Embodied Intelligence Observer

X²Localizer:跨视角视频地理定位的跨粒度对齐

Original title: X$^2$Localizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization

IndustryAI 60

Source: arXiv cs.ROPublish time unverified

arXiv:2608.16658v2 Announce Type: replace-cross Abstract: Cross-view Video Geo-localization (CVG) aims to localize ground-view videos by retrieving their corresponding geo-tagged aerial images. However, CVG approaches rely on fixed-length inputs and post-hoc refinement, hindering online-oriented localization under partial or dynamic observations.

X²Localizer:跨视角视频地理定位的跨粒度对齐 | Embodied Intelligence Observer