Multi-modal Multi-scale Attention Guidance in Cyber-Physical Environments
summary
Method ranks visual and auditive output devices by a computed closeness and salience suitability score that uses sigmoids for distance and direction, scaled brightness/size and sound pressure for salience, and an interaction weight to balance terms. Implementation runs in a VR supermarket with ceiling lamps, electronic shelf labels and product-placed speakers that beep. A user study finds mixed modality plus a margin 0.2 reduces travel distance; no-margin yields many more cues and volatility, and interaction weight shows no significant effect.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:15Primary and Secondary Functions
- 1:51Visual modality
- 2:47Accuracy
- 4:17Precision
- 4:58Margin
- 6:09User Study
- 6:49Virtual Reality Supermarket
- 7:07Results
- 7:55Conclusion
related talks
10mTowards Context-aware Automatic Haptic Effect Generation for Home Theatre Environments
13mEnhancing XR Audio Realism via Multimodal Scene-Aware Acoustic Rendering
07mMove, React, Repeat! The Role of Continuous Cues in Immersive Exergames
08mVirtual Objects as Spatial Cues in Collaborative Mixed Reality Environments: How They Shape ...
17mSeason Traveller: Multisensory Narration for Enhancing the Virtual Reality Experience
58mAccessible Spatial Computing
20mSpatial Communications at Scale in Virtual Environments
13mVRSight: An AI-Driven Scene Description System to Improve Virtual Reality Accessibility for Blind...