Emotion Recognition in the Wild Challenge and Workshop (EmotiW 2013) – 9 Dec 2013

The Vision and Sensing Group at the University of Canberra together with colleagues from the Australian National University is organising a Grand Challenge and Workshop on emotion recognition in the wild in conjunction with the 15th ACM International Conference on Multimodal Interaction ICMI2013, which will be held in Sydney, Australia, 9-13 Dec 2013. The EmotiW 2013 workshop will be held on the Mon, 9 Dec 2013, before the ICMI2013 main conference. This is conveniently timed directly after the IEEE International Conference on Computer Vision ICCV2013, which will also be held in Sydney, Australia, 1-8 Dec 2013 to facilitate easy planning for those who wish to attend both events.

The Emotion Recognition in the Wild 2013 Grand Challenge and Workshop consists of a multimodal emotion classification challenge, which mimics real-world conditions. Traditionally, emotion recognition has been performed on laboratory controlled data. While undoubtedly worthwhile at the time, such lab controlled data poorly represents the environment and conditions faced in real-world situations. With the increase in the number of video clips online, it is worthwhile to explore the performance of emotion recognition methods that work ‘in the wild’. The goal of this Grand Challenge is to define a common platform for evaluation of emotion recognition methods in real-world conditions.

The database in the 2013 challenge is the Acted Facial Expression in the Wild (AFEW), which consists of audio-video data collected from movies showing close-to-real-world conditions. Emotion recognition is to be performed on the sequence level. The datasets for training and validation are available now, while the testing dataset will be made available on the 30 Jun 2013. The challenge seeks participation from researchers working on emotion recognition intend to create, extend and validate their methods on data in real-world conditions. Researchers are welcome to test their existing state-of-art emotion recognition methods and to report the results.

In addition to the call for papers for the challenge, we also invite researchers to submit other original work in line with the 'Emotion Recognition in the Wild' theme as papers to the workshop, which will be held in conjunction with the challenge. Paper submissions to the challenge must use the challenge dataset, while papers to the workshop can make use of other datasets (e.g. SFEW, GENKI) but must be in line with the 'Emotion Recognition in the Wild' theme. Accepted challenge and workshop papers will be published in the ACM ICMI2013 conference proceedings.

Topics for the workshop include but are not limited to: Multimodal emotion recognition in the wild Vision based temporal expression analysis in the wild Vision based static expression analysis on database like SFEW/GENKI Audio based emotion analysis in the wild New data corpora representing real-world conditions Facial feature tracking in the wild Multimodal emotion recognition applications

Important Dates:

20 Mar 2013 – Challenge training and validation datasets available
30 Jun 2013 – Challenge test dataset available
15 Jul 2013 – Submission of challenge results (details of the format will be posted on the website)
25 Jul 2013 – Paper submission deadline
30 Aug 2013 – Notification of acceptance
15 Sep 2013 – Camera-ready papers
9 Dec 2013 – Workshop


Abhinav Dhall, Australian National University
Roland Goecke, University of Canberra / Australian National University
Jyoti Joshi, University of Canberra
Michael Wagner, University of Canberra / Australian National University
Tom Gedeon, Australian National University


Programme Committee:

Akshay Asthana, Imperial College London
Nadia Bianchi-Berthouze, University of College London
Carlos Busso, University of Texas, Dallas
Hazim Kemal Ekenel, Karlsruhe Institute of Technology
Hatice Gunes, Queen Mary University of London
Zakia Hammal, Carnegie Mellon University
Gwen Littlewort, University of California San Diego
Elisa Martinez Marroquin, University of Canberra
Christian Peter, Ambertree Assistance Technologies
Stefan Scherer, University of Southern California
Bjoern Schuller, Technische Universitaet Muenchen
Nicu Sebe, University of Trento
Shiguang Shan, Chinese Academy of Sciences
Gaurav Sharma, University of Caen
Michel Valstar, University of Nottingham
Stefanos Zafeiriou, Imperial College London