English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this report, we describe the technical details of our submission to theEPIC-Kitchens-100 Unsupervised Domain Adaptation (UDA) Challenge in ActionRecognition. To tackle the domain-shift which exists under the UDA setting, wefirst exploited a recent Domain Generalization (DG) technique, called RelativeNorm Alignment (RNA). It consists in designing a model able to generalize wellto any unseen domain, regardless of the possibility to access target data attraining time. Then, in a second phase, we extended the approach to work onunlabelled target data, allowing the model to adapt to the target distributionin an unsupervised fashion. For this purpose, we included in our frameworkexisting UDA algorithms, such as Temporal Attentive Adversarial AdaptationNetwork (TA3N), jointly with new multi-stream consistency losses, namelyTemporal Hard Norm Alignment (T-HNA) and Min-Entropy Consistency (MEC). Oursubmission (entry 'plnet') is visible on the leaderboard and it achieved the1st position for 'verb', and the 3rd position for both 'noun' and 'action'.

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