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

While significant advancements have been made in video question answering(VideoQA), the potential benefits of enhancing model generalization throughtailored difficulty scheduling have been largely overlooked in existingresearch. This paper seeks to bridge that gap by incorporating VideoQA into acurriculum learning (CL) framework that progressively trains models fromsimpler to more complex data. Recognizing that conventional self-paced CLmethods rely on training loss for difficulty measurement, which might notaccurately reflect the intricacies of video-question pairs, we introduce theconcept of uncertainty-aware CL. Here, uncertainty serves as the guidingprinciple for dynamically adjusting the difficulty. Furthermore, we address thechallenge posed by uncertainty by presenting a probabilistic modeling approachfor VideoQA. Specifically, we conceptualize VideoQA as a stochastic computationgraph, where the hidden representations are treated as stochastic variables.This yields two distinct types of uncertainty: one related to the inherentuncertainty in the data and another pertaining to the model's confidence. Inpractice, we seamlessly integrate the VideoQA model into our framework andconduct comprehensive experiments. The findings affirm that our approach notonly achieves enhanced performance but also effectively quantifies uncertaintyin the context of VideoQA.

Answering from Sure to Uncertain: Uncertainty-Aware Curriculum Learning for Video Question Answering