activity
20242026
most citedΦeat: Physically Grounded Material Feature Representation

1 citations · 1 across the 3 of their papers we have counts for

collaborators

8 papers

cs.CV20261 cited

Φeat: Physically Grounded Material Feature Representation

Giuseppe Vecchio, Adrien Kaiser, Claudia Cuttano +4

While foundation models have emerged as general-purpose visual backbones, their representations are primarily optimized for semantics and lack explicit modeling of physical factors…

cs.CV2026

MARCO: Navigating the Unseen Space of Semantic Correspondence

Claudia Cuttano, Gabriele Trivigno, Carlo Masone +1

Recent advances in semantic correspondence rely on dual-encoder architectures, combining DINOv2 with diffusion backbones. While accurate, these billion-parameter models generalize…

cs.CV2026

INSID3: Training-Free In-Context Segmentation with DINOv3

Claudia Cuttano, Gabriele Trivigno, Christoph Reich +3

In-context segmentation (ICS) aims to segment arbitrary concepts, e.g., objects, parts, or personalized instances, given one annotated visual examples. Existing work relies on (i)…

cs.CV2025

SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation

Claudia Cuttano, Gabriele Trivigno, Giuseppe Averta +1

Few-shot segmentation aims to segment unseen object categories from just a handful of annotated examples. This requires mechanisms that can both identify semantically related objec…

cs.CV2025

SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation

Claudia Cuttano, Gabriele Trivigno, Gabriele Rosi +2

Referring Video Object Segmentation (RVOS) relies on natural language expressions to segment an object in a video clip. Existing methods restrict reasoning either to independent sh…

cs.CV2024

PEM: Prototype-based Efficient MaskFormer for Image Segmentation

Niccolò Cavagnero, Gabriele Rosi, Claudia Cuttano +4

Recent transformer-based architectures have shown impressive results in the field of image segmentation. Thanks to their flexibility, they obtain outstanding performance in multipl…