Aff-Wild: Valence and Arousal ‘In-the-Wild’ Challenge

By Stefanos P. Zafeiriou, Dimitrios Kollias, Mihalis A. Nicolaou, Athanasios Papaioannou, Guoying Zhao, Irene Kotsia. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017

408 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/0bb662fb6d663005d15aef0e5a13b8d74a7aa2ad

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Experimental and Cognitive Psychology

Citations in the corpus

Continual Learning for Affective Robotics: Why, What and How? (2020, background): “1) include (i) perception models that are robust to real-world interaction settings [16] while being sensitive to each individual’s socio-emotional behaviours [18], [19], [54], and (ii) generation of context-specific behaviour attributing both the users’ behaviour as well as the interaction settings”
Analysing Affective Behavior in the First ABAW 2020 Competition (2020, background): “AffWild2 is an extension of Aff-Wild [18], [35], [17]; 260 more YouTube videos, with 1, 413, 000 frames, have been added to Aff-Wild.”
Privileged Information for Modeling Affect In The Wild (2021, background): “Towards this direction large databases [20], [25]–[28] that simulate human emotions in the wild are necessary [29].”
Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace (2019, methodology): “Collected dataset and properties We extend the Aff-Wild database [20, 50], by collecting a new dataset consisting of 260 YouTube videos, with 1,413,000 frames and a total length of 13 hours and 5 minutes.”
One Label, One Billion Faces: Usage and Consistency of Racial Categories in Computer Vision (2021, background): “Many of the most visible applications of computer vision require datasets consisting of human faces: face recognition[12], kinship[40], demographic estimation [15], emotion recognition [50], and generative modeling [26].”
Factorized Higher-Order CNNs With an Application to Spatio-Temporal Emotion Estimation (2019, background): “This task is the subject of most of the recent research in affect estimation [37, 19, 23, 50] and is the focus of this paper.”