Inverse Foraging: Inferring Users’ Interest in Pervasive Displays
summary
A method fits an information-foraging model to measured viewing times on tiled displays to estimate content interest. The tile forager model is fitted from three to five layout observations, reaching above 60% after three layouts and peaking at 77% accuracy with five layouts (reported R2 > 70%). A field prototype uses a Kinect to detect gaze and distance and counts passers-by to drive live content adaptation.
AI-written summary · about
related talks
19mGroup Touch: Distinguishing Tabletop Users in Group Settings via Statistical Modeling of Touch Pairs
18mHow the Experts Do It: Assessing and Explaining Agent Behaviors in Real-Time Strategy Games
11mDetection and Differentiation of Obstacles in Repeated Adaptive Human-Computer Interactions from ...
04mInteractive Sports Analytics
17mLearning Cooperative Personalized Policies from Gaze Data
19mUsing the activity logs to predict user behaviour
39mMind-Reading with Adaptive and Intelligent User Interfaces
28mPreference Learning from Minimal Human Feedback for Interactive