First Affect-in-the-Wild Challenge

Latest News

  • The Aff-Wild Challenge training sets are released here. The test data will be released shortly (for exact dates see below)
  • The test data are out. You have 8 days to submit your results if you want to be part of the challenge (until 30th of March) (for the test data see below).
  • We are providing the bounding boxes for the face in the video by using an automatic method ( here ).
  • If you use the above data please cite the following papers: 
    • S. Zafeiriou, et. al. "Aff-Wild: Valence and Arousal in-the-wild Challenge", CVPRW, 2017. 


Aff-Wild DATA

The  Affect-in-the-Wild Challenge to be held in conjunction with International Conference on Computer Vision & Pattern Recognition (CVPR) 2017, Hawaii, USA. 




Stefanos Zafeiriou, Imperial College London, UK                      

Mihalis Nicolaou, Goldsmiths University of London, UK                       

 Irene Kotsia, Hellenic Open University, Greeece,                         

Fabian Benitez-Quiroz,  Ohio State University, USA                   

Guoying Zhao, University of Oulu,                                               

Data Chairs:

Dimitris Kollias, Imperial College London, UK                     

Athanasios Papaioannou, Imperial College London, UK     



The human Face is arguably the most studied object in computer vision. Recently, tens of databases have been collected under unconstrained conditions (also referred to as “in-thewild”) for many face related task such as face detection, face verification and facial landmark localisation. However, well-established databases and benchmarks “in-the-wild” do not exist, specifically for problems such as  estimation of affect in a continuous dimensional space (e.g., valence and arousal) in videos displaying spontaneous facial behaviour. In CVPR 2017, we propose to make a significant step further and propose new comprehensive benchmarks for assessing the performance of facial affect/behaviour analysis/understanding “in-the-wild”. To the best of our knowledge, this is the first time that an attempt for benchmarking the efforts of valence and arousal "in-the-wild". 

The Aff-Wild Challenge

For analysis of continuous emotion dimensions (such as valence and arousal) we propose to advance previous works by providing more than 400 videos (over 2,000 minutes of data) annotated with regards to valence and arousal all captured “in-the-wild” (the main source being Youtube videos). 200 videos will be provided for training and the remaining ones for testing.

Even though the majority of the videos are under the creative commons licence ( the subjects have been notified about the use of their videos. in our study.  




                                        Fig. 1: Example of expressive faces in aff-w database.







                                        Fig. 2: Example scenaria. The annotators annotated all faces in the video with regards to valence and                                                    arousal.




The training video samples are available to download from  here and the annotations from  here. The training data contain the videos and their corresponding annotation (#_arousal.txt and  #_valence.txt, # is the number of video). Furthermore, to facilitate training, especially for people that do not have access to face detectors/tracking algorithms, we provide bounding boxes for the face(s) in the videos.

  • The  dataset and annotations are available for non-commercial research purposes only.
  • All the training/testing images of the dataset are obtained from Youtube. We are not responsible for the content nor the meaning of these images.
  • You agree not to reproduce, duplicate, copy, sell, trade, resell or exploit for any commercial purposes, any portion of the images and any portion of derived data.
  • You agree not to further copy, publish or distribute any portion of  annotations of the dataset. Except, for internal use at a single site within the same organization it is allowed to make copies of the dataset.
  • We reserve the right to terminate your access to the dataset at any time.
  • If your face is displayed in any video and you want it to be removed you can email us at any time. 



Participants will have their algorithms tested on other videos which will be provided in a predefined date (see below). This dataset aims at testing the ability of current systems for estimating valence and arousal in unseen subjects. To facilitate testing we provide bounding boxes for the face(s) present in the testing videos.

The test data are available  here.

The bounding boxes for the test videos are available  here.


Performance Assessment

Performance will be assessed using the standard concordance correlation coefficient, as well as  the mean squared error objective.


Faces in-the-wild 2017 Workshop

Our aim is to accept up to 10 papers to be orally presented at the workshop.  


Submission Information:

Challenge participants should submit a paper to the Faces-in-the-wild Workshop, which summarises the methodology and the achieved performance of their algorithm. Submissions should adhere to the main CVPR 2017 proceedings style. The workshop papers will be published in the CVPR 2017 proceedings. Please sign up in the submissions system to submit your paper.

Important Dates:


  • 27 January: Announcement of the Challenges
  • 30 January: Release of the training videos
  • 22 March:  Release of the test data
  • 31 March: Deadline of returning results (Midnight GMT)
  • 3 April: Return of the results to authors
  • 20 April: Deadline for paper submission
  • 27 April: Decisions 
  • 19 May: Camera-ready deadline
  • 26 July: Workshop date


Workshop Administrator:     



[1] Stefanos Zafeiriou, Athanasios Papaioannou, Irene Kotsia, Mihalis Nicolaou, Guoying Zhao, Facial Affect in-the-wild: A survey and a new database, International Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Affect "in-the-wild" Workshop, 2016.


Program Committee:

  • Jorge Batista, University of Coimbra (Portugal)
  • Richard Bowden, University of Surrey (UK)
  • Jeff Cohn, CMU/University of Pittsburgh (USA)
  • Roland Goecke, University of Canberra (AU)
  • Peter Corcoran, NUI Galway (Ireland)
  • Fred Nicolls, University of Cape Town (South Africa)
  • Mircea C. Ionita, Daon (Ireland)
  • Ioannis Kakadiaris, University of Houston (USA)
  • Stan Z. Li, Institute of Automation Chinese Academy of Sciences (China)
  • Simon Lucey, CMU (USA)
  • Iain Matthews, Disney Research (USA)
  • Aleix Martinez, University of Ohio (USA)
  • Dimitris Metaxas, Rutgers University (USA)
  • Stephen Milborrow,            
  • Louis P. Morency, University of South California (USA)      
  • Ioannis Patras, Queen Mary University (UK)      
  • Matti Pietikainen, University of Oulu (Finland)  
  • Deva Ramaman, University of Irvine (USA)
  • Jason Saragih, Commonwealth Sc. & Industrial Research Organisation (AU) 
  • Nicu Sebe, University of Trento (Italy)
  • Jian Sun, Microsoft Research Asia
  • Xiaoou Tang, Chinese University of Hong Kong (China)
  • Fernando De La Torre, Carnegie Mellon University (USA)
  • Philip A. Tresadern, University of Manchester (UK)
  • Michel Valstar, University of Nottingham (UK)
  • Xiaogang Wang, Chinese University of Hong Kong (China)
  • Fang Wen, Microsoft Research Asia
  • Lijun Yin, Binghamton University (USA)



This challenge has been supported by a distinguished fellowship to Dr. Stefanos Zafeiriou by TEKES.