Michel Valstar (Imperial College London, UK)
Marc Méhu (UNIGE, Switzerland)
Maja Pantic (Imperial College London, UK / Twente University, The Netherlands)
Klaus Scherer (Unige, Switzerland)
SSPNet Network of Excellence
Most Facial Expression Recognition and Analysis systems proposed in the literature resemble each other not only by means of processing and ever-present data sparseness, but also by the lack of standardised evaluation procedures. They therefore suffer of low comparability. This is in stark contrast with more established problems in human behaviour analysis from video such as face detection and face recognition. Yet at the same time, this is a rapidly growing field of research, due to the constantly increasing interest in applications for human behaviour analysis, and technologies for human-machine communication and multimedia retrieval.
In these respects, the FG 2011 Facial Expression Recognition and Analysis challenge (FERA2011) shall help bridging the gap between excellent research on facial expression recognition and low comparability of results, for two selected tasks: the detection of FACS Action Units and the detection of a set of emotional categories.
The “GEMEP-FERA” corpus will be provided by the organisers. It consists of recordings of people displaying a range of emotions while uttering a linguistically meaningless sentence. The recordings are of 10 professional actors, and will serve to evaluate features and algorithms for the detection of 12 FACS Action Units and/or a set of 5 emotion categories.
The corpus is provided as two strictly divided partitions: one test and one training partition. The test partition is constructed such that participating systems will be evaluated on both subject-dependent data and subject-independent data, as both situations occur frequently in real-life settings. The test partition will only be made available shortly before the submission deadline. The training partition will be available to the participants immediately. Evaluation guidelines to which the authors should adhere are outlined on the FERA2011 challenge’s website, http://sspnet.eu/FERA2011. Benchmark results of two basic approaches will be provided, which will act as a baseline. The first uses Local Binary Pattern features (LBP), PCA and Support Vector Machines, and the second uses tracked fiducial facial points, PCA and Support Vector machines.
Two sub-challenges are addressed:
- In the FACS Sub-Challenge, 12 Action Units have to be detected on frame basis. The AUs are: AU1, AU2, AU4, AU6, AU7, AU10, AU12, AU15, AU17, AU18, AU25, AU26
- In the Emotion Sub-Challenge, 5 emotion categories have to be detected on event (portrayal) basis. The categories are: Anger, Fear, Joy, Relief, and Sadness
The organisers will write a paper outlining the challenge’s goals, guidelines, data, and baseline methods for comparison. This ‘baseline paper’, including the results of the baseline method on the GEMEP-FERA test partition, will be available from the challenge’s website from November 22, 2010. Participants are kindly requested to refer to this paper.
Both sub-challenges allow participants to extract their own features and apply their own classification algorithm on these. The labels of the test set will remain unknown throughout the competition, and participants will need to adhere to the specified training and parameter optimisation procedure. Participants will be allowed only three trials to upload their results for the test set. After each upload of results, the organisers will inform the participants by email about the performance attained by their system.
Each participation will be accompanied by a paper presenting the results of a specific approach to facial expression analysis that will be subjected to a peer-review process. The organisers preserve the right to re-evaluate the findings, but will not participate themselves in the challenge. Participants are encouraged to compete in both sub-challenges. Please note that the test data will be made available only one week before the submission deadline! Please read the challenge guidelines carefully for more technical information about the challenge.
Papers should be 6 pages, and should adhere to the same formatting guidelines as the main FG2011 conference. The review process will be double blind.
- Paper submission: January 24, 2011
- Notification of acceptance: February 7, 2011
- Camera ready version: February 14, 2011
The results of the Challenge will be presented at the Facial Expression Recognition and Analysis Challenge 2011 Workshop to be held in conjunction with Automatic Face and Gesture Recognition 2011 in Santa Barbara, USA. Prizes will be awarded to the two sub-challenge winners.
If you are interested and planning to participate in the FERA2011 Challenge, or if you want to be kept informed about the Challenge, please send the organisers an e-mail to indicate your interest and visit the homepage:
Thank you and best wishes,
Michel Valstar, Marc Méhu, Maja Pantic, Klaus Scherer
Dr. Michel Valstar
Imperial College London
intelligent Behaviour Understanding Group (iBUG)
180 Queen’s Gate
London, SW7 2AZ
- Tanja Bänziger
- Marian Bartlett
- Nadia Berthouze
- Richard Bowden
- Jeff Cohn
- Rana el Kaliouby
- Shaogang Gong
- Hatice Günes
- Zakia Hammal
- Qiang Ji
- Ashish Kapoor
- Jenn Jier Lien
- Michael Lyons
- Aleix Martinez
- Javier Movellan
- Kostas Karpouzis
- Ioannis Patras
- Louis-Philippe Morency
- Ioannis Pitas
- Marcello Mortillaro
- Anton Nijholt
- Matti Piettikainen
- Peter Robinson
- Nicu Sebe
- Fernando de la Torre
- Lijun Yin