2 papers
cs.CV2025
Show or Tell? A Benchmark To Evaluate Visual and Textual Prompts in Semantic Segmentation
Gabriele Rosi, Fabio Cermelli
Prompt engineering has shown remarkable success with large language models, yet its systematic exploration in computer vision remains limited. In semantic segmentation, both textua…
cs.CV2024
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…