Giuseppe Averta

6

Papers

89

Total Citations

Papers (6)

PEM: Prototype-based Efficient MaskFormer for Image Segmentation

Your ViT is Secretly an Image Segmentation Model

AMEGO: Active Memory from long EGOcentric videos

A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives

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

HiERO: Understanding the Hierarchy of Human Behavior Enhances Reasoning on Egocentric Videos