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

Video question answering aims at answering a question about the video contentby reasoning the alignment semantics within them. However, since relyingheavily on human instructions, i.e., annotations or priors, current contrastivelearning-based VideoQA methods remains challenging to perform fine-grainedvisual-linguistic alignments. In this work, we innovatively resort to gametheory, which can simulate complicated relationships among multiple playerswith specific interaction strategies, e.g., video, question, and answer asternary players, to achieve fine-grained alignment for VideoQA task.Specifically, we carefully design a VideoQA-specific interaction strategy totailor the characteristics of VideoQA, which can mathematically generate thefine-grained visual-linguistic alignment label without label-intensive efforts.Our TG-VQA outperforms existing state-of-the-art by a large margin (more than5%) on long-term and short-term VideoQA datasets, verifying its effectivenessand generalization ability. Thanks to the guidance of game-theoreticinteraction, our model impressively convergences well on limited data (${10}^4~videos$), surpassing most of those pre-trained on large-scale data($10^7~videos$).

TG-VQA: Ternary Game of Video Question Answering