EPIC-KITCHENS-100 Challenge

Two-time consecutive winner of the Unsupervised Domain Adaptation Challenge

EPIC-KITCHENS-100 Challenge 🏆

Two-Time Consecutive Winner (2021 & 2022)

Achievement Summary

Proud to have achieved 3rd place in 2021 and remained among the top 3 winners in 2022 at the EPIC-KITCHENS Unsupervised Domain Adaptation Challenge, competing against teams from leading research institutions worldwide.

2022 - CVPR Workshop

TOP 3 WINNER

Our "Multi-Source Multi-Target Unsupervised Domain Adaptation" approach secured a position among the top 3 winner teams at the EPIC-KITCHENS Unsupervised Domain Adaptation Challenge presented at CVPR 2022.

Challenge Context

The challenge focused on multi-source multi-target domain adaptation, testing how models can generalize across different kitchen environments and temporal shifts in egocentric action recognition.

Key Innovation: We developed a novel approach to effectively leverage multiple source domains while adapting to multiple unlabeled target domains simultaneously, achieving robust performance across all evaluation metrics.

2021 - CVPR Workshop

3RD PLACE

Together with Chiara Plizzari, we achieved 3rd place in the third edition of the challenge, presented at the CVPR 2021 Workshop on Egocentric Perception, Interaction and Computing.

Technical Approach

We re-purposed the Relative Norm Alignment (RNA) loss, a multi-modal loss recently proposed for Domain Generalization, to operate between different backbone architectures in order to enhance their collaboration.

Results: Achieved top performance across all evaluation categories: verb, noun, and action recognition.

About EPIC-KITCHENS-100

EPIC-KITCHENS-100 is the largest-scale egocentric dataset, collected by 32 participants in their native kitchen environments, and densely annotated with actions and object interactions.

125
Verb Classes
331
Noun Classes
32
Participants

Unsupervised Domain Adaptation Challenge

The challenge tests how models can cope with temporal domain shift in action recognition. Videos recorded in 2018 (EPIC-KITCHENS-55) constitute the labeled source domain, while videos recorded two years later (EPIC-KITCHENS-100's extension) constitute the unlabeled target domain.

Objective: Assign accurate (verb, noun) labels to trimmed segments following the Unsupervised Domain Adaptation paradigm, where models must adapt to unlabeled target data without explicit supervision.

Challenge Moments

← Back to Home