Speak to the City: Multimodal Resolution for Outside-the-Vehicle References
This work presents a robust, multimodal OVR framework fusing user gaze and natural language to identify Points of Interest (POIs), and developed a VR-based pipeline synchronizing 360-degree transit videos with vehicle GNSS telemetry to address the scarcity of dynamic vehicular data.
Alireza Parchami, Artin Saberpour Abadian, Robin Connor Schramm et al.
· Proceedings of the 18th Inte... · 0 citations