Search papers, labs, and topics across Lattice.
This paper introduces TrajLoc, a unified framework that enhances cross-view geo-localization by integrating both video clips and route descriptions, addressing the limitations of existing methods that rely solely on visual data. By leveraging a new dataset of approximately 39,000 video-text-satellite triplets, the authors demonstrate that combining dense visual cues with abstract linguistic semantics significantly improves matching accuracy. Experimental results reveal that TrajLoc outperforms state-of-the-art techniques in both video and text geo-localization tasks, showcasing the effectiveness of trajectory-aware representations.
Combining video and route descriptions can dramatically enhance geo-localization accuracy, achieving significant improvements over existing methods.
Cross-view geo-localization matches ground-level observations against geo-tagged satellite imagery. Recent methods show that sequential queries such as video clips yield richer spatiotemporal cues than single images, yet they overlook a complementary sequential modality: route descriptions -- which capture the same trajectory at a higher level of abstraction and are often the only input available (e.g., a user directing an autonomous vehicle to a pickup point). To bridge this gap, we introduce SeqGeo-VL, a dataset of $\sim$39K video-text-satellite triplets, and TrajLoc, a unified framework capable of processing both video clips and route descriptions. By leveraging both dense visual and abstract linguistic semantics, TrajLoc enables these modalities to mutually reinforce cross-view matching. We further propose TrajMod, a lightweight module that conditions query embeddings on trajectory geometry, yielding spatially-aware representations. Experiments show that TrajLoc achieves substantial gains over state-of-the-art methods on both video and text geo-localization. The project page is available at https://humblegamer.github.io/trajloc/.
