Presentation

<
HOIGaze: Gaze Estimation During Hand-Object Interactions in Extended Reality Exploiting Eye-Hand-Head Coordination
SessionMoving, Seeing, Touching & Eating in VR
DescriptionWe present HOIGaze – a novel approach for gaze estimation during hand-object interactions in extended reality. HOIGaze features: 1) a novel hierarchical framework that first recognises attended hand and then estimates gaze; 2) a new gaze estimator combining CNN, GCN, and cross-modal Transformers; and 3) a novel eye-head coordination loss.
Authors
Zhiming Hu
University of Stuttgart
The Hong Kong University of Science and Technology (Guangzhou)
Daniel Haeufle
University of Tuebingen
The Center for Bionic Intelligence Tuebingen Stuttgart
Syn Schmitt
University of Stuttgart
The Center for Bionic Intelligence Tuebingen Stuttgart
Andreas Bulling
University of Stuttgart
Event Type
Technical Paper
TimeMonday, 11 August 202511:15am - 11:25am PDT
LocationWest Building, Rooms 118-120
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Monday, 11 August 202510:45am - 12:15pm PDTWest Building, Rooms 118-120
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation
Similar Presentations
FaceExpressions-70k: A Dataset of Perceived Expression Differences
VR-Doh: Hands-on 3D Modeling in Virtual Reality
Mapping Human Attention in Reconstructed 3D Scenes: Gaze, Language, and Point Cloud Fusion