Aff-Wild2 database

Affective computing has been largely limited in terms of available data resources. The need to collect and annotate diverse in-the-wild datasets has become apparent with the rise of deep learning models, as the default approach to address any computer vision task.
Some in-the-wild databases have been recently proposed. However: i) their size is small, ii) they are not audiovisual, iii) only a small part is manually annotated, iv) they contain a small number of subjects, or v) they are not annotated for all main behavior tasks (valence arousal estimation, action unit detection and basic expression classification).
To address these, we substantially extend the largest available in-the-wild database (Aff-Wild) to study continuous emotions such as valence and arousal. Furthermore, we annotate parts of the database with basic expressions and action units. We call this database Aff-Wild2. To the best of our knowledge, AffWild2 is the only in-the-wild database containing annotations for all 3 main behavior tasks. The database is also a large scale one. It is also the first audiovisual database with annotations for AUs. All AU annotated databases do not contain audio, but only images or videos.

The Aff-Wild2 is annotated in a per frame basis for the seven basic expressions (i.e., happiness, surprise, anger, disgust, fear, sadness and the neutral state), twelve action units (AUs 1,2,4,6,7,10,12,15,23,24,25, 26) and valence and arousal. In total Aff-Wild2 consists of 564 videos of around 2.8M frames with 554 subjects (326 of which are male and 228 female). All videos have been annotated in terms of valence and arousal. 546 videos of around 2.6M frames have been annotated in terms of the basic expressions. 541 videos of around 2.6M frames have been annotated in terms of action units. Aff-Wild2 displayes a big diversity in terms of subjects' ages, ethnicities and nationalities; it has also great variations and diversities of environments.

How to acquire Aff-Wild2

If you are an academic, (i.e., a person with a permanent position at a research institute or university, e.g. a professor or a post-doc, but not a PhD/PG/UG student), please:
i) fill in this EULA;
ii) use your official academic email (as data cannot be released to personal emails);
iii) send an email to d.kollias@qmul.ac.uk with subject: Aff-Wild2 request by academic;
iv) include in the email the above signed EULA, the reason why you require access to the Aff-Wild2 database, and your official academic website

in the case of Ph.D. students: your supervisor should perform the above described steps.

If you are from industry and you want to acquire Aff-Wild2, please send an email from your official industrial email to d.kollias@qmul.ac.uk with subject: Aff-Wild2 request from industry and explain the reason why the database access is needed; also specify if it is for research or commercial purposes.

If you are an undergraduate or postgraduate student (but not a Ph.D. student), please:
i) fill in this EULA;
ii) use your official university email (data cannot be released to personal emails);
iii) send an email to d.kollias@qmul.ac.uk with subject: Aff-Wild2 request by student
iv) include in the email the above signed EULA and proof/verification of your current student status (eg student ID card).
To all UG/PG students: 
1 ) The database cannot be shared to students for research internships; the supervisor should instead follow the steps outlined in the two above cases (industry or academia).
2) If the email does not contain all the required information or if the email contains incorrect information (e.g. non filled in EULA or non signed EULA or an incorrect EULA), then the database access request will be automatically rejected and there will be no reply to the request. 

Due to the high volume of requests, please allow about 14 days for the reply to your request for access.

References

If you use the above data, you must cite all following papers (and the white paper): 

• D. Kollias: "ABAW: Learning from Synthetic Data & Multi-Task Learning Challenges", 2022

@article{kollias2022abaw, title={ABAW: Learning from Synthetic Data \& Multi-Task Learning Challenges}, author={Kollias, Dimitrios}, journal={arXiv preprint arXiv:2207.01138}, year={2022} }

• D. Kollias: "ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Multi-Task Learning Challenges", IEEE CVPR, 2022

@inproceedings{kollias2022abaw, title={Abaw: Valence-arousal estimation, expression recognition, action unit detection \& multi-task learning challenges}, author={Kollias, Dimitrios}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={2328--2336}, year={2022} } 

• D. Kollias, et. al.: "Analysing Affective Behavior in the second ABAW2 Competition". ICCV, 2021

@inproceedings{kollias2021analysing, title={Analysing affective behavior in the second abaw2 competition}, author={Kollias, Dimitrios and Zafeiriou, Stefanos}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={3652--3660}, year={2021}}

• D. Kollias, et. al.: "Analysing Affective Behavior in the First ABAW 2020 Competition". IEEE FG, 2020

@inproceedings{kollias2020analysing, title={Analysing Affective Behavior in the First ABAW 2020 Competition}, author={Kollias, D and Schulc, A and Hajiyev, E and Zafeiriou, S}, booktitle={2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020)(FG)}, pages={794--800}}

• D. Kollias, et. al.: "Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study", 2021

@article{kollias2021distribution, title={Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study}, author={Kollias, Dimitrios and Sharmanska, Viktoriia and Zafeiriou, Stefanos}, journal={arXiv preprint arXiv:2105.03790}, year={2021} }

• D. Kollias, S. Zafeiriou: "Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace". BMVC, 2019

@article{kollias2019expression, title={Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace}, author={Kollias, Dimitrios and Zafeiriou, Stefanos}, journal={arXiv preprint arXiv:1910.04855}, year={2019} }

• D. Kollias, et at.: "Face Behavior a la carte: Expressions, Affect and Action Units in a Single Network", 2019

@article{kollias2019face,title={Face Behavior a la carte: Expressions, Affect and Action Units in a Single Network}, author={Kollias, Dimitrios and Sharmanska, Viktoriia and Zafeiriou, Stefanos}, journal={arXiv preprint arXiv:1910.11111}, year={2019}}

• D. Kollias, et. al.: "Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond". International Journal of Computer Vision (IJCV), 2019

@article{kollias2019deep, title={Deep affect prediction in-the-wild: Aff-wild database and challenge, deep architectures, and beyond}, author={Kollias, Dimitrios and Tzirakis, Panagiotis and Nicolaou, Mihalis A and Papaioannou, Athanasios and Zhao, Guoying and Schuller, Bj{\"o}rn and Kotsia, Irene and Zafeiriou, Stefanos}, journal={International Journal of Computer Vision}, pages={1--23}, year={2019}, publisher={Springer} }

• S. Zafeiriou, et. al. "Aff-Wild: Valence and Arousal in-the-wild Challenge", CVPRW, 2017

@inproceedings{zafeiriou2017aff, title={Aff-wild: Valence and arousal ‘in-the-wild’challenge}, author={Zafeiriou, Stefanos and Kollias, Dimitrios and Nicolaou, Mihalis A and Papaioannou, Athanasios and Zhao, Guoying and Kotsia, Irene}, booktitle={Computer Vision and Pattern Recognition Workshops (CVPRW), 2017 IEEE Conference on}, pages={1980--1987}, year={2017}, organization={IEEE} }

Evaluation of your predictions on the test set

First of all, you should clarify to which set (VA, AU, Expression) the predictions correspond. The format of the predictions should follow the (same) format of the annotation files that we provide. In detail:

In the VA case:  Send the files with names as the corresponding videos. Each line of each file should contain the values of valence and arousal for the corresponding frame separated by comma ,i.e. for file 271.csv:

line 1 should be: valence,arousal
line 2 should be: valence_of_first_frame,arousal_of_first_frame     (for instance it could be: 0.53,0.28)
line 3 should be: valence_of_second_frame,arousal_of_second_frame
...
last line: valence_of_last_frame,arousal_of_last_frame

In the Expression case:  Send the files with names as the corresponding videos. Each line of each file should contain the corresponding basic expression prediction (0,1,2,3,4,5,6, where: 0 denotes neutral, 1 denotes anger, 2 denotes disgust, 3 denotes fear, 4 denotes happiness, 5 denotes sadness and 6 denotes surprise). For instance for file 282.csv:

first line should be: Neutral,Anger,Disgust,Fear,Happiness,Sadness,Surprise
second line should be: basic_expression_prediction_of_first_frame    (such as 5)
...
last line should be: basic_expression_prediction_of_last_frame    

In the AU case:  Send the files with names as the corresponding videos. Each line of each file should contain 8 numbers (0 or 1) comma separated, that correspond to the 8 Action Units (AU1, AU2, AU4, AU6, AU12, AU15, AU20, AU25). For instance for file video18.csv:

first line should be: AU1,AU2,AU4,AU6,AU12,AU15,AU20,AU25
second line should be: AU1_of_first_frame,AU2_of_first_frame,AU4_of_first_frame,AU6_of_first_frame,AU12_of_first_frame,AU15_of_first_frame,AU20_of_first_frame,AU25_of_first_frame    (such as: 0,1,1,0,0,0,0,1)
...
last line should be: AU1_of_last_frame,AU2_of_last_frame,AU4_of_last_frame,AU6_of_last_frame,AU12_of_last_frame,AU15_of_last_frame,AU20_of_last_frame,AU25_of_last_frame      

Note that in your files you should include predictions for all frames in the video (irregardless if the bounding box failed or not). 

Important Information:

• All the training/validation/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.