Picture for Marta Sanzari

Marta Sanzari

DIAG Sapienza

Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation

Add code
Oct 31, 2022
Figure 1 for Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation
Figure 2 for Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation
Figure 3 for Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation
Viaarxiv icon

Deep execution monitor for robot assistive tasks

Add code
Feb 07, 2019
Figure 1 for Deep execution monitor for robot assistive tasks
Figure 2 for Deep execution monitor for robot assistive tasks
Figure 3 for Deep execution monitor for robot assistive tasks
Figure 4 for Deep execution monitor for robot assistive tasks
Viaarxiv icon

Visual search and recognition for robot task execution and monitoring

Add code
Feb 07, 2019
Figure 1 for Visual search and recognition for robot task execution and monitoring
Figure 2 for Visual search and recognition for robot task execution and monitoring
Figure 3 for Visual search and recognition for robot task execution and monitoring
Figure 4 for Visual search and recognition for robot task execution and monitoring
Viaarxiv icon

Discovery and recognition of motion primitives in human activities

Add code
Feb 04, 2019
Figure 1 for Discovery and recognition of motion primitives in human activities
Figure 2 for Discovery and recognition of motion primitives in human activities
Figure 3 for Discovery and recognition of motion primitives in human activities
Figure 4 for Discovery and recognition of motion primitives in human activities
Viaarxiv icon

Vision-based deep execution monitoring

Add code
Sep 29, 2017
Figure 1 for Vision-based deep execution monitoring
Figure 2 for Vision-based deep execution monitoring
Figure 3 for Vision-based deep execution monitoring
Figure 4 for Vision-based deep execution monitoring
Viaarxiv icon