Bodily Behaviors in Social Interaction: Novel Annotations and State-of-the-Art Evaluation
Michal Balazia, Philipp M\"uller, \'Akos Levente T\'anczos, August von, Liechtenstein, Fran\c{c}ois Br\'emond

TL;DR
This paper introduces BBSI, a new annotated dataset of complex bodily behaviors in social interactions, and evaluates state-of-the-art models for automatic detection, highlighting challenges and future directions.
Contribution
The paper presents the first annotated dataset of complex bodily behaviors in social interactions and adapts advanced models for behavior detection in continuous group settings.
Findings
Promising detection results with room for improvement
Comprehensive dataset with 26 hours of annotated social behavior
Evaluation of multiple spatial-temporal feature variants
Abstract
Body language is an eye-catching social signal and its automatic analysis can significantly advance artificial intelligence systems to understand and actively participate in social interactions. While computer vision has made impressive progress in low-level tasks like head and body pose estimation, the detection of more subtle behaviors such as gesturing, grooming, or fumbling is not well explored. In this paper we present BBSI, the first set of annotations of complex Bodily Behaviors embedded in continuous Social Interactions in a group setting. Based on previous work in psychology, we manually annotated 26 hours of spontaneous human behavior in the MPIIGroupInteraction dataset with 15 distinct body language classes. We present comprehensive descriptive statistics on the resulting dataset as well as results of annotation quality evaluations. For automatic detection of these behaviors,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsMulti-Head Attention · Attention Is All You Need · 3 Dimensional Convolutional Neural Network · Linear Layer · Stochastic Depth · Softmax · Dense Connections · Dropout · Adam · Byte Pair Encoding
