DiaLoc: An Iterative Approach to Embodied Dialog Localization

arXiv:2403.06846v1 Announce Type: new
Abstract: Multimodal learning has advanced the performance for many vision-language tasks. However, most existing works in embodied dialog research focus on navigation and leave the localization task understudied. The few existing dialog-based localization approaches assume the availability of entire dialog prior to localizaiton, which is impractical for deployed dialog-based localization. In this paper, we propose DiaLoc, a new dialog-based localization framework which aligns with a real human operator behavior. Specifically, we produce an iterative refinement of …

abstract advanced arxiv availability cs.cv dialog embodied focus however iterative language localization multimodal multimodal learning navigation performance prior research tasks type vision