Affective Understanding
in Video

Track 2 papers will be part of our virtual workshop & poster session. In order to give more visibility to the current work in the area of Affective Understanding in Video, we are opening a call to submit a short paper (up to 4 pages plus references) describing new, previously, or concurrently published research or work-in-progress related to any of the topics of the workshop. These papers are not going to be published in the proceedings of the conference. Authors of all accepted papers will be invited to present their work in a poster session, and a few may be invited to give an oral as a short talk.

Human interactions and communications are driven by affective signals. Videos can express affect through music, scenery, camera angles, and movement, as well as through character tone, facial expressions, and body language. We are interested in studying affective signals including (1) the expressions evoked in viewers by videos, and (2) affect expressed by people shown in videos. Understanding these affective signals is crucial for applications including social machines, video recommendation systems, and content generation.

Affective understanding of video is interdisciplinary, requiring expertise in psychology, statistics, human-computer interactions, machine learning, and computer vision. We encourage researchers to submit papers on affective video understanding from any area for any relevant topics listed below, as well as papers that discuss different perspectives on affective video understanding.

Ethical considerations: Submissions will also be considered on ethical grounds by the program committee. Regardless of scientific quality or contribution, a submission may be rejected for ethical considerations, including methods, applications, or data that create or reinforce unfair bias, that have a primary purpose of harm or injury, or with a focus on internal thoughts or state of people. We encourage authors to include a statement of the potential broader impact of their work, including its ethical aspects and future societal consequences. Authors should take care to discuss both positive and negative outcomes.

Topics include, but are not limited to:

• Methods to recognize affective expressions evoked in viewers by videos, such as from music/audio, scenes, character interactions, and related topics.

• Methods to recognize affective expressions of people shown in videos, including facial expression, body expressions, voice expression, and related topics.

• Ethics, bias and fairness in modeling and datasets for the problem of affective understanding in videos.

• Multimodal techniques for understanding affective expressions, including non-visual signals such as audio or speech.

• Explainability and interpretability in the context of affective video understanding.

• Temporal context and scene context in affective video understanding.

• Cross-cultural analysis of affect and subjective annotations.

• Open public academic datasets to understand affective expressions in video.

• Applications of affective understanding of videos to industry.

Submission Details and Reviews

• Authors are required to submit their papers to the CMT link by the submission deadline: https://cmt3.research.microsoft.com/AUVI2021.

• Papers are limited to 4 pages (excluding references) in the CVPR 2021 format. Submissions must abide by CVPR 2021 policies (plagiarism, dual-submissions, conflicts, etc.).

• Reviews are double-blind: authors do not know the names of the reviewers, and reviewers cannot, beyond reasonable doubt, infer the names of the authors from the submission. We will not have a rebuttal process, but you can submit supplementary materials following the CVPR policy: reviewers will be encouraged to look at the supplementary, but are not obligated to do so.

• Accepted papers will be published in the CVPR workshop proceedings on IEEE Xplore and as open access on http://openaccess.thecvf.com/. In addition, top paper submissions will be invited to present at our workshop.