cLuster: Smart Clustering of Free-Hand Sketches on Large Interactive Surfaces
summary
cLuster automatically groups free‑hand strokes on large interactive surfaces by training per‑perspective distance functions (over 20 geometric features) and combining them on the fly via a linear combination of pre‑trained perspectives estimated from a single user selection (one mlink and one ceiling). It implements single‑link agglomerative clustering, supports real‑time threshold, split/merge and gesture corrections, and an initial evaluation reports ~50% zero or one correction needed; it also enables rearrange/mirror workflows.
AI-written summary · about
chapters (4)
related talks
49mClustering in the Mapbox Tiling Service
06mOverthere : A Simple and Intuitive Object Registration Method for an Absolute Mid-air Pointing ...
46mArchitectural Decisions for Interactive Viz
01h 15mBursts, Cascades, and Hot Spots: Algorithmic Models of Social Phenomena
16mHandOver: Enabling Precise Selection & Manipulation of 3D Objects with Mouse and Hand Tracking
15mA Unified Model for User Identification on Multi-touch Surfaces. A Survey and Meta-analysis.
18mScenograph: Fitting Real-Walking VR Experiences into Various Tracking Volumes
21mOff-Limits: Interacting Beyond the Boundaries of Large Displays