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 technical report, we present our findings from a study conducted onthe EPIC-KITCHENS-100 Unsupervised Domain Adaptation task for ActionRecognition. Our research focuses on the innovative application of adifferentiable logic loss in the training to leverage the co-occurrencerelations between verb and noun, as well as the pre-trained Large LanguageModels (LLMs) to generate the logic rules for the adaptation to unseen actionlabels. Specifically, the model's predictions are treated as the truthassignment of a co-occurrence logic formula to compute the logic loss, whichmeasures the consistency between the predictions and the logic constraints. Byusing the verb-noun co-occurrence matrix generated from the dataset, we observea moderate improvement in model performance compared to our baseline framework.To further enhance the model's adaptability to novel action labels, weexperiment with rules generated using GPT-3.5, which leads to a slight decreasein performance. These findings shed light on the potential and challenges ofincorporating differentiable logic and LLMs for knowledge extraction inunsupervised domain adaptation for action recognition. Our final submission(entitled `NS-LLM') achieved the first place in terms of top-1 actionrecognition accuracy.

A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023