Picture for Mirco Planamente

Mirco Planamente

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

Bringing Online Egocentric Action Recognition into the wild

Add code
Nov 06, 2022
Viaarxiv icon

PoliTO-IIT-CINI Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition

Add code
Sep 09, 2022
Figure 1 for PoliTO-IIT-CINI Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
Figure 2 for PoliTO-IIT-CINI Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
Figure 3 for PoliTO-IIT-CINI Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
Viaarxiv icon

E$^2$MOTION: Motion Augmented Event Stream for Egocentric Action Recognition

Add code
Dec 07, 2021
Figure 1 for E$^2$MOTION: Motion Augmented Event Stream for Egocentric Action Recognition
Figure 2 for E$^2$MOTION: Motion Augmented Event Stream for Egocentric Action Recognition
Figure 3 for E$^2$MOTION: Motion Augmented Event Stream for Egocentric Action Recognition
Figure 4 for E$^2$MOTION: Motion Augmented Event Stream for Egocentric Action Recognition
Viaarxiv icon

Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition

Add code
Oct 19, 2021
Figure 1 for Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition
Figure 2 for Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition
Figure 3 for Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition
Figure 4 for Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition
Viaarxiv icon

PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition

Add code
Jul 01, 2021
Figure 1 for PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
Figure 2 for PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
Figure 3 for PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
Viaarxiv icon

Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment

Add code
Jun 03, 2021
Figure 1 for Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment
Figure 2 for Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment
Figure 3 for Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment
Figure 4 for Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment
Viaarxiv icon

DA4Event: towards bridging the Sim-to-Real Gap for Event Cameras using Domain Adaptation

Add code
Mar 23, 2021
Figure 1 for DA4Event: towards bridging the Sim-to-Real Gap for Event Cameras using Domain Adaptation
Figure 2 for DA4Event: towards bridging the Sim-to-Real Gap for Event Cameras using Domain Adaptation
Figure 3 for DA4Event: towards bridging the Sim-to-Real Gap for Event Cameras using Domain Adaptation
Figure 4 for DA4Event: towards bridging the Sim-to-Real Gap for Event Cameras using Domain Adaptation
Viaarxiv icon

Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition

Add code
Apr 21, 2020
Figure 1 for Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition
Figure 2 for Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition
Figure 3 for Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition
Figure 4 for Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition
Viaarxiv icon

Joint Encoding of Appearance and Motion Features with Self-supervision for First Person Action Recognition

Add code
Feb 10, 2020
Figure 1 for Joint Encoding of Appearance and Motion Features with Self-supervision for First Person Action Recognition
Figure 2 for Joint Encoding of Appearance and Motion Features with Self-supervision for First Person Action Recognition
Figure 3 for Joint Encoding of Appearance and Motion Features with Self-supervision for First Person Action Recognition
Figure 4 for Joint Encoding of Appearance and Motion Features with Self-supervision for First Person Action Recognition
Viaarxiv icon