Learning Egocentric In-Hand Object Segmentation through Weak Supervision from Human Narrations

by Giuseppe Caracciolo | Nov 4, 2025 | Publications

Click Here to...

One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework

by Giuseppe Caracciolo | Nov 4, 2025 | Publications

Click Here to...

Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation

by Giuseppe Caracciolo | Nov 4, 2025 | Publications

Click Here to...

Is CLIP the main roadblock for fine-grained open-world perception?

by Giuseppe Caracciolo | Nov 4, 2025 | Publications

Click Here to...

Training-free sparse representations of dense vectors for scalable information retrieval

by Giuseppe Caracciolo | Nov 4, 2025 | Publications

Click Here to...

Information Dissimilarity Measures in Decentralized Knowledge Distillation: A Comparative Analysis

by Giuseppe Caracciolo | Nov 4, 2025 | Publications

Click Here to...