4 papers · 1 filter
Fine-grained Human Motion Understanding with Language Models
Thomas Markhorst, Zhi-Yi Lin, Jouh Yeong Chew +2
Fine-grained motion understanding requires knowing not only which poses occur, but also when they occur. Existing motion-language models either compress motion clips or concatenate…
PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction
Zhi-Yi Lin, Thomas Markhorst, Jouh Yeong Chew +1
Human-like multimodal reaction generation is essential for natural group interactions between humans and embodied AI. However, existing approaches are limited to single-modality or…
MuPPet: Multi-person 2D-to-3D Pose Lifting
Thomas Markhorst, Zhi-Yi Lin, Jouh Yeong Chew +2
Multi-person social interactions are inherently built on coherence and relationships among all individuals within the group, making multi-person localization and body pose estimati…
Pushing Joint Image Denoising and Classification to the Edge
Thomas C Markhorst, Jan C van Gemert, Osman S Kayhan
In this paper, we jointly combine image classification and image denoising, aiming to enhance human perception of noisy images captured by edge devices, like low-light security cam…