73C6BD098FA(a)gmail.com> Content-Type: text/plain; charset=windows-1252 Dear Marlene, I don’t know of any databases per se, but I recently wondered the same thing and started pulling various links together. Below are a few instances I’m aware of when individuals or groups have taken photos every year (not ideal, but depending on what you’re after, could suffice). There is also a BBC documentary by Robert Winston (‘Child of Our Time') which follows 25 children born in 2000 - you could probably get some good images from there. If you ever pull together a database though, that would be a brilliant resource! - http://diply.com/same-family-photo-taken-22-years?publisher=trendyjoe - https://petapixel.com/2015/08/03/father-and-son-take-the-same-picture-every… - http://www.news.com.au/lifestyle/real-life/true-stories/five-friends-recrea… - https://www.nytimes.com/interactive/2014/10/03/magazine/01-brown-sisters-fo… Sorry to not be able to supply anything better! All the best, Jodie ------------------------------ Subject: Digest Footer _______________________________________________ Face-research-list mailing list Face-research-list(a)lists.stir.ac.uk http://lists.stir.ac.uk/cgi-bin/mailman/listinfo/face-research-list ------------------------------ End of Face-research-list Digest, Vol 84, Issue 2 ************************************************* ________________________________ **Disclaimer** The sender of this email does not represent Nanyang Technological University and this email does not express the views or opinions of the University.

1 0

Re: [Face-research-list] Database of faces across lifespan (Marlene Behrmann)
by Jodie Davies-Thompson 01 Mar '18

01 Mar '18

Dear Marlene, I don’t know of any databases per se, but I recently wondered the same thing and started pulling various links together. Below are a few instances I’m aware of when individuals or groups have taken photos every year (not ideal, but depending on what you’re after, could suffice). There is also a BBC documentary by Robert Winston (‘Child of Our Time') which follows 25 children born in 2000 - you could probably get some good images from there. If you ever pull together a database though, that would be a brilliant resource! - http://diply.com/same-family-photo-taken-22-years?publisher=trendyjoe - https://petapixel.com/2015/08/03/father-and-son-take-the-same-picture-every… - http://www.news.com.au/lifestyle/real-life/true-stories/five-friends-recrea… - https://www.nytimes.com/interactive/2014/10/03/magazine/01-brown-sisters-fo… Sorry to not be able to supply anything better! All the best, Jodie

1 0

[CFP] 6th Emotion Recognition in the Wild Challenge @ ACM ICMI 2018
by abhinav dhall 22 Feb '18

22 Feb '18

Apologies for cross-postings Call for challenge participation Sixth Emotion Recognition in the Wild (EmotiW) Challenge 2018 https://sites.google.com/view/emotiw2018 @ ACM International Conference on Multimodal Interaction 2018, Boulder, Colarado. --------------------------------------------------------------------- The sixth Emotion Recognition in the Wild (EmotiW) 2018 Grand Challenge consists of an all-day event with a focus on affective sensing in unconstrained conditions. There are three sub-challenges: engagement in the wild prediction sub-challenge, audio-video based emotion classification sub-challenge and image based group emotion recognition sub-challenge. *Challenge website*: https://sites.google.com/view/emotiw2018 *Contact email*: emotiw2014[AT]gmail.com *Timeline* Challenge website - January 2018 Train and validate data available - March 2018 Test data available - 8 June 2018 Last date for uploading the results - 23 June 2018 Paper submission deadline - 1 July 2018 Paper notification - 30 July 2018 Camera-ready papers - 8 August 2018 *Organizers* Abhinav Dhall (Indian Institute of Technology Ropar, India) Roland Goecke (University of Canberra, Australia) Jyoti Joshi Tom Gedeon (Australian National University, Australia) -- Abhinav Dhall, PhD Assistant Professor, Indian Institute of Technology, Ropar Webpage: https://goo.gl/5LrRB7 Google Scholar: https://goo.gl/iDwNTx

1 0

Queen Margaret University PhD bursary competition - eyewitness identification
by Mansour, Jamal 12 Feb '18

12 Feb '18

Hi everyone, Could I please ask you to pass on this PhD bursary opportunity to any students you think might be interested? Queen Margaret University (Edinburgh, UK) now invites applications to its PhD bursary competition. One of the bursaries available may be awarded to a student interested in studying eyewitness identification. Dr Jamal Mansour (https://www.qmu.ac.uk/schools-and-divisions/psychology-and-sociology/psycho… ) welcomes applications from competitive students with an honours undergraduate or masters degree. The bursary covers tuition as well as provides an annual stipend for living and a small research budget. The deadline for applications is Friday, March 30. The details of the eyewitness identification project can be found here: https://www.qmu.ac.uk/media/4209/cass-phd-bursary-topics-2018.pdf (BUR18-03). Further details about the competition can be found here: https://www.qmu.ac.uk/study-here/postgraduate-research-study/graduate-schoo…. Jamal would like to encourage anyone who is considering applying to email her directly at jmansour(a)qmu.ac.uk<mailto:jmansour@qmu.ac.uk>. Thanks! Jamal. --------------------------------------------------------------------------------- Jamal K. Mansour, PhD Senior Lecturer in Psychology Psychology & Sociology Queen Margaret University Edinburgh, UK EH21 6UU Email: jmansour(a)qmu.ac.uk Phone: +44 (0) 131 474 0000 and say my name (Jam-el Man-sir) when prompted Fax: +44 (0) 131 474 0001 Web: https://www.qmu.ac.uk/schools-and-divisions/psychology-and-sociology/psycho… Memory Research Group Web site: https://memoryresearchgroup.wordpress.com/ Twitter: @EyewitnessIDUp Check out my recent paper on conducting multiple-trial lineup experiments: https://link.springer.com/article/10.3758/s13428-017-0855-0 Participate in our study on legal attitudes! https://www.psytoolkit.org/cgi-bin/psy2.4.0/survey?s=Z8jMR This message and its attachment(s) are intended for the addressee(s) only and should not be read, copied, disclosed, forwarded or relied upon by any person other than the intended addressee(s) without the permission of the sender. If you are not the intended addressee, you must not take any action based on this message and its attachment(s) nor must you copy or show them to anyone. If you have received this email in error, please inform the sender immediately and delete all copies of it. It is your responsibility to ensure that this message and its attachment(s) are scanned for viruses or other defects. Queen Margaret University does not accept liability for any loss or damage which may result from this message or its attachment(s), or for errors or omissions arising after it was sent. Email is not a secure medium. Email traffic entering Queen Margaret University's system is subject to routine monitoring and filtering by Queen Margaret University. Queen Margaret University, Edinburgh is a registered charity: Scottish Charity Number SC002750.

1 0

Re: [Face-research-list] PsychoMorph Questions
by Rachel Robbins 04 Feb '18

04 Feb '18

Thanks Peter, that's very helpful! And Thanks Lisa De Bruine for the other email about WebMorph, I had already applied for an account, so I will check it out. :) I will also send a separate email to you about template files. Regards, Rachel > > > Today's Topics: > > 1. Re: PsychoMorph Questions (Peter Hancock) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Thu, 25 Jan 2018 09:22:57 +0000 > From: Peter Hancock <p.j.b.hancock(a)stir.ac.uk> > To: face-research-list Mailing List > <face-research-list(a)lists.stir.ac.uk> > Subject: Re: [Face-research-list] PsychoMorph Questions > Message-ID: <4d6140ad51e44576905d8da9be1b6cb6(a)havra.ad.stir.ac.uk> > Content-Type: text/plain; charset="utf-8" > > The lines in Psychomorph are also for helping with placement, so far as I > know. The end of the file does just tell you which points are joined > together. Here’s the start of a ‘standard’ template file line section: > > 39 # 39 line definitions > 0 # move on > 2 #first line has two points > 0 0 #they are both point 0 ## I don’t know the significance of defining > a zero length line, this is the pupil > 0 # move on > 2 #next line has two points > 1 1 #other pupil > 0 > 9 # a proper line with 9 points! > 2 3 4 5 6 7 8 9 2 # the line forms a ring, starting and ending at point 2 > 0 > 9 > 10 11 12 13 14 15 16 17 10 > > You can define the lines from within Psychomorph from the delineate menu. > I’ve attached a superbatch file for caricaturing, with some comments > > Peter > > > From: Face-research-list [mailto:face-research-list- > bounces(a)lists.stir.ac.uk] On Behalf Of Rachel Robbins > Sent: 16 January 2018 23:30 > To: face-research-list Mailing List <face-research-list(a)lists.stir.ac.uk> > Subject: [Face-research-list] PsychoMorph Questions > > Hi everyone, > I am trying to learn PsychoMorph having previously used Fantamorph. I have > read through Clare Sutherland's basic guide, but I need some help with more > detailed qus and I can't find anything Wiki site. If anyone can provide > advice on any of these questions I would be very grateful! > > In Fantamorph the lines are are purely for visual grouping and don't do > anything, morphing is all to do with matched dot placement, and you can > check that dots are correctly matched by looking at the triangles. Do the > lines in PsychoMorph do anything, or are they just guides? > > Part of the reason I need to know is that I am trying to import Fantamorph > information into PsychoMorph. I have managed to import my point dot > information by taking the lines of paired dot position information from the > .fmd files and putting them into a .tem file with the number of dots in the > first line corrected. However, I couldn't figure out exactly what the info > at the end of the original .tem files generated by PsychoMorph is and > whether I need it or something equivalent. It SEEMS to be the information > about lines, does anyone know about this? > > I would also love to be able to batch importing and/or making caricatures > if I can get the .tem files set up properly. It seems like I might be able > to do this with SuperBatchTransform, but from this page > http://cherry.dcs.aber.ac.uk:8080/wiki/batch > I can't figure out exactly what needs to go in my input file. Does anyone > have an example they would be willing to share? > > Thanks! > Rachel > > -- > You make a living by what you get; you make a life by what you give. > -Winston Churchill. >

1 0

Re: [Face-research-list] Face-research-list Digest, Vol 82, Issue 6
by Lisa Debruine 25 Jan '18

25 Jan '18

Hi Rachel, You might find Webmorph.org<http://Webmorph.org> useful (it’s a web-based version of Psychomorph). It has a lot of extra batch functions that are easier to use than Psychmorph. Send me your email and I’ll sign you up for a beta testing account. I’d also be keen to add a function to webmorph to import FantaMorph templates. If you have any examples of template files you could send me, I can have a bash at writing a conversion script. Cheers, Lisa ---------------------------------------------------------- Dr Lisa M DeBruine Institute of Neuroscience and Psychology University of Glasgow 58 Hillhead Street G12 8QB lisa.debruine(a)glasgow.ac.uk<mailto:lisa.debruine@glasgow.ac.uk> http://facelab.org 0141 330 5351 ---------------------------------------------------------- On 25 Jan 2018, at 09:22, face-research-list-request(a)lists.stir.ac.uk<mailto:face-research-list-request@lists.stir.ac.uk> wrote: Send Face-research-list mailing list submissions to face-research-list(a)lists.stir.ac.uk<mailto:face-research-list@lists.stir.ac.uk> To subscribe or unsubscribe via the World Wide Web, visit http://lists.stir.ac.uk/cgi-bin/mailman/listinfo/face-research-list or, via email, send a message with subject or body 'help' to face-research-list-request(a)lists.stir.ac.uk You can reach the person managing the list at face-research-list-owner(a)lists.stir.ac.uk When replying, please edit your Subject line so it is more specific than "Re: Contents of Face-research-list digest..." Today's Topics: 1. Re: PsychoMorph Questions (Peter Hancock) ---------------------------------------------------------------------- Message: 1 Date: Thu, 25 Jan 2018 09:22:57 +0000 From: Peter Hancock <p.j.b.hancock(a)stir.ac.uk> To: face-research-list Mailing List <face-research-list(a)lists.stir.ac.uk> Subject: Re: [Face-research-list] PsychoMorph Questions Message-ID: <4d6140ad51e44576905d8da9be1b6cb6(a)havra.ad.stir.ac.uk> Content-Type: text/plain; charset="utf-8" The lines in Psychomorph are also for helping with placement, so far as I know. The end of the file does just tell you which points are joined together. Here’s the start of a ‘standard’ template file line section: 39 # 39 line definitions 0 # move on 2 #first line has two points 0 0 #they are both point 0 ## I don’t know the significance of defining a zero length line, this is the pupil 0 # move on 2 #next line has two points 1 1 #other pupil 0 9 # a proper line with 9 points! 2 3 4 5 6 7 8 9 2 # the line forms a ring, starting and ending at point 2 0 9 10 11 12 13 14 15 16 17 10 You can define the lines from within Psychomorph from the delineate menu. I’ve attached a superbatch file for caricaturing, with some comments Peter From: Face-research-list [mailto:face-research-list-bounces@lists.stir.ac.uk] On Behalf Of Rachel Robbins Sent: 16 January 2018 23:30 To: face-research-list Mailing List <face-research-list(a)lists.stir.ac.uk> Subject: [Face-research-list] PsychoMorph Questions Hi everyone, I am trying to learn PsychoMorph having previously used Fantamorph. I have read through Clare Sutherland's basic guide, but I need some help with more detailed qus and I can't find anything Wiki site. If anyone can provide advice on any of these questions I would be very grateful! In Fantamorph the lines are are purely for visual grouping and don't do anything, morphing is all to do with matched dot placement, and you can check that dots are correctly matched by looking at the triangles. Do the lines in PsychoMorph do anything, or are they just guides? Part of the reason I need to know is that I am trying to import Fantamorph information into PsychoMorph. I have managed to import my point dot information by taking the lines of paired dot position information from the .fmd files and putting them into a .tem file with the number of dots in the first line corrected. However, I couldn't figure out exactly what the info at the end of the original .tem files generated by PsychoMorph is and whether I need it or something equivalent. It SEEMS to be the information about lines, does anyone know about this? I would also love to be able to batch importing and/or making caricatures if I can get the .tem files set up properly. It seems like I might be able to do this with SuperBatchTransform, but from this page http://cherry.dcs.aber.ac.uk:8080/wiki/batch I can't figure out exactly what needs to go in my input file. Does anyone have an example they would be willing to share? Thanks! Rachel -- You make a living by what you get; you make a life by what you give. -Winston Churchill. -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.stir.ac.uk/pipermail/face-research-list/attachments/20180125/1…> -------------- next part -------------- A non-text attachment was scrubbed... Name: superbatch_new.xls Type: application/vnd.ms-excel Size: 27648 bytes Desc: superbatch_new.xls URL: <http://lists.stir.ac.uk/pipermail/face-research-list/attachments/20180125/1…> ------------------------------ Subject: Digest Footer _______________________________________________ Face-research-list mailing list Face-research-list(a)lists.stir.ac.uk http://lists.stir.ac.uk/cgi-bin/mailman/listinfo/face-research-list ------------------------------ End of Face-research-list Digest, Vol 82, Issue 6 *************************************************

1 0

PsychoMorph Questions
by Rachel Robbins 25 Jan '18

25 Jan '18

Hi everyone, I am trying to learn PsychoMorph having previously used Fantamorph. I have read through Clare Sutherland's basic guide, but I need some help with more detailed qus and I can't find anything Wiki site. If anyone can provide advice on any of these questions I would be very grateful! In Fantamorph the lines are are purely for visual grouping and don't do anything, morphing is all to do with matched dot placement, and you can check that dots are correctly matched by looking at the triangles. Do the lines in PsychoMorph do anything, or are they just guides? Part of the reason I need to know is that I am trying to import Fantamorph information into PsychoMorph. I have managed to import my point dot information by taking the lines of paired dot position information from the .fmd files and putting them into a .tem file with the number of dots in the first line corrected. However, I couldn't figure out exactly what the info at the end of the original .tem files generated by PsychoMorph is and whether I need it or something equivalent. It SEEMS to be the information about lines, does anyone know about this? I would also love to be able to batch importing and/or making caricatures if I can get the .tem files set up properly. It seems like I might be able to do this with SuperBatchTransform, but from this page http://cherry.dcs.aber.ac.uk:8080/wiki/batch I can't figure out exactly what needs to go in my input file. Does anyone have an example they would be willing to share? Thanks! Rachel -- You make a living by what you get; you make a life by what you give. -Winston Churchill.

2 1