The first workshop on “What's next in Affect Modeling?” (http://whatnext.tamed-project.eu/) will be held online in conjunction with ACII 2023 (https://acii-conf.net/).

*** Description ***

The valid and reliable evaluation of affect and affective interaction is key for the advancement of affective computing (AC). Recent breakthroughs in deep (machine) learning and generative AI have boosted the efficiency and generality of affect models by discovering novel representations of users and their context acting on high resolutions of multimodal signals. Such representations, however, are data-hungry and in need of large datasets that AC is not able to offer. Moreover, as affect models gradually become larger and more complex, their expressivity, explainability, and transparency become increasingly opaque.

This workshop series puts an emphasis on state-of-the-art methods in machine learning and their suitability for advancing the reliability, validity, and generality of affective models. We will be investigating entirely new methods, untried in AC, but also methods that can be coupled with traditional and dominant practices in affective modeling. In particular, we encourage submissions that offer visions of particular algorithmic advancements for affect modeling and proof-of-concept case studies showcasing the potential of new sophisticated machine learning methods. This is the third workshop in the series after the successful first and second events organised in conjunction with ACII 2021 and 2022. Papers were submitted, and after a double-blind peer-review process (three reviewers assigned to each paper), the accepted ones were presented during the event. Besides paper presentations, the workshop featured a keynote talk delivered by Prof. Michel Valstar (2021) and Prof. Erik Cambria (2022). Around twenty-five participants attended each of the workshops.

Topics include but are not limited to:

– Representation learning of affect

– Signal tensorization for affect modelling

– Unsupervised tensor subspace learning and supervised (semi- and self-) tensor-based machine learning for affect modeling

– RL as an affective computing paradigm

– Causal and anticausal predictors in affect modeling

– Contrastive learning paradigms and models for affect modeling

– Neural architecture search and open-ended evolution for affect

– Distributed and Disentangled Affect Representation

– Sophisticated multimodal fusion (e.g. via tensors) of affective signals

– Explainable affect models

– Applications studies in education, art, creativity, health, psychology, and beyond

*** Important dates ***

– Paper submission: 28 April 2023

– Notification of acceptance: TBA

– Camera-ready submission: TBA

Organizers

– Matthew Barthet, Konstantinos Makantasis, Georgios N. Yannakakis, Bjoern Schuller, Guoying Zhao

** Endorsed by ***

AI4MEDIA project: https://www.ai4media.eu 

sustAGE EU RIA project: https://www.sustage.eu