activity
20012023
most citedLearning Recursive Segments for Discourse Parsing

27 citations · 137 across the 13 of their papers we have counts for

collaborators

14 papers

cs.CV2023★ 19 cited

MultiMediate'23: Engagement Estimation and Bodily Behaviour Recognition in Social Interactions

Philipp Müller, Michal Balazia, Tobias Baur +9

Automatic analysis of human behaviour is a fundamental prerequisite for the creation of machines that can effectively interact with- and support humans in social interactions. In M…

cs.CV2023

Backchannel Detection and Agreement Estimation from Video with Transformer Networks

Ahmed Amer, Chirag Bhuvaneshwara, Gowtham K. Addluri +3

Listeners use short interjections, so-called backchannels, to signify attention or express agreement. The automatic analysis of this behavior is of key importance for human convers…

cs.CV2022

Multimodal Vision Transformers with Forced Attention for Behavior Analysis

Tanay Agrawal, Michal Balazia, Philipp Müller +1

Human behavior understanding requires looking at minute details in the large context of a scene containing multiple input modalities. It is necessary as it allows the design of mor…

cs.HC2022★ 13 cited

MultiMediate '22: Backchannel Detection and Agreement Estimation in Group Interactions

Philipp Müller, Michael Dietz, Dominik Schiller +5

Backchannels, i.e. short interjections of the listener, serve important meta-conversational purposes like signifying attention or indicating agreement. Despite their key role, auto…

cs.LG2022★ 12 cited

Gaze-enhanced Crossmodal Embeddings for Emotion Recognition

Ahmed Abdou, Ekta Sood, Philipp Müller +1

Emotional expressions are inherently multimodal -- integrating facial behavior, speech, and gaze -- but their automatic recognition is often limited to a single modality, e.g. spee…

cs.CV2021★ 21 cited

Multimodal Integration of Human-Like Attention in Visual Question Answering

Ekta Sood, Fabian Kögel, Philipp Müller +3

Human-like attention as a supervisory signal to guide neural attention has shown significant promise but is currently limited to uni-modal integration - even for inherently multimo…