6 papers
Contrastive Learning under Noisy Temporal Self-Supervision for Colonoscopy Videos
Luca Parolari, Pietro Gori, Lamberto Ballan +2
Learning robust representations of polyp tracklets is key to enabling multiple AI-assisted colonoscopy applications, from polyp characterization to automated reporting and retrieva…
Benchmarking Layout-Guided Diffusion Models through Unified Semantic-Spatial Evaluation in Closed and Open Settings
Luca Parolari, Nicla Faccioli, Lamberto Ballan
Evaluating layout-guided text-to-image generative models requires assessing both semantic alignment with textual prompts and spatial fidelity to prescribed layouts. Assessing layou…
7Bench: a Comprehensive Benchmark for Layout-guided Text-to-image Models
Elena Izzo, Luca Parolari, Davide Vezzaro +1
Layout-guided text-to-image models offer greater control over the generation process by explicitly conditioning image synthesis on the spatial arrangement of elements. As a result,…
Temporally-Aware Supervised Contrastive Learning for Polyp Counting in Colonoscopy
Luca Parolari, Andrea Cherubini, Lamberto Ballan +1
Automated polyp counting in colonoscopy is a crucial step toward automated procedure reporting and quality control, aiming to enhance the cost-effectiveness of colonoscopy screenin…
Towards Polyp Counting In Full-Procedure Colonoscopy Videos
Luca Parolari, Andrea Cherubini, Lamberto Ballan +1
Automated colonoscopy reporting holds great potential for enhancing quality control and improving cost-effectiveness of colonoscopy procedures. A major challenge lies in the automa…
Harlequin: Color-driven Generation of Synthetic Data for Referring Expression Comprehension
Luca Parolari, Elena Izzo, Lamberto Ballan
Referring Expression Comprehension (REC) aims to identify a particular object in a scene by a natural language expression, and is an important topic in visual language understandin…