Picture for Giuseppe Averta

Giuseppe Averta

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

Add code
Nov 26, 2024
Viaarxiv icon

Select2Plan: Training-Free ICL-Based Planning through VQA and Memory Retrieval

Add code
Nov 06, 2024
Viaarxiv icon

Egocentric zone-aware action recognition across environments

Add code
Sep 21, 2024
Figure 1 for Egocentric zone-aware action recognition across environments
Figure 2 for Egocentric zone-aware action recognition across environments
Figure 3 for Egocentric zone-aware action recognition across environments
Figure 4 for Egocentric zone-aware action recognition across environments
Viaarxiv icon

AMEGO: Active Memory from long EGOcentric videos

Add code
Sep 17, 2024
Viaarxiv icon

Transient Fault Tolerant Semantic Segmentation for Autonomous Driving

Add code
Aug 30, 2024
Viaarxiv icon

What does CLIP know about peeling a banana?

Add code
Apr 18, 2024
Viaarxiv icon

The revenge of BiSeNet: Efficient Multi-Task Image Segmentation

Add code
Apr 15, 2024
Viaarxiv icon

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

Add code
Mar 05, 2024
Figure 1 for A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives
Figure 2 for A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives
Figure 3 for A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives
Figure 4 for A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives
Viaarxiv icon

PEM: Prototype-based Efficient MaskFormer for Image Segmentation

Add code
Mar 01, 2024
Figure 1 for PEM: Prototype-based Efficient MaskFormer for Image Segmentation
Figure 2 for PEM: Prototype-based Efficient MaskFormer for Image Segmentation
Figure 3 for PEM: Prototype-based Efficient MaskFormer for Image Segmentation
Figure 4 for PEM: Prototype-based Efficient MaskFormer for Image Segmentation
Viaarxiv icon

Cross-Domain Transfer Learning with CoRTe: Consistent and Reliable Transfer from Black-Box to Lightweight Segmentation Model

Add code
Feb 20, 2024
Viaarxiv icon