6 papers · 1 filter
PrAda: Few-Shot Visual Adaptation for Text-Prompted Segmentation
Gabriele Rosi, Fabio Cermelli, Carlo Masone +1
Segmenting images is critical for visual understanding but demands extensive pixel-level annotations. Foundational models have enabled new paradigms for predicting new classes guid…
Road Obstacle Video Segmentation
Shyam Nandan Rai, Shyamgopal Karthik, Mariana-Iuliana Georgescu +3
With the growing deployment of autonomous driving agents, the detection and segmentation of road obstacles have become critical to ensure safe autonomous navigation. However, exist…
Egocentric zone-aware action recognition across environments
Simone Alberto Peirone, Gabriele Goletto, Mirco Planamente +3
Human activities exhibit a strong correlation between actions and the places where these are performed, such as washing something at a sink. More specifically, in daily living envi…
MeshVPR: Citywide Visual Place Recognition Using 3D Meshes
Gabriele Berton, Lorenz Junglas, Riccardo Zaccone +3
Mesh-based scene representation offers a promising direction for simplifying large-scale hierarchical visual localization pipelines, combining a visual place recognition step based…
EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photography
Gabriele Berton, Gabriele Goletto, Gabriele Trivigno +3
Precise, pixel-wise geolocalization of astronaut photography is critical to unlocking the potential of this unique type of remotely sensed Earth data, particularly for its use in d…
The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement
Gabriele Trivigno, Carlo Masone, Barbara Caputo +1
Pose refinement is an interesting and practically relevant research direction. Pose refinement can be used to (1) obtain a more accurate pose estimate from an initial prior (e.g.,…