SOURCE-LINKED INTELLIGENCE

EgoSIS: From Factorized Visual Ego-Transitions to Motion-Canonical Spatial Evidence for UAV Reasoning

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

UAV video question answering requires separating camera motion from changes in the scene, but RGB-only multimodal models receive no explicit, stable reference for that separation. We present EgoSIS, a pose-free adapter that converts RGB-derived bidirectional flow into motion-canonical visual evidence in three stages. Factorized Visual Ego-Transitions (FVET) fits a robust image-plane transition and exposes motion, residual-support, and reliability factors. Reliability-Gated Ego-Transition Memory (ReTEM) uses reliability-weighted updates for a bounded history and re-anchors it at cuts or sustain

Read original source ↗ Open in workspace

recordType

paper

region

Global